KR20230002813A - Systems and methods for decoding barcodes - Google Patents

Abstract

Systems and methods for decoding symbol characters. The method includes: acquiring a symbol image of a symbol including a plurality of symbol characters in a symbol area; determining a plurality of row lines along the length direction of the symbol; determining a plurality of column boundaries among the plurality of symbol characters and a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines; determining, for each of the plurality of symbol characters, a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and decoding the symbol character based on a gray value associated with a character area corresponding to the symbol character.

Description

Systems and methods for decoding barcodes

This application claims priority from Chinese Patent Application No. 202010378011.9 filed on May 7, 2020, the contents of which are hereby incorporated by reference.

The present disclosure relates generally to image processing, and more specifically to systems and methods for decoding barcodes in images.

Portable Data File (PDF) 417 Barcode symbols such as barcodes are widely used in daily life, such as social activities, certificates, management, transportation, payments, and the like. A barcode symbol has a series of bars and spaces that encode high-density data. Barcode symbols can be read from the image using a scanner such as a camera. After the barcode symbol is read from the image, the data encoded in the barcode symbol can be decoded using a processing device. However, during the decoding process, errors usually occur due to factors such as image distortion, uneven lighting, and the like. It would therefore be desirable to provide a system and method for accurately and efficiently decoding barcode symbols.

The present invention provides a system and method for efficiently decoding barcode symbols.

In an aspect of the present disclosure, a system is provided. The system includes at least one storage device for storing a set of instructions; and at least one processor configured to communicate with the at least one storage device. When executing the set of instructions, at least one processor obtains a symbol image of a symbol including a plurality of symbol characters in a symbol area; determining a plurality of row lines along the length direction of the symbol; determining a plurality of column boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters; determine a plurality of row boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; for each of the plurality of symbol characters, determine a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and perform an operation comprising decoding the symbol character based on a gray value associated with a character area corresponding to the symbol character.

In another aspect of the present disclosure, a method is provided. The method is performed on a computing device having a processor and a computer readable storage device. The method includes obtaining a symbol image of a symbol including a plurality of symbol characters in a symbol area; determining a plurality of row lines along the length direction of the symbol; determining a plurality of column boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters; determining a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; determining, for each of the plurality of symbol characters, a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and decoding the symbol character based on a gray value associated with a character area corresponding to the symbol character.

In another aspect of the present disclosure, a non-transitory readable medium is provided. The non-transitory readable medium includes at least one set of instructions, and when executed by at least one processor of a computing device, the at least one set of instructions causes the at least one processor to perform a method. The method includes obtaining a symbol image of a symbol including a plurality of symbol characters in a symbol area; determining a plurality of row lines along the length direction of the symbol; determining a plurality of column boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters; determining a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; determining, for each of the plurality of symbol characters, a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and decoding the symbol character based on a gray value associated with a character area corresponding to the symbol character.

In some implementations, determining the plurality of column boundaries among the plurality of symbol characters based on the plurality of row lines determines a width of a reference symbol character associated with the plurality of symbol characters; determine a reference width range based on the width of the reference symbol character; and determining a plurality of column boundaries among the plurality of symbol characters based on boundary characteristics between adjacent symbol characters and reference width ranges.

In some implementations, the reference symbol character includes a start symbol character or an end symbol character.

In some implementations, determining the width of the reference symbol character may include obtaining a preset codeword string associated with the reference symbol character; identifying, for at least one of the plurality of row lines, at least one reference line segment based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with a predetermined codeword string; and specifying the length of at least one reference line segment as the width of the reference symbol character.

In some implementations, determining the row boundaries among the plurality of symbol characters based on the plurality of row lines includes the row boundaries among the plurality of symbol characters from the plurality of row lines based on the boundary property between adjacent symbol characters. includes identifying

In some implementations, for each of the plurality of symbol characters, decoding the symbol character based on a gray value associated with a character area corresponding to the symbol character into a plurality of blocks along a row direction. share; determine a global gray value of each of the plurality of blocks; determining a contrast value of a symbol character based on the global gray values of the plurality of blocks; and determining the codeword corresponding to the symbol character based on the collation value.

In some implementations, determining the contrast value of the symbol character based on the global gray values of the plurality of blocks includes determining a first ratio of gray values of blocks of the first type to counts of blocks of the first type in the character area; ; determine a second ratio of gray values of blocks of a second type to counts of blocks of a second type in the character area; and determining a contrast value of the symbol character based on the difference value between the first ratio and the second ratio.

In some implementations, the operation further includes determining a start boundary, an end boundary, an upper boundary, and a lower boundary of the symbol region.

In some implementations, determining the starting boundary of the symbol region is based on, for at least one of the plurality of row lines, a gray value of a pixel on at least one of the plurality of row lines and a predetermined gray value associated with the starting codeword string. identify at least one end point of the start symbol character; and determining the starting boundary of the symbol region based on at least one end point of the starting symbol character.

In some implementations, determining an end boundary of the symbol region is based on, for at least one of the plurality of row lines, a gray value of a pixel on at least one of the plurality of row lines and a predetermined gray value associated with the ending codeword string. identify at least one starting point of the ending symbol character; and determining the end boundary of the symbol region based on the starting point of at least one of the ending symbol characters.

In some implementations, determining the upper boundary of the symbol region comprises, for each of the plurality of column boundaries, determining a plurality of intersections of the plurality of row lines and the column boundary; perform an upward traverse until the upper pixel of the first intersection point is identified, and the upper pixel and the first intersection point satisfy the upper boundary characteristic; and determining an upper boundary of the symbol region based on each first intersection of the plurality of column boundaries.

In some implementations, determining the lower boundary of the symbol region includes: determining, for each of the plurality of column boundaries, a plurality of intersections of the plurality of row lines and the column boundary; perform a downward traverse until the lower pixel of the second intersection point is identified, and the lower pixel and the second intersection point satisfy the lower boundary characteristic; and determining a lower boundary of the symbol region based on each second intersection of the plurality of column boundaries.

Additional features will be set forth in part in the ensuing description, and will become apparent in part to those skilled in the art upon review of the following and accompanying drawings, or may be learned by making or operating the embodiments. Features of the present disclosure may be realized and obtained by the practice or use of various aspects of the methodologies, instrumentalities, and combinations set forth in the specific examples discussed below.

The present disclosure is further described in terms of example implementations. These exemplary implementations are specifically described with reference to the drawings. Drawings are not to scale. These implementations are non-limiting example implementations, and like reference numbers indicate like structures throughout the various views of the figures, where:
1 is a schematic diagram showing an exemplary image processing system in accordance with some implementations of the present disclosure;
2 is a schematic diagram illustrating example hardware and/or software components of an example computing device, in accordance with some implementations of the present disclosure;
3 is a schematic diagram showing example components of an example terminal in accordance with some implementations of the present disclosure;
4 is a block diagram illustrating an example processing device in accordance with some implementations of the present disclosure;
5 is a flow diagram illustrating an example process for decoding symbol characters of a symbol into a symbol image, in accordance with some implementations of the present disclosure;
6 and 7 show example PDF 417 barcodes according to some implementations of the present disclosure;
8 is a schematic diagram showing an example row line in a symbol image, in accordance with some implementations of the present disclosure;
9 is a partially exploded view of a PDF 417 barcode, in accordance with some implementations of the present disclosure;
10 is a schematic diagram showing an example row boundary between two adjacent symbol characters, in accordance with some implementations of the present disclosure;
11 shows an example symbol image in accordance with some implementations of the present disclosure;
12 is a flow diagram illustrating an exemplary process for determining a plurality of column boundaries among a plurality of symbol characters in a symbol region of a symbol, in accordance with some implementations of the present disclosure;
13 shows an example symbol image in accordance with some implementations of the present disclosure;
14 is a flow diagram illustrating an exemplary process for decoding symbol characters based on gray values associated with a character area corresponding to the symbol character, in accordance with some implementations of the present disclosure.
15 is a flow diagram illustrating an example process for decoding symbol characters of a symbol into a symbol image, in accordance with some implementations of the present disclosure; And
16 is a schematic diagram of an exemplary PDF 417 barcode, in accordance with some implementations of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS To illustrate technical solutions related to the embodiments of the present disclosure, a brief introduction of drawings referred to in the description of the embodiments is provided below. Obviously, the drawings described below are only some examples or implementations of the present disclosure. A person skilled in the art may apply the present disclosure to other similar scenarios according to these figures without further creative efforts. Like reference numbers in the drawings refer to like structures and operations unless otherwise stated or apparent from context.

As used in the disclosure and appended claims, the singular forms “a,” “an,” and “the” include plural referents unless the content clearly dictates otherwise. As used in this disclosure, the terms "comprises", "comprising", "include" and/or "including" specify the presence of stated steps and elements. However, it will be further appreciated that the presence or addition of one or more other steps and elements is not excluded.

While some modules of the system may be referred to in various ways according to some implementations of the present disclosure, any number of other modules may be used and operated in a client terminal and/or server. These modules are intended to be illustrative and are not intended to limit the scope of the present disclosure. Other modules may be used in other aspects of the systems and methods.

According to some implementations of the present disclosure, flow diagrams are used to depict operations performed by the system. It should be clearly understood that the operations above or below may or may not be executed sequentially. Conversely, the operations may be performed in reverse order or concurrently. Additionally, one or more other operations may be added to the flowchart or one or more operations may be omitted from the flowchart.

Technical solutions of the embodiments of the present disclosure are described with reference to the drawings as described below. It is to be understood that the described embodiments are not exhaustive and not limiting. Other embodiments obtained based on the embodiments presented in this disclosure by those skilled in the art without any creative work are within the scope of this disclosure.

Aspects of the present disclosure relate to systems and methods for image decoding. The system may obtain a symbol image including a plurality of symbol characters in a symbol area. A symbol image may be an image of a symbol (eg, a portable data file (PDF) 417 barcode). A plurality of row lines may be determined along the length direction of the symbol. Each row line may cross pixels on the same row in the symbol area. The system may also determine multiple column boundaries among multiple symbol characters and multiple row boundaries among multiple symbol characters based on the multiple row lines. For each of the plurality of symbol characters, the system may determine a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries. The system may further decode the symbol character based on the gray value associated with the character area corresponding to the symbol character. In this case, the position of each of the plurality of symbol characters is determined more accurately, and the codeword corresponding to the symbol character can be determined more efficiently and accurately, and the decoding process caused by factors such as image distortion, uneven light, and the like Errors in can be reduced or eliminated, thus improving the effectiveness and accuracy of the decoding process.

1 is a schematic diagram illustrating an exemplary image processing system in accordance with some implementations of the present disclosure. The image processing system 100 may process an image or video composed of a plurality of images and extract data from the image or video. As shown, the image processing system 100 includes an image source 101, a processing unit 104, a buffer manager 105, a buffer 106, a transmitter 107, a terminal 108 (or a plurality of terminals ( 108), a network 112, and a network storage device 113 (or a plurality of network storage 113).

Image source 101 may provide an image or video containing at least one image (also referred to as a video frame) of a user of terminal 108 over network 112 . In some implementations, image source 101 may include scanner 102 and/or media server 103 .

The scanner 102 may be capable of capturing an image or a video comprising at least one image. In some implementations, the image can be a symbol image. As used herein, a symbol image may be an image of a symbol. In some implementations, a symbol image can be a video frame obtained from a still image or video. The symbol image may be a two-dimensional (2D) image or a three-dimensional (3D) image. The scanner 102 may be a laser scanner, optical scanner, or the like.

In some implementations, the optical scanner can be a camera. The camera can be, for example, a digital camera, video camera, security camera, web camera, smartphone, tablet, laptop, video gaming console equipped with a web camera, a camera with multiple lenses, and the like.

For illustrative purposes only, a camera may include a lens, shutter, sensor, processing element, and storage element. A lens may be an optical element that focuses a light beam by refraction to form an image. The lens may be configured to take a target object (eg, a bar code on a card, paper, bag, package, etc.). The aperture of the lens may define the size of the hole through which light passes to reach the sensor. The aperture may be adjustable to adjust the amount of light passing through the lens. The focal length of the lens may be adjustable to adjust the range of the camera.

The shutter can be opened to allow light through the lens when an image is captured. The shutter may be manually or automatically controlled by a processing element.

The sensor may be configured to receive light passing through the lens and convert an optical signal of the received light into an electrical signal. The sensor may include a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS). The sensor may communicate with the logic circuitry and may be configured to detect a target object using a lens and convert light received from the target object into an electronic signal.

A processing element may be configured to process data and/or information relating to the camera and/or to control one or more components (eg, lens, shutter) in the camera. For example, the processing element may automatically determine the values of exposure parameters of the camera, such as exposure time, exposure gain, and aperture. The processing element may also adjust the quality (eg, sharpness, contrast, noise level, etc.) of the image taken by the camera.

In some implementations, processing elements can be local or remote. For example, the processing element may communicate with the camera over a network. As another embodiment, the processing element may be integrated into the camera.

A storage element may store data, instructions, and/or any other information. In some implementations, the storage element can store data obtained from the processing element. For example, the storage element may store captured images. In some implementations, the storage element may store data and/or instructions that a processing device may execute or use to perform example methods described in this disclosure. In some implementations, the storage element may include mass storage, removable storage, volatile read and write memory, read only memory (ROM), or the like, or any combination thereof. Exemplary mass storage may include magnetic disks, optical disks, solid state drives, and the like. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, zip disks, magnetic tape, and the like. Exemplary volatile read and write memory may include random access memory (RAM). Exemplary RAMs may include dynamic RAM (DRAM), double-speed synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero-capacitor RAM (Z-RAM), and the like. . Exemplary ROMs include mask ROM (MROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital may include a multi-purpose disk ROM, and the like.

The media server 103 may be a server (eg, a computer or group of computers) for storing or providing an image or a video containing a plurality of images. Media server 103 may also include an image processing element (not shown) configured to process images using the example methods introduced in this disclosure.

Image source 101 may send an image or video to processing unit 104 . The processing device 104 may process images or video. For example, an image or video may include a symbol image. A symbol image may be an image of a symbol. For example, the symbol may be a barcode (eg, Portable Data File (PDF) 417, Code 16K, Code 49, etc.). A symbol may include a plurality of symbol characters in a symbol area. As used herein, a symbol character may refer to the smallest unit for encoding data in a symbol. A symbol area may refer to an area corresponding to at least a portion of a symbol, in which a plurality of symbol characters are located. Processing unit 104 may decode the symbol and generate decoded data corresponding to the symbol.

In some implementations, processing device 104 may be a single server or group of servers. Server groups can be centralized or distributed. In some implementations, the processing device 104 can be local or remote. In some implementations, the processing unit 104 can run on a cloud platform. By way of example only, a cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter cloud, multi cloud, or the like, or any combination thereof. In some implementations, processing device 104 may be executed by computing device 200 having one or more components as shown in FIG. 2 .

Images, video, and/or decoded data corresponding to images or video may be stored in buffer 106 . Buffer 106 may be managed by buffer manager 105 . Buffer 106 may be a storage device for buffering images, video, and/or decoded data corresponding to images or video to be transmitted over network 112 . It can be a remote device from the image source 101 or a local device interpreted by the image source 101, such as a camera's storage medium. Buffer 106 may include mass storage, removable storage, volatile read and write memory, read only memory (ROM), or the like, or any combination thereof. Exemplary mass storage may include magnetic disks, optical disks, solid state drives, and the like. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, zip disks, magnetic tape, and the like. Exemplary volatile read and write memories include dynamic RAM (DRAM), double-speed synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), and zero-capacitor RAM (Z-RAM). It may include random access memory (RAM). Exemplary ROMs include mask ROM (MROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital may include a multi-purpose disk ROM, and the like.

Transmitter 107 may transmit the image, video, and/or decoded data corresponding to the image or video buffered in buffer 106 to network 112 . Transmitter 107 responds to commands sent from video source 101, buffer manager 105, terminal 108, or the like, or a combination thereof, and transmits images, videos, and/or images or videos corresponding to them. Decoded data can be transmitted. Alternatively or additionally, transmitter 107 may voluntarily transmit images, videos, and/or decoded data corresponding to images or video stored in buffer 106 . Transmitter 107 may transmit images, video, and/or decoded data corresponding to the images or video to terminal 108 over network 112 .

Terminal 108 may receive images, videos, and/or decoded data corresponding to images or video transmitted over network 112 . In some implementations, terminal 108 may display images, videos, and/or decoded data corresponding to images or video to a user, or may further perform operations such as payment, authentication of identification, registration, and the like.

Terminal 108 can vary in shape. For example, terminal 108 may include mobile device 109, tablet computer 110, laptop computer 111, or the like, or any combination thereof. In some implementations, mobile device 109 may include a wearable device, a mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some implementations, a wearable device may include a bracelet, shoe, eyeglasses, helmet, watch, clothing, backpack, smart accessory, or the like, or any combination thereof. In some implementations, a mobile device may include a mobile phone, personal digital assistant (PDA), laptop, tablet computer, desktop, or the like, or any combination thereof. In some implementations, the virtual reality device and/or augmented reality device is a virtual reality helmet, virtual reality glasses, virtual reality patch, augmented reality helmet, augmented reality glasses, augmented reality patch, or the like, or any combination thereof. can include For example, virtual reality devices and/or augmented reality devices may include Google Glass™, Oculus Rift™, HoloLens™, Gear VR™, and the like. In some implementations, terminal(s) 108 may be part of a processing engine.

Network 112 may include any suitable network capable of facilitating data transmission. Network 112 may be a public network (eg, the Internet), a private network (eg, a local area network (LAN), a wide area network (WAN)), a wired network (eg, an Ethernet network), a wireless network (eg, a local area network (LAN), a wide area network (WAN)), a wireless network (eg, 802.11 networks, Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), frame relay networks, virtual private networks ("VPNs"), satellite networks, telephone networks, routers, hubs, switches, may be and/or include a server computer, and/or any combination thereof. By way of example only, networks 112 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth™ networks, Zigbee ™ network, a near field communication (NFC) network, or the like, or any combination thereof. In some implementations, network 112 may include one or more network access points.

In some implementations, network 112 may include one or more network storage devices 113 . The network storage device 113 may be a device for buffering or caching data transmitted over the network 112 . Images, video, and/or decoded data corresponding to images or video transmitted by transmitter 107 may be buffered or cached on one or more network storage devices 113 prior to being received by terminal 108. Network storage device 113 may be a server, hub, gateway, or the like, or a combination thereof.

It should be noted that one or more of processing unit 104, buffer manager 105, buffer 106, and transmitter 107 may be stand-alone devices, or modules integrated into image source 101 or another stand-alone device. can For example, one or more of processing unit 104, buffer manager 105, buffer 106, and transmitter 107 may be integrated into scanner 102, media server 103, and/or terminal 108. can As another embodiment, processing unit 104, buffer manager 105, buffer 106, and transmitter 107 communicate with image source 101 via a direct wired connection, network 112, or another network. can be included in a video processing engine capable of As another example, processing unit 104 may be a stand-alone device (eg, a computer or server) while buffer manager 105, buffer 106, and transmitter 107 may be in another stand-alone device. can be included

2 is a schematic diagram illustrating example hardware and/or software components of an example computing device, in accordance with some implementations of the present disclosure. For example, the computing device 200 may be a media server 103 , a processing element of the scanner 102 , and/or an electronic device specialized for image processing. Processing unit 104 and buffer manager 105 may also be executed on computing device 200 . As shown in FIG. 2 , computing device 200 may include a processor 222 , storage 227 , input/output (I/O) 226 , and a communication port 225 .

Processor 222 may execute computer instructions (eg, program code) and perform functions in accordance with the techniques described herein. For example, processor 222 may include interface circuitry and processing circuitry therein. The interface circuitry may be configured to receive electronic signals from the bus (not shown in FIG. 2), the electronic signals encoding structured data and/or instructions for processing circuitry to process. Processing circuitry may perform logical operation calculations and then determine conclusions, results, and/or instructions encoded as electronic signals. The interface circuitry can then send electronic signals from the processing circuitry over the bus.

Computer instructions may include, for example, routines, programs, objects, components, data structures, procedures, modules, and functions that perform specific functions described herein. In some implementations, processor 222 is a microcontroller, microprocessor, reduced instruction set computer (RISC), application specific integrated circuits (ASICs), application specific instruction set processor (ASIP), central processing unit (CPU), graphics processing unit ( GPU), physical processing unit (PPU), microcontroller unit, digital signal processor (DSP), field programmable gate array (FPGA), enhanced RISC machine (ARM), programmable logic unit (PLD), capable of executing one or more functions may include one or more hardware processors, such as any circuitry or processor, or the like, or any combination thereof.

For illustrative purposes only, only one processor is listed in computing device 200 . However, computing device 200 in this disclosure may also include multiple processors, and thus operations and/or method steps performed by one processor as described in this disclosure may also be performed jointly or separately by the multiple processors. It should be mentioned that this can be done by For example, if the processor of computing device 200 in this disclosure executes both steps A and B, then steps A and B may also be performed jointly or separately on computing device 200. may be performed by two or more different processors (e.g., a first processor performs step (A) and a second processor performs step (B), or a first and second processor perform step (B) jointly) (A) and performing steps (B)) should be understood.

Storage 227 includes image source 101, processing unit 104, buffer manager 105, buffer 106, transmitter 107, terminal 108, network 112, network storage device 113, and/or data/information obtained from any other component of the image processing system 100. In some implementations, storage 222 may include mass storage, removable storage, volatile read and write memory, read only memory (ROM), or the like, or any combination thereof. For example, mass storage may include magnetic disks, optical disks, solid state drives, and the like. Removable storage may include flash drives, floppy disks, optical disks, memory cards, zip disks, magnetic tape, and the like. Volatile read and write memory may include random access memory (RAM), which includes dynamic RAM (DRAM), double speed synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), and zero-capacitor RAM (Z-RAM); ROM includes mask ROM (MROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital versatile disk ROM, etc. In some implementations, storage 222 may store one or more programs and/or instructions to perform example methods described in this disclosure. For example, storage 222 may store programs for processing engines (eg, media server 103, processing device 104) to decode symbol images.

I/O 226 may input and/or output signals, data, information, and the like. In some implementations, I/O 226 may include input devices and output devices. Examples of input devices may include a keyboard, mouse, touch screen, microphone, or the like, or combinations thereof. Examples of output devices may include display devices, loudspeakers, printers, projectors, or the like, or combinations thereof. Examples of display devices may include liquid crystal displays (LCDs), light emitting diode (LEDs)-based displays, flat panel displays, curved screens, television devices, cathode ray tubes (CRTs), touch screens or the like, or combinations thereof. can

Communications port 225 may be coupled to a network (eg, network 112 ) to facilitate data communication. The communication port 225 is an image source 101, a processing unit 104, a buffer manager 105, a buffer 106, a transmitter 107, a terminal 108, a network 112, a network storage device 113 , and/or any other component of the image processing system 100. A connection can be a wired connection, a wireless connection, any other communication connection that can enable data transmission and/or reception, and/or any combination of these connections. Wired connections may include, for example, electrical cables, optical cables, telephone lines, or the like, or any combination thereof. A wireless connection may be, for example, a Bluetooth™ link, a Wi-Fi™ link, a Wimax™ link, a WLAN link, a ZigBee link, a mobile network link (eg, 3G, 4G, 5G), or the like, or a combination thereof. can include In some implementations, communication port 225 may be and/or include a standardized communication port such as RS232, RS485, or the like. In some implementations, communication port 225 may be a specially designed communication port.

3 is a schematic diagram showing example components of an example terminal in accordance with some implementations of the present disclosure. As shown in FIG. 3 , the terminal 300 includes a communication platform 320, a display 310, a graphics processing unit (GPU) 330, a central processing unit (CPU) 330, and an I/O port 350. ), memory 360, and storage 390. In some implementations, any other suitable component may also be included in terminal 300, including but not limited to a system bus or controller (not shown). In some implementations, mobile operating system 370 (eg, iOS™, Android™, Windows Phone™) and one or more applications 380 are transferred from storage 390 to memory 360 to be executed by processor 340 . ) can be loaded. Terminal 300 may be an implementation of terminal 108 .

To implement the various modules, units, and functions described in this disclosure, a computer hardware platform may be used as the hardware platform(s) for one or more of the elements described herein. A computer with user interface elements may be used to run a personal computer (PC) or any other type of workstation or terminal device. A computer can also act as a server if properly programmed.

4 is a block diagram illustrating an exemplary processing device according to some implementations of the present disclosure. As shown in FIG. 4 , the processing unit 104 may include an acquisition module 410 , a row line determination module 420 , a character area determination module 430 , and a decoding module 440 .

The acquiring module 410 may acquire data/information. In some implementations, the acquisition module 410 may obtain a symbol image of a symbol including a plurality of symbol characters. In some implementations, a symbol in a symbol image may be a barcode. Exemplary barcodes may include Code 16K, Code 49, PDF 417, Micro PDF 417, Code One, Maxicode, Quick Response (QR) Code, Data Matrix, HanXin Code, Grid Matrix, and the like. In some implementations, the data/information obtained may further include processed results, user instructions, algorithms, program code, or the like, or combinations thereof.

The row line determination module 420 may determine a plurality of row lines in the symbol image along the length direction of the symbol. In some implementations, processing unit 104 can identify an edge of a symbol. The edge of a symbol can be identified based on the pixels in the symbol image. In some implementations, processing device 104 can dynamically adjust the size, position, and/or orientation of the positioning box until the edge of the symbol coincides with or substantially coincides with the edge of the positioning box. In some implementations, each of the plurality of row lines can be determined by connecting a pixel to the same row in a positioning box.

The character area determination module 430 may determine a character area corresponding to a symbol character for each of a plurality of symbol characters. In some implementations, a character area corresponding to the symbol character for each of the plurality of symbol characters may be determined based on a plurality of column boundaries and a plurality of row boundaries of a symbol area including the plurality of symbol characters. The character area determination module 430 may obtain the plurality of row lines from the row line determination module 420 and determine the plurality of column boundaries and the plurality of row boundaries based on the plurality of row lines. Details regarding the determination of the plurality of column boundaries and the plurality of row boundaries may be found elsewhere in this disclosure, such as in FIGS. 5, 12, and 15, and related descriptions thereof.

The decoding module 440 may decode each symbol character based on the gray value associated with the character area corresponding to the symbol character.

For each character area, decoding module 440 may divide the character area into a plurality of blocks. Each of the plurality of blocks may include one or more pixels (eg, 1×4 pixels (ie, 1 pixel in a row and 4 pixels in a column)). A gray value of one or more pixels of a block may be obtained. A block's global gray value may be an overall representation of the gray values of one or more pixels of the block.

In some implementations, the decoding module 440 may determine a contrast value of a symbol character corresponding to a character area based on the global gray values of the plurality of blocks. The decoding module 440 may determine a codeword corresponding to the symbol character based on the reference value. In some implementations, decoding module 440 can obtain a plurality of preset codewords (eg, 2787 codewords). Each of the plurality of codewords may correspond to a predetermined codeword string. A reference collation value of each of the plurality of preset codewords may be determined based on the corresponding predetermined codeword string. Then, the processing unit 104 determines a similarity value between each of the plurality of preset codewords and the symbol character based on the reference collation value of each codeword and the collation value of the symbol character. The decoding module 440 may determine a codeword corresponding to the symbol character based on the similarity value. A codeword corresponding to a symbol character may be or include decoded data (eg, number, character, vector, etc.) corresponding to a symbol in a symbol image.

Modules in the processing device 104 may be connected to or communicate with each other via wired or wireless connections. Wired connections may include metal cables, optical cables, hybrid cables, or the like, or any combination thereof. A wireless connection may include Local Area Network (LAN), Wide Area Network (WAN), Bluetooth, ZigBee, Near Field Communication (NFC), or the like, or any combination thereof. Two or more of the modules may be combined into a single module, and any one of the modules may be divided into two or more units. For example, processing device 104 may include a storage module (not shown) configured to store information and/or data (eg, scanning data, images) associated with the modules noted above.

5 is a flow diagram illustrating an example process for decoding symbol characters of a symbol into a symbol image, in accordance with some implementations of the present disclosure. In some implementations, process 500 can be executed on image processing system 100 shown in FIG. 1 . For example, process 500 may be stored in the form of instructions on a storage medium (eg, network storage device 113 or storage 227 of computing device 220) and may be performed by processing device 104. can be called and/or executed. It is intended to illustrate the operation of process 500 presented below. In some implementations, process 500 can be accomplished with one or more additional actions not described and/or without one or more of the discussed actions. Additionally, the order in the operation of process 500 as shown in FIG. 5 and described below may not be intended to be limiting.

At 510, the processing device 104 (eg, the processor 222 or the acquisition module 410) may obtain a symbol image including a plurality of symbol characters in a symbol region.

A symbol image may be an image of a symbol. In some implementations, the symbol image may be obtained from image source 101 (eg, scanner 102 or media server 103) of image processing system 100. In some implementations, a symbol in a symbol image may be a barcode. Exemplary barcodes may include Code 16K, Code 49, PDF 417, Micro PDF 417, Code One, Maxi Code, Quick Response (QR) Code, Data Matrix, Hanshin Code, Grid Matrix, and the like. Unless explicitly stated otherwise, the following description is provided for illustration and not intended to be limiting with reference to the PDF 417 barcode.

A PDF 417 barcode can be a symbol with a stacked linear barcode format. For illustrative purposes only, exemplary PDF 417 barcodes are shown in FIGS. 6 and 7 . As shown in FIG. 6, a PDF 417 barcode may include a start symbol character (also referred to as a start pattern) A, a symbol area B, and an end symbol character (also referred to as a stop pattern) C. The start symbol character A, the symbol area B, and the end symbol character C may be sequentially arranged along the length direction of the symbol (eg, as shown in FIG. 6). Symbol region B may include four boundaries. The four boundaries include a start boundary (i.e., the boundary separating symbol area B from starting symbol character A), an ending boundary (i.e., the boundary separating symbol area B from ending symbol character C), an upper boundary, and a lower boundary. can do. A PDF417 barcode may include a plurality of symbol characters in symbol area B. Each of a plurality of symbol characters in the symbol area may be represented by a combination of 4 bars and 4 spaces. The four bars and four spaces may alternatively be arranged. In some implementations, the 4 bars and 4 spaces can be made up of 17 blocks. Each of the four bars and four spaces may correspond to a specific number or count of blocks along the length of the symbol. A specific number of blocks or an arrangement of counts corresponding to each of the bars and spaces along the length direction of the symbol can be expressed as a codeword string corresponding to the symbol character. Data encoded in symbol characters can be decoded based on the codeword string.

For illustrative purposes only, exemplary symbol characters are provided in FIG. 7 . As shown in FIG. 7, the symbol text 700 may be in a dotted box. The symbol character 700 may include 4 bars and 4 spaces. The 4 bars and 4 spaces can be represented by the black and white parts of the dotted box, respectively.

In some implementations, the 4 bars and 4 spaces can be made up of 17 blocks, labeled numbers 1 through 17 above symbol character 700 as shown in FIG. 7 . The 17 blocks may have the same width along the length direction of the symbol (eg, the horizontal direction in FIG. 7 ). Each block may have a stripe shape. A length direction of each stripe may be perpendicular to a length direction of a symbol (eg, a symbol width direction).

For the symbol character 700, the first bar corresponds to 5 blocks, the first space corresponds to 1 block, the second bar corresponds to 1 block, and the second space corresponds to 1 block. , the third bar corresponds to one block, the third space corresponds to one block, the fourth bar corresponds to two blocks, and the fourth space corresponds to five blocks. Illustratively, the width of each of the four bars and spaces may be labeled under the corresponding bars or spaces in FIG. 7 . In this case, the symbol character 700 represented by bars and spaces can be represented by the codeword string 51111125. Data (eg, numbers, text, etc.) encoded in the symbol character 700 can be decoded based on the codeword string 51111125.

Each block in the symbol image may correspond to one or more pixels of the symbol image. Just for a better understanding of the present disclosure, each block may be represented by 1×4 pixels in a symbol image (ie, 1 pixel in a row and 4 pixels in a column as shown in FIG. 9 ). The direction of a row (also referred to as a row direction) may be parallel to the length direction of a symbol. The direction of a column (also referred to as a column direction) may be parallel to the width direction of a symbol. It should be mentioned that this is for illustrative purposes and is not intended to be limiting. A block corresponds to any number or count of pixels, such as 1x3 pixels (i.e. 1 pixel per row and 3 pixels per column), 2x7 pixels (i.e. 2 pixels per row and 7 pixels per column), etc. can do.

The PDF 417 barcode may further include a first quiet zone and a second quiet zone (not shown). The first quiet zone and the second quiet zone may be located on both sides of the symbol along the length direction. The first quiet zone and/or the second quiet zone may be a space (ie, a white area) having a preset width.

At 520, processing unit 104 (eg, processor 222, row line determination module 420) may determine a plurality of row lines along the length of the symbol.

In some implementations, upon obtaining a symbol image, processing unit 104 can use a positioning box to determine the length direction of the symbol. In some implementations, the positioning box can be a rectangular box. In some implementations, processing unit 104 can identify an edge of a symbol. The edge of a symbol can be identified based on the pixels in the symbol image. For example, the processing device 104 may obtain gray values of all pixels in the symbol image. Since the color of the bar of the start symbol character, the end symbol character, and the plurality of symbol characters in the symbol is black, the gray value of the pixel corresponding to the bar may be relatively small (eg, 0). The processing unit 104 can identify the edge of a symbol based on the gray value of the pixel. The processing unit 104 may adjust the size, position, and/or orientation of the positioning box based on the identified edge of the symbol. The orientation of the positioning box may be parallel to the longitudinal direction of the positioning box. In some implementations, processing device 104 can dynamically adjust the size, position, and/or orientation of the positioning box until the edge of the symbol coincides with or substantially coincides with the edge of the positioning box. The orientation of the positioning box can be determined as the length direction of the symbol.

After the length direction of the symbol is determined, processing unit 104 may determine a plurality of row lines. In some implementations, the pixels in the positioning box can be in a first plurality of rows and a second plurality of columns. A row direction of each of the first plurality of rows may be parallel to a length direction of the symbol. A column direction of each of the second plurality of columns may be perpendicular to the length direction of the symbol. In some implementations, each of the plurality of row lines can be determined by connecting a pixel to the same row in a positioning box. Alternatively, multiple scan lines may be determined. In some implementations, multiple scan lines can be parallel to the length direction of a symbol. Each scan line may cross pixels on the same row in the positioning box. Multiple scan lines can be determined as row lines. In some implementations, at least one of the plurality of row lines can be straight. In some implementations, at least one of the plurality of row lines can be curved. Each of each of two neighboring row lines of the plurality of row lines may have the same distance or different distances.

For illustrative purposes only, an exemplary row line in a symbol image may be shown in FIG. 8 . Symbol image 800 may include symbol 810 . The pixels in the symbol image 800 may be in eight rows. Thus, eight row lines can be determined by connecting pixels to the same row. As shown in FIG. 8, eight row lines L1 to L8 may be determined. L1 through L8 may cross pixels in different rows of symbol 810 .

At 530, processing unit 104 (e.g., processor 222, character area determination module 430) may determine a plurality of column boundaries among the plurality of symbol characters based on the plurality of row lines.

Regarding the PDF 417 barcode, multiple symbol characters in the symbol area may be in a stacked arrangement. For example, a plurality of symbol characters may be arranged in multiple rows and columns in a symbol area. A column boundary may refer to a boundary between two adjacent columns of symbol characters.

The processing unit 104 may determine a plurality of column boundaries between the plurality of symbol characters. Each of the plurality of column boundaries may correspond to two adjacent columns of symbol characters of the plurality of symbol characters. In some implementations, the plurality of column boundaries may be determined based on the plurality of row lines. In some implementations, the plurality of column boundaries may be determined by identifying pixels on the column boundary corresponding to two adjacent columns of the plurality of symbol characters from the plurality of row lines.

In some implementations, processing unit 104 can determine the width of a reference symbol character associated with a plurality of symbol characters. A reference symbol character can refer to a symbol character specific to a symbol. A reference symbol character can be used to determine the width of a symbol character in a symbol area. In some implementations, the reference symbol character is a start symbol character (eg, start symbol character A as shown in FIG. 6 ) or an end symbol character (eg, end symbol character C as shown in FIG. 6 ). can be Regarding the PDF 417 barcode, multiple symbol characters in the symbol area may have the same width. The width of the start symbol character may be the same as the width of the symbol character in the symbol area. The width of the end symbol character may be proportional to the width of the symbol character in the symbol area.

In some implementations, processing unit 104 can identify a start symbol character and an end symbol character from the symbol image. The start symbol character and the end symbol character may be from the symbol area. The start symbol character may include a start edge and an end edge along the row direction of the symbol. For PDF 417 barcodes, the ending edge of the start symbol character may coincide with the start boundary of the symbol area. The processing unit 104 may determine the start boundary of the symbol region by determining the end edge of the start symbol character. The ending symbol character may also include a starting edge and an ending edge along the row direction of the symbol. The start edge of the end symbol character may coincide with the end boundary of the symbol area. The processing unit 104 may determine the end boundary of the symbol region by determining the start edge of the end symbol character. A plurality of column boundaries may be determined between the start boundary and the end boundary of the symbol region.

In some implementations, the processing unit 104 can determine the reference width range based on the width of the reference symbol character. Theoretically, for a PDF 417 barcode, the width of the start symbol character can be equal to the width of each symbol character in the symbol area. The width of the end symbol character may be proportional to the width of each symbol character in the symbol area. However, the width of a symbol character may change in an actual position due to various factors, for example distortion of a symbol image. Accordingly, the processing device 104 can determine a reference width range having various factors taken into account. The reference width range may be a range in which the width of symbol characters of a plurality of characters may vary. In some implementations, the reference width range increases and/or decreases (eg, 0.2 millimeter, 0.5 millimeter, 1 millimeter, 1 pixel, 2 pixels) the width of the reference symbol character. , 0.2 mm, 0.5 mm, 1 mm, 1 pixel, 2 pixels). Increments and/or decrements can be defined as errors corresponding to symbol characters. In some implementations, the reference width range may be adjustable under different circumstances, such as different brightness conditions, different image resolutions, different image quality (eg, noise levels), and the like.

The processing unit 104 may determine a plurality of column boundaries among a plurality of symbol characters based on boundary characteristics between adjacent symbol characters and the reference width range. For a PDF 417 barcode, the fourth space of the current symbol character may be continuous with the first bar of adjacent symbol characters along the row direction of the symbol. The column boundary between two adjacent symbol characters in the row direction is such that the color of the last block in the fourth space of the current symbol character and the color of the first block in the first bar of the adjacent symbol character change from white to black along the row direction. properties (also referred to as thermal boundary properties). Thus, a gray value of a pixel of a block may decrease from 255 to 0 along the row direction, for example. More description regarding the determination of the plurality of thermal boundaries can be found elsewhere in this disclosure, for example in FIG. 12 and its description.

At 540, processing unit 104 (e.g., processor 222, character area determination module 430) may determine a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines.

For each of the plurality of column boundaries, processing unit 104 may determine a plurality of intersections (eg, pixels) of the plurality of row lines and the column boundary. The processing unit 104 may perform an upward traverse and identify an upper intersection among the plurality of intersections. An upward traverse may refer to an operation to traverse an intersection point-by-point upward along a column boundary. The pixel above the upper intersection along the column boundary (also referred to as the upper pixel) and the pixel following the upper pixel along the row direction in the same row (also referred to as the pixel following the upper pixel) can be determined. The top pixel and the pixels that follow it may be located on the other side of the column boundary.

In a PDF 417 barcode, the upper boundary of the symbol region is such that the upper pixel and the pixel following the upper pixel along the row direction do not satisfy the column boundary characteristic, and the reference pixel below the upper pixel along the column boundary (e.g., intersection) and pixels following the reference pixel along the row direction may have characteristics that satisfy the column boundary characteristics (also referred to as upper boundary characteristics). The reference pixel and the pixels following the reference point may be on the upper boundary of the symbol region.

Processing unit 104 may determine whether the top intersection and the pixel that follows the top intersection, and the top pixel and the pixel that follows the top pixel satisfy the column boundary characteristics (i.e., the color of the top pixel and the pixel that follows the top pixel). The color of the next pixel is black, and the color of the two pixels may change from white to black along the row direction). If the top pixel and the pixel following it do not satisfy the column boundary property and the top intersection and the pixel following the top intersection along the row direction satisfy the column boundary property (if the top pixel and the top intersection satisfy the top boundary property) Also referred to as), the upper intersection point and the subsequent intersection point of the upper pixel may be on the upper boundary of the symbol region.

In some implementations, a RANSAN algorithm can be used to determine the upper boundary of the symbol region based on the upper pixel and the pixels following the upper pixel corresponding to each of the plurality of column boundaries.

Similarly, for each of the plurality of thermal boundaries, processing device 104 may perform a downward traverse and identify a lower intersection among the plurality of intersections. A downward traverse may refer to an operation to traverse an intersection point-by-point downward along a column boundary. A pixel under the lower intersection along a column boundary (also referred to as a lower pixel) and a pixel succeeding the lower pixel along a row direction in the same row (also referred to as a pixel following a lower pixel) may be determined. The bottom pixel and the pixels that follow it may be located on the other side of the column boundary.

For PDF 417 barcodes, the lower boundary of the symbol region is such that the lower pixel and the pixel following the lower pixel along the row direction do not satisfy the column boundary characteristics, and the reference pixel above the lower pixel along the column boundary (e.g., the intersection point ) and a pixel following the reference pixel along the row direction may have a property (also referred to as a lower border property) that satisfies the column boundary property. The reference pixel and the pixels following the reference point may be on the lower boundary of the symbol region.

The processing unit 104 may determine whether the lower intersection point and the pixel that follows the lower intersection point, and the lower pixel and the pixel that follows the lower pixel satisfy the column boundary property. If the bottom pixel and the pixels following it do not satisfy the column boundary property and the bottom intersection and the pixels following the bottom intersection along the row direction satisfy the column boundary property (the bottom pixel and the bottom intersection satisfy the bottom boundary property). Also referred to as ), it may indicate that the lower intersection point and the pixel that follows the lower intersection point may be on the lower boundary of the symbol region.

In some implementations, a RANSAN algorithm can be used to determine the lower boundary of the symbol region based on the lower pixel and the pixels that follow the lower pixel corresponding to each of the plurality of column boundaries.

After the upper and lower boundaries of the symbol region are determined, a plurality of row boundaries between the upper and lower boundaries of the symbol region may be determined. As used herein, a column boundary may refer to a boundary between two adjacent rows of symbol characters.

The processing unit 104 may determine multiple row boundaries between multiple symbol characters. Each of the plurality of row boundaries may correspond to two adjacent rows of symbol characters of the plurality of symbol characters. In some implementations, the plurality of row boundaries can be determined based on the plurality of row lines. In some implementations, multiple row boundaries can be determined by specifying multiple row boundaries from multiple row lines based on boundary properties between adjacent symbol characters.

In some implementations, the widths of the bars and spaces between two adjacent symbol characters in the column direction may vary. Thus, for a row boundary between two adjacent symbol characters in the column direction, the color of all pixels on the row boundary is the same as the color of corresponding pixels on the first adjacent row line of the row boundary, and the color of at least one pixel on the row boundary This row boundary may have characteristics (also referred to as row boundary characteristics) that may differ from the color of the corresponding pixel on the second adjacent row line. In some implementations, a first adjacent row line can be above a row boundary and a second adjacent row line can be below a row boundary. Alternatively, the first adjacent row line may be below the row boundary and the second adjacent row line may be above the row boundary. In this case, the gray value of every pixel on the row boundary may be equal to or close to the gray value of a corresponding pixel on a first adjacent row line of the row boundary, and the gray value of at least one pixel on the row boundary is may be different from the gray value of the corresponding pixel on the second adjacent row line of .

10 is a schematic diagram illustrating an exemplary row boundary between two adjacent symbol characters, in accordance with some implementations of the present disclosure. As shown in FIG. 10, the symbol character P can be expressed as 41111144. For the symbol character P, row lines L1 - L4 can be determined, each connecting pixels in the same row. The symbol character (Q) can be expressed as 41111315. For the symbol letter Q, row lines L5 - L8 can be determined, each connecting pixels in the same row. For row line L4, the gray value of every pixel on row line L3 may be equal to or close to the gray value of the corresponding pixel on row line L4. A gray value of at least one pixel on the row line L5 (eg, a pixel in a rectangular box as shown in FIG. 10 ) may be different from a gray value of a corresponding pixel on the row line L4 . Pixels on row line L4 may satisfy row boundary characteristics. Thus, row line L4 can be determined as a row boundary between symbol character P and symbol character Q.

In some implementations, the number or count of pixels in a symbol image can be relatively large (ie, the symbol image can be high resolution (eg, 7680×4320 pixels)). In some implementations, instead of traversing every pixel on each row line, processing unit 104 can sample a specific number or count of pixels on each row line from every pixel on each row line, each Multiple row boundaries can be determined among multiple symbol characters based on the sampled pixels on the row lines of . In some implementations, instead of traversing all of the plurality of row lines, processing unit 104 can sample a specific number or count of row lines from on the plurality of row lines, and based on the sampled row lines, the plurality of row lines. Multiple line boundaries can be determined among symbol characters.

At 550, processing unit 104 (e.g., processor 222, character area determination module 430) determines the symbol for each of the plurality of symbol characters based on the plurality of column boundaries and the plurality of row boundaries. A character area corresponding to a character may be determined.

Since the start boundary, end boundary, upper boundary, and lower boundary of the symbol area are determined, a plurality of column boundaries and a plurality of row boundaries can divide the symbol area into a plurality of character areas. Each of the plurality of character areas may correspond to one of a plurality of symbol characters.

At 560, processing unit 104 (e.g., processor 222, decoding module 440) may decode each symbol character based on the gray value associated with the character region corresponding to the symbol character. .

As for each text area, the processing unit 104 can divide the text area into a plurality of blocks. In some implementations, a character area can be divided into multiple blocks (eg, 17 blocks) along a row direction. The processing unit 104 may determine a global gray value of each of the plurality of blocks. Each of the plurality of blocks may include one or more pixels (eg, 1×4 pixels (ie, 1 pixel in a row and 4 pixels in a column)). A gray value of one or more pixels of a block may be obtained. A block's global gray value may be an overall representation of the gray values of one or more pixels of the block. In some implementations, a block's global gray value can be an average value of gray values of one or more pixels in the block.

In some implementations, the processing unit 104 may determine a contrast value of the symbol character corresponding to the character area based on the global gray values of the plurality of blocks. In some implementations, the processing unit 104 divides a first type of block (e.g., a block belonging to a space of symbol characters) and a second type of block (e.g., a symbol character's block) from a plurality of blocks in the character area. block belonging to the bar) can be specified. The contrast value of the symbol character may be determined based on at least a global gray value of the first type block and a global gray value of the second type block.

After the comparison value of the symbol character corresponding to the character area is determined, the processing unit 104 may determine a codeword corresponding to the symbol character based on the comparison value. In some implementations, the processing unit 104 can obtain a plurality of preset codewords (eg, 2787 codewords). Each of the plurality of codewords may correspond to a predetermined codeword string. A reference collation value of each of the plurality of preset codewords may be determined based on the corresponding predetermined codeword string. Then, the processing unit 104 determines a similarity value between each of the plurality of preset codewords and the symbol character based on the reference collation value of each codeword and the collation value of the symbol character. The processing unit 104 may determine a codeword corresponding to the symbol character based on the similarity value. A codeword corresponding to a symbol character may be or include decoded data (eg, a number, text, vector, etc.) corresponding to a symbol in a symbol image. Details regarding the decoding of symbol characters may be found elsewhere in this disclosure, for example in FIG. 14 and its description.

In some implementations, the decoded data may be transmitted by transmitter 107 over network 112 to terminal 108 . Terminal 108 may accept decoded data corresponding to a symbol in a symbol image via network 112 and display the decoded data to a user or perform additional operations such as payment, identity authentication, registration, and the like.

According to some implementations of the present disclosure, the processing unit 104 determines a plurality of column boundaries among a plurality of symbol characters and a plurality of row boundaries, column boundary characteristics, and row boundary characteristics among a plurality of symbol characters based on row lines. can The symbol area may be segmented into a plurality of character areas based on a plurality of column boundaries among a plurality of symbol characters and a plurality of row boundaries among a plurality of symbol characters. Then, the processing unit 104 may decode the symbol character corresponding to each of the plurality of character areas based on the gray value associated with the character area corresponding to the symbol character. In this case, the position of each of the plurality of symbol characters is determined more accurately, and the codeword corresponding to the symbol character can be determined more efficiently and accurately based on the plurality of preset codewords, image distortion, uneven light Errors in the decoding process caused by factors such as and the like can be reduced or eliminated, thus improving the effectiveness and accuracy of the decoding process.

It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of the present disclosure. For those skilled in the art, multiple variations and modifications may be made in light of the teachings of this disclosure. However, such variations and modifications do not depart from the scope of the present disclosure.

In some implementations, the upper and lower boundaries of a symbol region may be determined in a variety of ways. As shown in FIG. 11 , a symbol image 1100 including a symbol 1110 is provided. A plurality of scan lines L ₁ to L _n may be determined in the symbol image 1100 . Two adjacent scan lines among the plurality of scan lines L ₁ to L _n may have the same distance or different distances. The plurality of scan lines L ₁ to L _n may be parallel to the length direction of the symbol 1110 . Each of the plurality of scan lines (L ₁ -L _n ) may cross pixels in the same row in the symbol region ABCD. The processing device 104 may determine a plurality of column boundaries (S ₁ to S _n ) between a plurality of symbol characters in the symbol region ABCD. In some implementations, the plurality of thermal boundaries (S ₁ -S _n ) may be determined based on the plurality of scan lines (L ₁ -L _n ).

For each of the plurality of thermal boundaries S ₁ -S _n , the processing device 104 may determine a plurality of intersections of the plurality of scan lines and the column boundary. The processing device 104 may identify an intersection point (also referred to as an upper intersection point) at an uppermost position among the plurality of intersection points. Processing unit 104 may further perform an upward traverse from the intersection point to the top position until an upper point is identified. An upward traverse may be an operation to traverse the location above the junction to the top location one-by-one up along the column boundary. For PDF 417 barcodes, the upper boundary (L _u ) of the symbol area ABCD is such that the upper point and the point following the upper point along the row direction do not satisfy the column boundary characteristics, and the reference point below the upper point along the column boundary and A point following the reference point along the row direction may have a property (also referred to as an upper boundary property) that satisfies the column boundary property. The reference point and the points following the reference point may be on the upper boundary L _u of the symbol region ABCD. In some implementations, the upper point, the reference point, the point following the upper point, and/or the point following the reference point may differ from the intersection at the topmost location. In some implementations, the top point, the reference point, the point following the top point, and/or the point following the reference point can be a pixel.

Depending on the upper boundary property, the upper point and the point following the upper point along the row direction (also referred to as the point following the upper point) can be determined. The top point and the point following the top point may be located on the other side of the thermal boundary. The processing device 104 may determine whether the upper point and the point following the upper point, and the reference point below the upper point and the point following the reference point satisfy the thermal boundary characteristic. If the top point and the point following the top point, and the reference point below the top point and the point following the reference point satisfy the thermal boundary property (i.e., the top point and the reference point satisfy the top boundary property), then it is a reference point. It may indicate that the point following the point and the reference point may be on the upper boundary (L _u ) of the symbol region ABCD. In some implementations, the upper boundary (L _u ) of the symbol region ABCD may be determined based on a plurality of reference points corresponding to the plurality of column boundaries (S ₁ -S _n ). In some implementations, the RANSAN algorithm can be used to determine the upper boundary (L _u ) of the symbol region ABCD based on a plurality of reference points. Similarly, the lower boundary (L _d ) of the symbol region ABCD can be determined.

12 is a flow diagram illustrating an example process for determining a plurality of column boundaries among a plurality of symbol characters in a symbol region of a symbol, in accordance with some implementations of the present disclosure. In some implementations, process 1200 can be executed on image processing system 100 shown in FIG. 1 . For example, process 1200 may be stored in the form of instructions on a storage medium (eg, network storage device 113 or storage 227 of computing device 220) and performed by processing device 104. can be called and/or executed. It is intended to illustrate the operation of process 1200 presented below. In some implementations, process 1200 can be accomplished with one or more additional actions not described and/or without one or more of the discussed actions. Additionally, the order in the operation of process 1200 as shown in FIG. 12 and described below may not be limiting.

At 1210, processing unit 104 may determine a width of a reference symbol character associated with the plurality of symbol characters.

In some implementations, the reference symbol character can be a start symbol character or an end symbol character. Regarding the PDF 417 barcode, multiple symbol characters in the symbol area may have the same width. The width of the start symbol character may be the same as the width of the symbol character in the symbol area. The width of the end symbol character may be proportional to the width of the symbol character in the symbol area.

In some implementations, processing unit 104 can obtain a codeword string corresponding to the reference symbol character. A codeword string corresponding to a reference symbol character may also be referred to as a predetermined codeword string. In some implementations, the predetermined codeword string may be a standard codeword string. In some other implementations, the predetermined codeword string corresponding to the reference symbol character may be determined by a user according to default settings of the image processing system 100 or the like.

In some implementations, processing unit 104 can determine the arrangement and/or width of bars and spaces of reference symbol characters based on a predetermined codeword string. In some implementations, processing unit 104 may further determine gray values of at least a portion of the pixels corresponding to the bars and spaces of the reference symbol character. By way of example only, at least a portion of the pixels may be, for example, pixels in at least one row corresponding to the bars and spaces of the reference symbol character. A gray value of at least a portion of a pixel may be referred to as a predetermined gray value.

After the predetermined gray value is determined, the processing unit 104 may compare the gray value of the pixel on at least one of the plurality of row lines with the predetermined gray value corresponding to the reference symbol character. Based on the comparison, processing device 104 may identify at least one line segment on at least one row line. A gray value of a pixel of at least one line segment may match a predetermined gray value. The processing unit 104 may indicate the length of at least one line segment as the width of the reference symbol character.

For a PDF 417 barcode, the predetermined codeword string corresponding to the start symbol character (also referred to as the start codeword string) may be 81111113. For illustration only, each of the 17 blocks constituting a symbol character is represented by one pixel in the symbol image. A pixel may be represented by black and white dots, as shown in FIG. 13 . The start symbol character 1310 is eight pixels as first bar, one pixel as first space, one pixel as second bar, one pixel as second space, one pixel as third bar, third space It may include one pixel as , one pixel as the fourth bar, and three pixels as the fourth space. A gray value (ie, a predetermined gray value) of a pixel corresponding to the start symbol character 1310 may be determined. Processing device 104 can identify at least one line segment 1030 on row line 1320 based on the predetermined gray value. A gray value of a pixel of at least one line segment 1330 may match a predetermined gray value. The processing unit 104 may indicate the length of the line segment 1320 as the width of the start symbol character. The predetermined codeword string (also referred to as the ending codeword string) corresponding to the ending symbol character may be 711311121. The width of the end symbol character can be similarly determined.

In some implementations, processing unit 104 can identify a reference symbol character from a symbol image when at least one line segment is determined. Each of the line segments may include a start point and an end point. The starting points of two or more line segments may form the starting edges of reference symbol characters. The ending points of two or more line segments may form the ending edge of a reference symbol character.

Specifically, processing unit 104 may identify two or more line segments corresponding to start symbol characters on multiple row lines. The ending points of two or more line segments corresponding to the start symbol character (also referred to as the end points of the start symbol character) may form the end edges of the start symbol character. In some implementations, a random samples consensus (RANSAN) algorithm can be used to determine the ending edge of the start symbol character based on the ending points of the two or more line segments corresponding to the start symbol character. In some implementations, the ending edge of the start symbol character can be determined by fitting lines according to the RANSAN algorithm based on the ending points of two or more line segments corresponding to the start symbol character. For PDF 417 barcodes, the starting symbol character can be from the symbol area. The end edge of the start symbol character may coincide with the start boundary of the symbol area. In this case, the starting boundary of the symbol region can be determined.

Similarly, processing unit 104 may identify two or more line segments corresponding to end symbol characters on multiple row lines. The starting point of two or more line segments corresponding to the ending symbol character (also referred to as the starting point of the ending symbol character) may form the starting edge of the ending symbol character. In some implementations, the RANSAN algorithm can be used to determine the starting edge of the ending symbol character based on the starting points of the two or more line segments corresponding to the ending symbol character. For PDF 417 barcodes, the ending symbol character can be from the symbol area. The start edge of the start symbol character may coincide with the end boundary of the symbol area. In this case, the end boundary of the symbol region can be determined. A plurality of column boundaries may be determined between the start boundary and the end boundary of the symbol region.

At 1220, processing unit 104 may determine a reference width range based on the width of the reference symbol character.

In some implementations, the reference width range increases and/or decreases the width of the reference symbol character by increments (eg, 0.2 millimeters, 0.5 millimeters, 1 millimeter, 1 pixel, 2 pixels, etc.) eg, 0.2 millimeters, 0.5 millimeters, 1 millimeter, 1 pixel, 2 pixels, etc.). Increments and/or decrements can be defined as errors corresponding to symbol characters. In some implementations, each of the plurality of symbol characters may correspond to the same error. In some implementations, at least one of the plurality of symbol characters may correspond to another error.

If the reference symbol character is a start symbol character, the processing unit 104 may determine a reference width range for each of a plurality of symbol characters in the symbol area based on the width of the start symbol character and an error corresponding to the symbol character. If the reference symbol character is the end symbol character, the processing unit 104 determines the reference width range for each of a plurality of symbol characters in the symbol area based on the width of the end symbol character, the width ratio, and the error corresponding to the symbol character. can The width ratio may be the ratio of the width of the symbol character to the width of the end symbol character.

9 is a partially enlarged view of a PDF 417 barcode according to some implementations of the present disclosure. A loupe may contain two symbol letters M and N. The reference width range can be determined based on the start symbol character width and errors. As shown in Figure 9, the error can be represented by an increment of two pixels and a subtraction of two pixels shown in parentheses 910 on each of the plurality of row lines.

At 1230, the processing unit 104 may determine a plurality of column boundaries among the plurality of symbol characters based on boundary characteristics between adjacent symbol characters and the reference width range.

Referring to FIG. 9, a column boundary S2 between symbol character M and symbol character N is determined based on a column boundary characteristic between adjacent symbol characters and a reference width range. The color of the last block 920 of symbol character M (represented by four pixels in a column) and the color of the first block 930 of symbol character N (represented by four pixels in a column) are white to black along the row direction. can change color. Accordingly, the gray values of the pixels of blocks 920 and 930 may decrease along the row direction (eg, from 255 to 0).

In some implementations, for two or more plurality of row lines, processing unit 104 directs the plurality of row lines on at least two of the plurality of row lines to symbol regions that satisfy column boundary characteristics between adjacent symbol characters and reference width ranges. A pixel or point (eg, a pixel, midpoint each between two consecutive pixels, etc.) can be identified. The RANSAN algorithm can be used to determine multiple thermal boundaries based on multiple points. It should be noted that the RANSAN algorithm is provided for illustrative purposes and is not intended to be limiting. Any algorithm or model for curve fitting may be used to determine column boundaries among a plurality of symbol characters.

For illustrative purposes only, referring to FIG. 8 , the plurality of row lines L1 - L8 along the symbol direction may be curved due to distortion of the symbol image 800 . In some implementations, a plurality of pixels on a plurality of row lines (L1-L8) that satisfy a column boundary characteristic between adjacent symbol characters and reference width ranges may be identified. Column boundaries S1-S5 may be formed based on a plurality of identified pixels and a RANSAN algorithm.

14 is a flow diagram illustrating an example process for decoding symbol characters based on gray values associated with character regions corresponding to symbol characters, in accordance with some implementations of the present disclosure. In some implementations, process 1400 can be executed on image processing system 100 shown in FIG. 1 . For example, process 1400 may be stored in the form of instructions on a storage medium (eg, network storage device 113 or storage 227 of computing device 200) and may be performed by processing device 104. can be called and/or executed. Process 1400 presented below is intended to illustrate operation. In some implementations, process 1400 can be accomplished with one or more additional actions not described and/or without one or more of the discussed actions. Additionally, the order in the operation of process 1400 as shown in FIG. 14 and described below may not be limiting. In some implementations, operation 560 of process 500 in FIG. 5 may be performed according to process 1400 .

In step 1410, the processing unit 104 divides the character area corresponding to the symbol character into a plurality of blocks along the row direction.

In some implementations, processing unit 104 may equally divide a character area corresponding to a symbol character along a row direction into a predetermined number or count of blocks. For PDF 417 barcodes, the preset number or count may be 17.

At 1420, the processing device 104 may determine a global gray value for each of the plurality of blocks.

Each of the plurality of blocks may include one or more pixels. By way of example only, a block may be 1x4 pixels (i.e. 1 pixel in a row and 4 pixels in a column), 1x3 pixels (i.e. 1 pixel in a row and 3 pixels in a column), 2x7 pixels pixels (i.e., 2 pixels in a row and 7 pixels in a column), and the like. A gray value of one or more pixels of a block may be obtained. A block's global gray value may be an overall representation of the gray values of one or more pixels of the block. In some implementations, a block's global gray value can be an average value of gray values of one or more pixels in the block. The average value may be, for example, an arithmetic average value, a harmonic average value, a secondary average value, and the like. In some implementations, the gray value of a particular pixel of a block can be determined as the block's global gray value. In some implementations, a particular pixel may be specified by a user according to default settings of the data imaging system 100 or the like. In some implementations, a particular pixel can be randomly selected from one or more pixels.

At 1430, the processing unit 104 may determine a contrast value of the symbol character based on the global gray values of the plurality of blocks.

In some implementations, processing unit 104 can identify a first type of block and a second type of block from a plurality of blocks in the text area. In some implementations, a first type of block may refer to a block belonging to a space of symbol characters, and a second type of block may refer to a block belonging to a bar of symbol characters. In this case, the first type of block may be in white color and the second type of block may be in black color. Alternatively, a first type of block may refer to a block belonging to a bar of symbol characters, and a second type of block may refer to a block belonging to a space of symbol characters.

In some implementations, the processing unit 104 can identify a first type of block and a second type of block from the plurality of blocks in the text area based on the global gray values of the plurality of blocks. If a block of the first type includes a block belonging to a space of symbol characters and a block of a second type includes a block belonging to a bar of symbol characters, the block of the first type has a larger global gray value (e.g. , 255, 240, 230, 220, etc.), and the second type block may have a smaller global gray value (eg, 0, 10, 20, 30, etc.).

In some implementations, the contrast value of the symbol character can be determined based on at least the global gray value of the first type of block and the global gray value of the second type of block. For example, the processing device 104 may determine a first ratio of gray values of blocks of the first type to counts of blocks of the first type in the character area. Similarly, the processing unit 104 may determine a second ratio of gray values of blocks of the second type to counts of blocks of the second type in the character area. The contrast value of the symbol character may be determined based on a difference value between the first ratio and the second ratio. By way of example only, the contrast value of a symbol character can be determined according to Equation (1):

Here, contrast represents the contrast value of the symbol character, space gray sum ( spaceGraySum ) represents the sum of the global gray values of blocks in the space of the symbol character, and space number ( spaceNum ) represents the number or count of blocks in space , the bar gray number ( barGrayNum ) represents the sum of the global gray values of the bar block of the symbol character, and the bar number ( barNum ) represents the number or count of blocks in the bar.

At 1440, processing unit 104 may determine a codeword corresponding to the symbol character based on the comparison value.

In some implementations, the processing unit 104 can obtain a plurality of preset codewords (eg, 2787 codewords). The plurality of preset codewords may be, for example, a storage device of the image processing system 100 (eg, a network storage device 113, or a storage device 227 of the computing device 228, etc.) or an external device (eg, For example, it can be obtained from a cloud database). In some implementations, the plurality of preset codewords can be numbers (eg, natural numbers). Each of the plurality of codewords may correspond to a predetermined codeword string. Corresponding relationships between the plurality of preset codewords and the plurality of predetermined codeword strings may be provided in a matrix, vector, data array, table, or the like. For illustrative purposes only, a plurality of codewords and corresponding codeword strings are provided in Table 1.

codeword string preset
code word codeword string preset
code word codeword string preset
code word 31111136 0 51111152 2 31111235 3 41111243 4 51111251 5 21111326 6 31111334 7 21111425 8 11111516 9 21111524 10 11111615 11 21112136 12 31112144 13 41112152 14 21112235 15

In some implementations, a reference collation value for each of a plurality of preset codewords may be determined. In some implementations, the determination of the reference contrast value of each of the plurality of preset codewords may be according to Equation (1), which is similar to or identical to the determination of the symbol character's contrast value, as described in 1430, and won't be repeated

In some implementations, a similarity value between each of the plurality of preset codewords and a symbol character may be determined based on a reference match value of each codeword and a match value of the symbol character. The processing unit 104 may determine a codeword corresponding to the symbol character based on the similarity value. In some implementations, similar values can be sorted (eg, in ascending or descending order). The processing device 104 may identify the greatest similarity value from the determined similarity values. A preset codeword corresponding to the identified similar value may be determined as a codeword corresponding to the symbol character.

15 is a flow diagram illustrating an example process for decoding symbol characters of a symbol into a symbol image, in accordance with some implementations of the present disclosure. In some implementations, process 1500 can be executed on image processing system 100 shown in FIG. 1 . For example, process 1500 may be stored in the form of instructions on a storage medium (eg, network storage device 113 or storage 227 of computing device 200) and may be performed by processing device 104. can be called and/or executed. The process 1500 presented below is intended to illustrate operation. In some implementations, process 1500 can be accomplished with one or more additional actions not described and/or without one or more of the discussed actions. Additionally, the order in the operation of process 1500 as shown in FIG. 15 and described below may not be limiting. For a better understanding of this disclosure, a process 1500 for decoding symbol characters is described in combination with FIG. 16, which is a schematic illustration of an exemplary PDF 417 barcode.

In operation 1505, the processing unit 104 may obtain a symbol image of a symbol including a plurality of symbol characters in the symbol area. In some implementations, symbol image 1600 may be obtained from image source 101 of image processing system 100 . As shown in FIG. 15 , the PDF 417 barcode in the symbol image 1600 may include a start symbol character, a symbol area ABCD, and an end symbol character BGHC in the area EADF. A PDF 417 barcode may include a plurality of symbol characters in the symbol area ABCD.

At 1510, the processing unit 104 may determine a plurality of row lines along the length direction of the symbol.

In some implementations, multiple scan lines can be determined in a positioning box. The positioning box can be used to determine the longitudinal direction (eg, horizontal direction as shown in FIG. 16) of the PDF 417 barcode. Each of the plurality of scan lines may cross pixels in the same row along the length direction of the PDF 417 barcode. A plurality of scan lines may be determined as row lines. As shown in FIG. 16 , a plurality of row lines P1 to P19 may be determined. Each of the plurality of row lines P1 - P19 may cross a pixel in the same row in the symbol area 1600 . Alternatively, each of the plurality of row lines P1 to P19 may be determined by connecting pixels in the same row in the symbol image 1600 along the length direction of the PDF 417 barcode.

At 1515, processing unit 104 may determine start and end boundaries of the symbol region.

In some implementations, the processing unit 104 can determine the arrangement and/or width of the bars and spaces of the start symbol character and/or end symbol character. The processing unit 104 determines the gray value of at least a portion of the pixels corresponding to the bars and spaces of the start symbol character and/or the end symbol character (also referred to as the predetermined gray value corresponding to the start symbol character and/or the end symbol character). ) can be further determined. The predetermined gray values corresponding to the start symbol character and/or the end symbol character may be compared with gray values of pixels on at least one of the plurality of row lines. Based on the comparison, processing unit 104 may identify at least one line segment on at least one of the plurality of row lines corresponding to the start symbol character and/or the end symbol character.

In some implementations, processing unit 104 may identify two or more line segments corresponding to start symbol characters on multiple row lines. Each of the two or more line segments may include a start point and an end point. As shown in FIG. 16, the start point of the start symbol character of the PDF 417 barcode may be an intersection between the line segment EF and the plurality of row lines P1-P19. The end point of the start symbol character of the PDF 417 barcode may be an intersection point between the line segment AD and the plurality of row lines (P1-P19).

Start points of two or more line segments corresponding to the start symbol character may form the start edge of the start symbol character. End points of two or more line segments corresponding to the start symbol character may form the end edge of the start symbol character. In some implementations, a random sample consensus (RANSAN) algorithm can be used to determine the ending edge of the start symbol character based on the ending points of the two or more line segments corresponding to the start symbol character. In some implementations, the ending edge of the start symbol character can be determined by fitting lines according to the RANSAN algorithm based on the ending points of two or more line segments corresponding to the start symbol character. For PDF 417 barcodes, the starting symbol character can be from the symbol area. The end edge of the start symbol character may coincide with the start boundary of the symbol area. In this case, the starting boundary of the symbol region can be determined. Referring to FIG. 16, the start boundary of the symbol region may be A1.

Similarly, processing unit 104 may identify two or more line segments corresponding to end symbol characters on multiple row lines. Each of the two or more line segments may include a start point and an end point. As shown in FIG. 16, the start point of the end symbol character of the PDF 417 barcode may be an intersection between the line segment BC and the plurality of row lines P1-P19. The end point of the end symbol character of the PDF 417 barcode may be an intersection point between the line segment GH and the plurality of row lines (P1-P19).

The starting points of two or more line segments corresponding to the ending symbol character may form the starting edge of the ending symbol character. The end points of two or more line segments corresponding to the end symbol character may form the end edge of the end symbol character. In some implementations, a random samples consensus (RANSAN) algorithm can be used to determine the starting edge of the ending symbol character based on the starting points of the two or more line segments corresponding to the ending symbol character. In some implementations, the starting edge of the ending symbol character can be determined by fitting lines according to the RANSAN algorithm based on the starting points of two or more line segments corresponding to the ending symbol character. For PDF 417 barcodes, the ending symbol character can be from the symbol area. The start edge of the start symbol character may coincide with the end boundary of the symbol area. In this case, the end boundary of the symbol region can be determined. Referring to FIG. 16, the end boundary of the symbol region may be A5.

In operation 1520, the processing unit 104 may determine a plurality of column boundaries among a plurality of symbol characters between a start boundary and an end boundary of the symbol area based on the plurality of row lines.

The processing unit 104 may obtain the length of at least one line segment corresponding to the start symbol character. The length of at least one line segment corresponding to the start symbol character may be indicated as the width of the start symbol character. For example, referring to FIG. 16, the line segment between the intersection point O1 of the row line P1 and the line segment BC and the intersection point O2 of the row line P1 and the line segment AD is PDF 417 It may be a line segment corresponding to the start symbol character of the barcode 1600. The length of the line segment O1O2 may be indicated as the width of the start symbol character.

The processing unit 104 may determine a plurality of column boundaries among a plurality of symbol characters based on boundary characteristics between adjacent symbol characters and the reference width range. The reference width range may be a range defined as an increment (eg, two pixels) and a decrement (eg, two pixels).

In some implementations, for two or more of the plurality of row lines, the processing unit 104 directs the plurality of row lines (e.g., P1) to symbol regions that satisfy column boundary properties between adjacent symbol characters and reference width ranges. -P19) may identify a plurality of pixels or points (eg, pixels, midpoints each between two consecutive pixels, etc.) on at least two of them. The RANSAN algorithm can be used to determine multiple thermal boundaries based on multiple points. For illustrative purposes only, a plurality of thermal boundaries A2, A3, A4, and A5 may be determined.

At 1525, the processing unit 104 may determine an upper boundary and a lower boundary of the symbol region.

For each of the plurality of column boundaries, processing unit 104 may determine a plurality of intersections (eg, pixels) of the plurality of row lines and the column boundary. The processing unit 104 may perform an upward traverse and identify an upper intersection among the plurality of intersections. The pixel above the upper intersection along the column boundary (also referred to as the upper pixel) and the pixel following the upper pixel along the row direction in the same row (also referred to as the pixel following the upper pixel) can be determined. The top pixel and the pixels that follow it may be located on the other side of the column boundary.

Processing unit 104 may determine whether the top intersection and the pixel that follows the top intersection, and the top pixel and the pixel that follows the top pixel satisfy the column boundary characteristics (i.e., the color of the top pixel and the pixel that follows the top pixel). The color of the next pixel is black, and the color of the two pixels may change from white to black along the row direction). If the top pixel and the pixel following it do not satisfy the column boundary property and the top intersection and the pixel following the top intersection along the row direction meet the column boundary property (i.e., the top pixel and the top intersection meet the top boundary property). If it is satisfied), it may indicate that the upper intersection point and the pixel following the upper intersection point may be on the upper boundary of the symbol region.

Referring to FIG. 16 , a pixel O3 that is an intersection point between the column boundary A2 and the row line P1 may be determined as an upper intersection point. The pixel following the upper intersection point O3 along the row direction (also referred to as the pixel following the upper intersection point) may be (O6). Upper cross point O3 and pixels following upper cross point O6 satisfy the column boundary characteristics, and upper pixel O4 of upper cross point O3 and pixels following upper pixel O5 satisfy the column boundary characteristics. If not (i.e., if the upper pixel O4 and the upper intersection point O3 satisfy the upper boundary property), then it means that the upper intersection point O3 and the pixel following the upper intersection point O4 are on the upper boundary of the symbol area. can indicate that it can. Similarly, pixels on the upper boundary of the symbol region may be determined according to column boundaries A3, A4, and A5.

In some implementations, a RANSAN algorithm can be used to determine the upper boundary of the symbol region based on the upper intersection point and subsequent pixels of the upper intersection point corresponding to each of the plurality of column boundaries. The upper boundary may be P1 as shown in FIG. 16 .

Similarly, for each of the plurality of thermal boundaries, processing device 104 may perform a downward traverse and identify a lower intersection among the plurality of intersections. A pixel under the lower intersection along a column boundary (also referred to as a lower pixel) and a pixel succeeding the lower pixel along a row direction in the same row (also referred to as a pixel following a lower pixel) may be determined. The bottom pixel and the pixels that follow it may be located on the other side of the column boundary.

The processing unit 104 may determine whether the lower intersection point and the pixel that follows the lower intersection point, and the lower pixel and the pixel that follows the lower pixel satisfy the column boundary property. If the bottom pixel and the pixels following it do not satisfy the column boundary property and the bottom intersection and the pixels following the bottom intersection along the row direction satisfy the column boundary property (i.e., the bottom pixel and the bottom intersection meet the bottom boundary property). If satisfied), it may indicate that the lower intersection point and the pixel following the lower intersection point may be on the lower boundary of the symbol region.

Referring to FIG. 16 , a pixel O7 that is an intersection of the column boundary A2 and the row line P19 may be determined as a lower intersection point. The pixel following the lower intersection point O7 along the row direction (also referred to as the pixel following the lower intersection point) may be (O8). The lower intersection point O7 and subsequent pixels of lower intersection point O8 satisfy the column boundary characteristics, and the lower pixel O9 of lower intersection point O7 and the subsequent pixels of lower pixel O10 satisfy the column boundary characteristics. If not (ie lower pixel O9 and lower intersection point O7 satisfy the lower boundary property), then it means that the pixels following lower intersection point O7 and lower intersection point O8 are on the lower boundary of the symbol area. can indicate that it can. Similarly, pixels on the lower boundary of the symbol region may be determined according to column boundaries A3, A4, and A5.

In some implementations, a RANSAN algorithm can be used to determine the lower boundary of the symbol region based on the lower intersection point and subsequent pixels of the lower intersection point corresponding to each of the plurality of column boundaries. The lower boundary may be P19 as shown in FIG. 16 .

At 1530, the processing unit 104 may determine a plurality of row boundaries among a plurality of symbol characters between the start boundary and the end boundary of the symbol region.

In some implementations, multiple row boundaries can be determined by specifying multiple row boundaries from multiple row lines based on boundary properties between adjacent symbol characters. In some implementations, the widths of the bars and spaces between two adjacent symbol characters in the column direction may vary. Thus, for a row boundary between two adjacent symbol characters in the column direction, the color of all pixels on the row boundary is the same as the color of corresponding pixels on the first adjacent row line of the row boundary, and the color of at least one pixel on the row boundary This row boundary may have characteristics (also referred to as row boundary characteristics) that may differ from the color of the corresponding pixel on the second adjacent row line. In some implementations, a first adjacent row line can be above a row boundary and a second adjacent row line can be below a row boundary. Alternatively, the first adjacent row line may be below the row boundary and the second adjacent row line may be above the row boundary. In this case, the gray value of every pixel on the row boundary may be equal to or close to the gray value of a corresponding pixel on a first adjacent row line of the row boundary, and the gray value of at least one pixel on the row boundary is may be different from the gray value of the corresponding pixel on the second adjacent row line of .

Referring to FIG. 16 , row lines P4 , P7 , P10 , P13 , and P16 may satisfy row boundary characteristics. Row lines P4, P7, P10, P13, and P16 may be indicated as row boundaries among a plurality of symbol characters.

At 1535, the processing unit 104 may determine a character area corresponding to the symbol character for each of the plurality of symbol characters based on the plurality of column boundaries and the plurality of row boundaries.

Referring to FIG. 16 , a plurality of character areas corresponding to symbol characters may be determined based on row boundaries (P4, P7, P10, P13, and P16) and column boundaries (A2, A3, and A4).

At 1540, processing unit 104 may decode each symbol character based on the gray value associated with the character area corresponding to the symbol character. In some implementations, the operations for decoding each symbol character can be similar or identical to operations 1410 through 1440 of process 1400 as shown in FIG. 14 and will not be repeated here.

Therefore, since the basic concept has been described, it may become more apparent to those skilled in the art after reading this detailed disclosure that the aforementioned detailed disclosure is intended to be presented only through examples and is not limiting. Although not explicitly stated herein, various variations, improvements, and modifications may occur and are intended to those skilled in the art. These changes, improvements, and modifications are intended to be suggested by this disclosure and are within the spirit and scope of the exemplary implementations of this disclosure.

Additionally, certain terminology has been used to describe embodiments of the present disclosure. For example, the terms “one embodiment,” “an embodiment,” and “some embodiments” mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, it should be emphasized and acknowledged that two or more references to "an embodiment" or "an embodiment" or "alternative embodiment" in various places in this specification are not necessarily all referring to the same embodiment. In addition, certain features, structures or characteristics may be combined as suitable for one or more embodiments of the present disclosure.

In addition, aspects of the present disclosure may be shown and described herein in any of a number of patentable classes or contexts, including any new and useful process, machine, manufacture, or configuration of matter, or any new and useful improvement thereof. This will be appreciated by those skilled in the art. Accordingly, aspects of the present disclosure may all be generally hardware as a whole, software as a whole (firmware, resident software, microcode, etc.) ) or as a combination software and hardware implementation. Additionally, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer readable media having computer readable program code embodied thereon.

A computer readable signal medium may include a propagated data signal having computer readable program code embodied therein, for example, at baseband or as part of a carrier wave. Such propagated signals may take any of a variety of forms, including electromagnetic, optical, or the like, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can convey, propagate or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable signal medium may be transmitted using any suitable medium including wireless, wired, fiber optic cable, RF, or the like, or any suitable combination of the foregoing. .

Computer program code for carrying out operations relating to aspects of the present disclosure may be implemented in any combination of one or more programming languages, including object oriented programming languages such as Java, Scala, Smalltalk, Eiffel, Jade, Emerald, C++, C#, VB can be written as NET, Python or the like, the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, conventional procedural programming languages such as PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy; or any other programming language. The program code may execute entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on the user's computer and partly on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or wide area network (WAN), or the connection can be made to an external computer (e.g., Internet service It can be done in a cloud computing environment (over the Internet using a provider (ISP)) or can be provided as a service, such as Software as a Service (SaaS).

Furthermore, the stated order of processing elements or sequences, or the use of numbers, letters, or other designations, is therefore not intended to limit the claimed processes and methods to any order except as may be specified in the claims. Although the above disclosure, through various embodiments, discusses what are presently considered to be various useful implementations of the present disclosure, such detail is for that purpose only and the appended claims are not limited to the disclosed implementations, but, on the contrary, the disclosed implementations. It should be understood that the examples are intended to cover modifications and equivalent arrangements within the spirit and scope of the examples. For example, although execution of the various components described above may be implemented in a hardware device, it may also be implemented as a software-only solution, eg, as an installation on an existing server or mobile device.

Similarly, in the foregoing description of embodiments of the present disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure to aid in the understanding of one or more of the various embodiments. It has to be recognized. However, this method of disclosure is not to be interpreted as reflecting an intention that the claimed subject matter requires more features than are expressly recited in each claim. Rather, claimed subject matter lies in less than all features of a single foregoing disclosed embodiment.

Claims (25)

at least one storage device for storing a set of instructions; and
and at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor:
obtaining a symbol image of a symbol including a plurality of symbol characters in a symbol area;
determining a plurality of row lines along the length direction of the symbol;
determine a plurality of column boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters;
determine a plurality of row boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; And
For each of the plurality of symbol characters,
determine a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; And
and perform an operation comprising decoding the symbol character based on a gray value associated with the character area corresponding to the symbol character. According to claim 1,
Based on the plurality of row lines, determining the plurality of column boundaries among the plurality of symbol characters:
determine a width of a reference symbol character associated with the plurality of symbol characters;
determine a reference width range based on the width of the reference symbol character; And
and determining the plurality of column boundaries among the plurality of symbol characters based on boundary characteristics between adjacent symbol characters and the reference width range. According to claim 2,
The system of claim 1, wherein the reference symbol character includes a start symbol character or an end symbol character. According to claim 2,
The width of the reference symbol character is:
obtain a preset codeword string associated with the reference symbol character;
identify at least one reference line segment for at least one of the plurality of row lines based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with the predetermined codeword string; ; And
and indicating the length of the at least one reference line segment as the width of the reference symbol character. According to any one of claims 1 to 4,
Based on the plurality of row lines, determining the plurality of row boundaries among the plurality of symbol characters:
and identifying the plurality of row boundaries among the plurality of symbol characters from the plurality of row lines based on boundary characteristics between adjacent symbol characters. According to any one of claims 1 to 5,
For each of the plurality of symbol characters, decoding the symbol character based on the gray value associated with the character area corresponding to the symbol character:
divide the character area corresponding to the symbol character into a plurality of blocks along a row direction;
determine a global gray value of each of the plurality of blocks;
determine a contrast value of the symbol character based on the global gray values of the plurality of blocks; And
and determining a codeword corresponding to the symbol character based on the reference value. According to claim 6,
Determining the contrast value of the symbol character based on the global gray values of the plurality of blocks:
determine a first ratio of a gray value of a block of a first type in the character area to a count of the block of the first type;
determine a second ratio of a gray value of a block of a second type to a count of the block of the second type in the character area; And
and determining the contrast value of the symbol character based on a difference value between the first ratio and the second ratio. According to any one of claims 1 to 7,
The operation is:
and determining a start boundary, an end boundary, an upper boundary, and a lower boundary of the symbol region. According to claim 8,
Determining the starting boundary of the symbol region is:
Identifying, for at least one of the plurality of row lines, at least one end point of a start symbol character based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with a start codeword string do; And
and determining the starting boundary of the symbol region based on the at least one ending point of the starting symbol character. According to claim 8 or 9,
Determining the end boundary of the symbol region is:
identifying, for at least one of the plurality of row lines, at least one starting point of an ending symbol character based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with an ending codeword string do; And
and determining the ending boundary of the symbol region based on the at least one starting point of the ending symbol character. According to any one of claims 8 to 10,
Determining the upper boundary of the symbol region is:
For each of the plurality of thermal boundaries,
determine a plurality of intersections of the plurality of row lines and the column boundary;
perform an upward traverse until an upper pixel of a first intersection is identified, the upper pixel and the first intersection satisfy an upper boundary characteristic; And
and determining the upper boundary of the symbol region based on the first intersection of each of the plurality of column boundaries. According to any one of claims 8 to 11,
Determining the lower boundary of the symbol region is:
For each of the plurality of thermal boundaries,
determine a plurality of intersections of the plurality of row lines and the column boundary;
perform a downward traverse until a lower pixel of a second intersection point is identified, the lower pixel and the second intersection point meeting a lower boundary characteristic; And
and determining the lower boundary of the symbol region based on the second intersection of each of the plurality of column boundaries. Way:
obtaining a symbol image of a symbol including a plurality of symbol characters in a symbol area;
determining a plurality of row lines along the length direction of the symbol;
determining a plurality of column boundaries among the plurality of symbol characters based on the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters; ;
determining a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; And
For each of the plurality of symbol characters,
determining a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and
and decoding the symbol character based on a gray value associated with the character area corresponding to the symbol character. According to claim 13,
Based on the plurality of row lines, determining the plurality of column boundaries among the plurality of symbol characters comprises:
determine a width of a reference symbol character associated with the plurality of symbol characters;
determine a reference width range based on the width of the reference symbol character; And
determining the plurality of column boundaries among the plurality of symbol characters based on a boundary characteristic between adjacent symbol characters and the reference width range. According to claim 14,
wherein the reference symbol character comprises a start symbol character or an end symbol character. According to claim 14,
Determining the width of the reference symbol character is:
obtain a preset codeword string associated with the reference symbol character;
identify at least one reference line segment for at least one of the plurality of row lines based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with the predetermined codeword string; ; And
and indicating the length of the at least one reference line segment as the width of the reference symbol character. According to any one of claims 1 to 16,
Based on the plurality of row lines, determining the plurality of row boundaries among the plurality of symbol characters:
A method performed on a computing device having a processor and a computer readable storage device comprising identifying the plurality of row boundaries among the plurality of symbol characters from the plurality of row lines based on boundary characteristics between adjacent symbol characters. . The method of any one of claims 1 to 17,
For each of the plurality of symbol characters, decoding the symbol character based on the gray value associated with the character area corresponding to the symbol character:
divide the character area corresponding to the symbol character into a plurality of blocks along a row direction;
determine a global gray value of each of the plurality of blocks;
determine a contrast value of the symbol character based on the global gray values of the plurality of blocks; And
determining a codeword corresponding to the symbol character based on the reference value. According to claim 18,
Determining the contrast value of the symbol character based on the global gray values of the plurality of blocks:
determine a first ratio of a gray value of a block of a first type in the character area to a count of the block of the first type;
determine a second ratio of a gray value of a block of a second type to a count of the block of the second type in the character area; And
determining the contrast value of the symbol character based on a difference value between the first ratio and the second ratio. According to any one of claims 1 to 19,
The operation is:
and determining a start boundary, an end boundary, an upper boundary, and a lower boundary of the symbol region. 21. The method of claim 20,
Determining the starting boundary of the symbol region is:
Identifying, for at least one of the plurality of row lines, at least one end point of a start symbol character based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with a start codeword string do; And
determining the starting boundary of the symbol region based on the at least one ending point of the starting symbol character. According to claim 20 or 21,
Determining the end boundary of the symbol region is:
identifying, for at least one of the plurality of row lines, at least one starting point of an ending symbol character based on a gray value of a pixel on the at least one of the plurality of row lines and a predetermined gray value associated with an ending codeword string do; And
determining the ending boundary of the symbol region based on the at least one starting point of the ending symbol character. 23. The method of any one of claims 20 to 22,
Determining the upper boundary of the symbol region is:
For each of the plurality of thermal boundaries,
determine a plurality of intersections of the plurality of row lines and the column boundary;
perform an upward traverse until an upper pixel of a first intersection is identified, the upper pixel and the first intersection satisfy an upper boundary characteristic; And
and determining the upper boundary of the symbol region based on the first intersection of each of the plurality of column boundaries. The method of any one of claims 20 to 23,
Determining the upper boundary of the symbol region is:
For each of the plurality of thermal boundaries,
determine a plurality of intersections of the plurality of row lines and the column boundary;
perform a downward traverse until a lower pixel of a second intersection point is identified, the lower pixel and the second intersection point meeting a lower boundary characteristic; And
determining the lower boundary of the symbol region based on the second intersection of each of the plurality of column boundaries. comprising at least one set of instructions, wherein when executed by at least one processor of a computing device, the at least one set of instructions causes the at least one processor to perform a method comprising:
obtaining a symbol image of a symbol including a plurality of symbol characters in a symbol area;
determining a plurality of row lines along the length direction of the symbol;
determining a plurality of column boundaries among the plurality of symbol characters according to the plurality of row lines, each of the plurality of column boundaries corresponding to two consecutive columns of two symbol characters of the plurality of symbol characters;
determining a plurality of row boundaries among the plurality of symbol characters based on the plurality of row lines, each of the plurality of row boundaries corresponding to two adjacent rows of the plurality of symbol characters; And
For each of the plurality of symbol characters,
determining a character area corresponding to the symbol character based on the plurality of column boundaries and the plurality of row boundaries; and
decoding the symbol character based on a gray value associated with the character area corresponding to the symbol character.

Images