CN111626285A - Character recognition system and method - Google Patents
Character recognition system and method Download PDFInfo
- Publication number
- CN111626285A CN111626285A CN202010460052.2A CN202010460052A CN111626285A CN 111626285 A CN111626285 A CN 111626285A CN 202010460052 A CN202010460052 A CN 202010460052A CN 111626285 A CN111626285 A CN 111626285A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- dynamic speckle
- identified
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003384 imaging method Methods 0.000 claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 53
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012935 Averaging Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/145—Illumination specially adapted for pattern recognition, e.g. using gratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Abstract
The invention relates to a character recognition system and method, one embodiment of the system comprises: a light source, a digital micromirror array, a bucket detector, and a computing device; the digital micro-mirror array converts light rays emitted by a light source into dynamic speckle signals and projects the dynamic speckle signals to the surface of a target to be identified; a barrel detector receives a light intensity signal reflected by a target to be identified; the calculating device carries out second-order correlation calculation on the dynamic speckle signals and the light intensity signals to obtain ghost imaging images of the target to be identified; and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized. This embodiment enables accurate recognition of characters at a lower cost.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a character recognition system and a method.
Background
Image information is the most direct and effective information that can be obtained at present. With the rapid development of information technology, optical imaging is widely regarded worldwide, and plays an indispensable role in future scientific and technological development, such as optical imaging technology in the fields of artificial intelligence, electronic payment, industrial automation, military industry and the like. How to rapidly acquire more effective target image information becomes an important research subject of scholars all over the world, at present, the high-speed camera technology is rapidly developed, a femtosecond camera can shoot images of 200 hundred million frames per second, but the optical path is complex, and the manufacturing cost is high.
The current image recognition technology mainly adopts a technology of training feature points of a target image by using a neural network, wherein the feature points refer to points in the image, wherein the local pixel textures and colors of the points have obvious changes with surrounding pixels. The area of the region where the feature points may exist is very small with respect to the entire image, and therefore the more abundant the texture of the image, the more feature points can be extracted. In practical application, a common camera is used for shooting a high-speed target, the obtained image is fuzzy, the texture structure of the image is not clear, the number of the obtained effective characteristic points is small, and accurate recognition of characters in the effective characteristic points is difficult.
Therefore, in view of the above disadvantages, it is desirable to provide a character recognition method with low cost and high recognition speed.
Disclosure of Invention
In view of the defects in the prior art, embodiments of the present invention provide a character recognition system and method, which can accurately recognize characters in a target at a low cost.
In order to solve the above technical problems, the present invention provides a character recognition system.
The character recognition system of the embodiment of the invention may include: a light source, a digital micromirror array, a bucket detector, and a computing device; the digital micro-mirror array converts light rays emitted by a light source into dynamic speckle signals and projects the dynamic speckle signals to the surface of a target to be identified; a barrel detector receives a light intensity signal reflected by a target to be identified; the calculating device carries out second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain a ghost imaging image of the target to be identified; and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
Preferably, the calculation means performs a second order correlation calculation on the dynamic speckle signal and the light intensity signal according to the following formula:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the averaging operator is taken for the summation.
Preferably, the computing device is further configured to: after obtaining a ghost imaging image of the target to be identified, performing median filtering on the ghost imaging image.
Preferably, the character recognition model is a convolutional neural network trained by a training set including a plurality of training samples, each training sample including: a training image as an input portion and known characters in the training image as a label portion; wherein the training image is obtained according to the following: the digital micromirror array converts light rays emitted by the light source into dynamic speckle signals and projects the dynamic speckle signals to an original image; the bucket detector receives a light intensity signal reflected by an original image; and the computing device performs second-order correlation computation on the dynamic speckle signal and the light intensity signal to obtain the training image.
The invention also provides a character recognition method.
The character recognition method of the embodiment of the invention comprises the following steps: projecting a dynamic speckle signal generated by a digital micromirror array to the surface of a target to be identified, and receiving a light intensity signal reflected by the target to be identified by using a barrel detector; performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain a ghost imaging image of the target to be identified; and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
Preferably, the method further comprises: after obtaining a ghost imaging image of the target to be identified, performing median filtering on the ghost imaging image.
Preferably, the performing a second-order correlation calculation on the dynamic speckle signal and the light intensity signal includes: the second order correlation calculation is performed using the following formula:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the averaging operator is taken for the summation.
Preferably, the character recognition model is a convolutional neural network trained by a training set including a plurality of training samples, each training sample including: a training image as an input portion and known characters in the training image as a label portion; wherein the training image is obtained according to the following steps: projecting the dynamic speckle signals generated by the digital micromirror array to an original image, and receiving light intensity signals reflected by the original image by using the bucket detector; and performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain the training image.
The character recognition system and the method have the following beneficial effects: the embodiment of the invention provides a character recognition system and method based on a single-pixel bucket detector. Specifically, a light path is constructed according to a ghost imaging principle, a projector is used for projecting a black-and-white matrix in an area through which a target passes, light reflected by the target is converged and received by a barrel detector, then a ghost imaging image of the target is calculated by using a second-order correlation calculation formula, finally median filtering is carried out on the ghost imaging image to weaken shot noise in the image, and the filtered image is input into a convolution neural network trained in advance for recognition, so that characters in the target are obtained. The single-pixel bucket detector is used in the process, so that the cost of obtaining the image can be reduced, the imaging speed is improved, the character recognition mode based on the convolutional neural network can accelerate the recognition speed, the characteristic information of the image can be increased by processing the image by using median filtering, and the recognition rate of the neural network is improved.
Drawings
FIG. 1 is a schematic diagram of the components of a character recognition system in an embodiment of the present invention;
FIG. 2 is a schematic illustration of a ghost image in an embodiment of the present invention;
FIG. 3 is a diagram illustrating the main steps of a character recognition method according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an implementation of a character recognition method according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic structural diagram of an electronic device for implementing the character recognition method in the embodiment of the present invention.
In the figure: 11: a target to be identified; 12: a digital micromirror array; 13: a bucket detector; 14: a projector; 15: a computing device.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic diagram of components of a character recognition system in an embodiment of the present invention, and as shown in fig. 1, the character recognition system in the embodiment of the present invention may include: a light source (which may be a projector 14), a Digital Micro-mirror array (DMD) 12, a bucket detector 13, and a computing Device 15. The bucket detector 13 is a single-pixel bucket detector, and the computing device 15 can be any device with computing function, such as a computer.
In specific application, the digital micromirror array 12 can convert light emitted from a light source into a dynamic speckle signal, project the dynamic speckle signal onto the surface of the object 11 to be identified, and receive a light intensity signal reflected by the object 11 to be identified by the bucket detector 13. The calculating device 15 performs second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain a ghost imaging image of the target 11 to be recognized, and inputs the ghost imaging image into a pre-trained character recognition model to obtain characters in the target 11 to be recognized. Generally, the dynamic speckle signal is generated by black and white squares of the dmd array 12, wherein the black squares are opaque portions and the white squares are transparent portions, and the ratio of the number of the black squares to the number of the white squares may be 4: 1. in practical application, each time the digital micromirror array 12 projects a speckle, the bucket detector 13 records and stores image data once as a sample, and after multiple samples, the image data can be calculated by a second-order correlation calculation formula to obtain a corresponding ghost imaging image, namely a quantum correlation imaging image.
Fig. 2 is a schematic diagram of a ghost-imaged image in the embodiment of the present invention, showing ghost-imaged images of characters 0 to 9.
Specifically, the second order correlation calculation formula may be as follows:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the average operator is taken for summation and i is the acquisition sequence number.
The operation rule of the sum-and-average operator is as follows (in D)iFor example, where M denotesLumped order):
after obtaining the ghost image of the object to be identified, the computing device 15 may perform preprocessing on the image, such as performing median filtering to attenuate shot noise in the image, so as to make the characteristic points of the image more obvious. Finally, the computing device 15 inputs the image after the preprocessing is performed into the character recognition model which is trained in advance, so as to obtain the characters in the target to be recognized.
Preferably, the character recognition model may employ a convolutional neural network cnn (convolutional neural networks), which may be trained by a training set including a plurality of training samples, each of the training samples may include: a training image as an input portion, and known characters in the training image as a label portion. It will be appreciated that the training images may also be processed in a manner similar to the target to be identified: the digital micromirror array 12 converts light emitted by the light source into dynamic speckle signals, projects the dynamic speckle signals to an original image corresponding to a training image, the bucket detector 13 receives light intensity signals reflected by the original image, the calculating device 15 performs second-order correlation calculation on the dynamic speckle signals and the light intensity signals to obtain ghost imaging images of the original image, and finally performs median filtering to obtain the training image. In practical applications, a plurality of training images (e.g., 100) of each character (including any chinese characters, numbers, letters, etc.) can be obtained to form the training set. When shooting images, the shot images can be sorted by using the code wheel value of the rotary table.
Fig. 3 is a schematic diagram of main steps of a character recognition method in an embodiment of the present invention, and as shown in fig. 3, the character recognition method in the embodiment of the present invention may specifically execute the following steps:
step S301: and projecting the dynamic speckle signals generated by the digital micromirror array to the surface of the target to be identified, and receiving the light intensity signals reflected by the target to be identified by using a barrel detector. Step S302: and performing second-order correlation calculation on the dynamic speckle signals and the light intensity signals to obtain a ghost imaging image of the target to be identified. Step S303: and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
In some embodiments, after obtaining the ghost imaging image of the target to be identified, the ghost imaging image may be median filtered to remove shot noise in the ghost imaging image.
In an alternative implementation, the second order correlation calculation described above is performed using the following equation:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the averaging operator is taken for the summation.
In addition, in an embodiment of the present invention, the character recognition model is a convolutional neural network, which is trained by a training set including a plurality of training samples, each training sample including: a training image as an input portion and known characters in the training image as a label portion; wherein the training image is obtained according to the following steps: projecting the dynamic speckle signal generated by the digital micromirror array to an original image, and receiving a light intensity signal reflected by the original image by using the bucket detector; and performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain the training image.
Fig. 4 is a schematic diagram of a specific implementation of the character recognition method in the embodiment of the present invention, and as shown in fig. 4, the character recognition method in the embodiment of the present invention may be divided into a left training process and a right recognition process. In the training process, multiple samples (i.e., multiple original images corresponding to each known character) are first placed in a single-pixel bucket detector imaging system (i.e., an imaging system including a light source, a digital micromirror array, a bucket detector, and a computing device for obtaining a ghost image), and a ghost image (i.e., a training image) of each original image is obtained, i.e., a training set including multiple training samples is generated. And then, performing median filtering on each training image, and inputting the obtained image into a convolutional neural network for training. In the identification process, a target is placed in a single-pixel bucket detector imaging system to obtain a ghost imaging image of the target, and then the ghost imaging image is input into a trained convolutional neural network after median filtering, so that a character identification result can be obtained.
Fig. 5 illustrates an exemplary system architecture 500 to which the character recognition method of embodiments of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505 (this architecture is merely an example, and the components included in a particular architecture may be adapted according to application specific circumstances). The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have various client applications installed thereon, such as a character recognition application or the like (for example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server that provides various services, such as an arithmetic server (for example only) that provides support for a character recognition application operated by a user using the terminal devices 501, 502, 503. The server may process the received character recognition request and feed back the processing results (e.g., recognized characters-by way of example only) to the terminal devices 501, 502, 503.
It should be noted that the character recognition method provided by the embodiment of the present invention is generally executed by the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The invention also provides the electronic equipment. The electronic device of the embodiment of the invention comprises: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the character recognition method provided by the present invention.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use with the electronic device implementing an embodiment of the present invention. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the computer system 600 are also stored. The CPU601, ROM 602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as an internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, the processes described in the main step diagrams above may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the main step diagram. In the above-described embodiment, the computer program can be downloaded and installed from the network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the central processing unit 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, 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 medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to perform steps comprising: projecting a dynamic speckle signal generated by a digital micromirror array onto the surface of a target to be identified, and receiving a light intensity signal reflected by the target to be identified by using a barrel detector; performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain a ghost imaging image of the target to be identified; and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
In summary, in the technical solution of the embodiment of the present invention, a light path is constructed according to a principle of ghost imaging, a projector is used to project a black-and-white matrix on an area through which a target passes, light reflected by the target is converged and received by a bucket detector, then a second-order correlation calculation formula is used to calculate a target ghost imaging image, finally, median filtering is performed on the ghost imaging image to weaken shot noise in the image, and the filtered image is input to a convolutional neural network trained in advance to be identified, so as to obtain characters in the target. The single-pixel bucket detector is used in the process, so that the cost of obtaining the image can be reduced, the imaging speed is improved, the character recognition mode based on the convolutional neural network can accelerate the recognition speed, the characteristic information of the image can be increased by processing the image by using median filtering, and the recognition rate of the neural network is improved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may be modified or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A character recognition system, comprising: a light source, a digital micromirror array, a bucket detector, and a computing device; wherein the content of the first and second substances,
the digital micromirror array converts light rays emitted by the light source into dynamic speckle signals and projects the dynamic speckle signals to the surface of a target to be identified;
a barrel detector receives a light intensity signal reflected by a target to be identified;
the calculating device carries out second-order correlation calculation on the dynamic speckle signals and the light intensity signals to obtain ghost imaging images of the target to be identified; and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
2. The system of claim 1, wherein the computing device performs a second order correlation calculation on the dynamic speckle signal and the intensity signal according to the following formula:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the averaging operator is taken for the summation.
3. The system of claim 1, wherein the computing device is further configured to: after obtaining a ghost imaging image of the target to be identified, performing median filtering on the ghost imaging image.
4. The system according to any one of claims 1-3, wherein the character recognition model is a convolutional neural network trained by a training set comprising a plurality of training samples, each training sample comprising: a training image as an input portion and known characters in the training image as a label portion; wherein the training image is obtained according to the following:
the digital micromirror array converts light rays emitted by the light source into dynamic speckle signals and projects the dynamic speckle signals to an original image; the barrel detector receives a light intensity signal reflected by an original image;
and the computing device performs second-order correlation computation on the dynamic speckle signal and the light intensity signal to obtain the training image.
5. A character recognition method, comprising:
projecting a dynamic speckle signal generated by a digital micromirror array to the surface of a target to be identified, and receiving a light intensity signal reflected by the target to be identified by using a barrel detector;
performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain a ghost imaging image of the target to be identified; and
and inputting the ghost imaging image into a character recognition model which is trained in advance to obtain characters in a target to be recognized.
6. The method of claim 5, further comprising:
after obtaining a ghost imaging image of the target to be identified, performing median filtering on the ghost imaging image.
7. The method of claim 5, wherein performing a second order correlation calculation on the dynamic speckle signal and the intensity signal comprises: the second order correlation calculation is performed using the following formula:
GI(x,y)=<Di·Si(x,y)>-<Di><Si(x,y)>
wherein GI (x, y) is a ghost image of the object to be recognized, DiFor the light intensity signal, Si(x, y) is the dynamic speckle signal, x is the light field abscissa, y is the light field ordinate,<>the averaging operator is taken for the summation.
8. The method of any one of claims 5-7, wherein the character recognition model is a convolutional neural network trained using a training set comprising a plurality of training samples, each training sample comprising: a training image as an input portion and known characters in the training image as a label portion; wherein the training image is obtained according to the following steps:
projecting the dynamic speckle signal generated by the digital micromirror array to an original image, and receiving a light intensity signal reflected by the original image by using the bucket detector;
and performing second-order correlation calculation on the dynamic speckle signal and the light intensity signal to obtain the training image.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 5-8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 5-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010460052.2A CN111626285A (en) | 2020-05-27 | 2020-05-27 | Character recognition system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010460052.2A CN111626285A (en) | 2020-05-27 | 2020-05-27 | Character recognition system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111626285A true CN111626285A (en) | 2020-09-04 |
Family
ID=72272143
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010460052.2A Pending CN111626285A (en) | 2020-05-27 | 2020-05-27 | Character recognition system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111626285A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022091972A1 (en) * | 2020-10-28 | 2022-05-05 | 株式会社小糸製作所 | Imaging device, vehicle lighting fixture, and vehicle |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107748885A (en) * | 2017-06-30 | 2018-03-02 | 南京理工大学 | A kind of method that ambiguous characters are identified |
CN110646810A (en) * | 2019-09-27 | 2020-01-03 | 北京理工大学 | Speckle optimization compressed sensing ghost imaging method and system |
CN110826567A (en) * | 2019-11-06 | 2020-02-21 | 北京字节跳动网络技术有限公司 | Optical character recognition method, device, equipment and storage medium |
CN110930317A (en) * | 2019-10-30 | 2020-03-27 | 西安交通大学 | Ghost imaging method based on convolutional neural network |
-
2020
- 2020-05-27 CN CN202010460052.2A patent/CN111626285A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107748885A (en) * | 2017-06-30 | 2018-03-02 | 南京理工大学 | A kind of method that ambiguous characters are identified |
CN110646810A (en) * | 2019-09-27 | 2020-01-03 | 北京理工大学 | Speckle optimization compressed sensing ghost imaging method and system |
CN110930317A (en) * | 2019-10-30 | 2020-03-27 | 西安交通大学 | Ghost imaging method based on convolutional neural network |
CN110826567A (en) * | 2019-11-06 | 2020-02-21 | 北京字节跳动网络技术有限公司 | Optical character recognition method, device, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
姚银萍;万仁刚;薛玉郎;张世伟;张同意;: "基于统计光学的正负热光非定域成像" * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022091972A1 (en) * | 2020-10-28 | 2022-05-05 | 株式会社小糸製作所 | Imaging device, vehicle lighting fixture, and vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107578017B (en) | Method and apparatus for generating image | |
US11941529B2 (en) | Method and apparatus for processing mouth image | |
CN109191512B (en) | Binocular image depth estimation method, binocular image depth estimation device, binocular image depth estimation apparatus, program, and medium | |
CN108235116B (en) | Feature propagation method and apparatus, electronic device, and medium | |
CN109255767B (en) | Image processing method and device | |
US11514263B2 (en) | Method and apparatus for processing image | |
CN111414879B (en) | Face shielding degree identification method and device, electronic equipment and readable storage medium | |
CN109377508B (en) | Image processing method and device | |
CN109711508B (en) | Image processing method and device | |
CN112183492B (en) | Face model precision correction method, device and storage medium | |
CN108510084B (en) | Method and apparatus for generating information | |
WO2023273342A1 (en) | Method and apparatus for repairing video, and device, medium and product | |
JP2023531350A (en) | A method for incrementing a sample image, a method for training an image detection model and a method for image detection | |
CN111757100B (en) | Method and device for determining camera motion variation, electronic equipment and medium | |
CN112381717A (en) | Image processing method, model training method, device, medium, and apparatus | |
CN114612872A (en) | Target detection method, target detection device, electronic equipment and computer-readable storage medium | |
WO2019242409A1 (en) | Qr code generation method and apparatus for terminal device | |
CN111626285A (en) | Character recognition system and method | |
CN114399814A (en) | Deep learning-based obstruction removal and three-dimensional reconstruction method | |
CN116597430A (en) | Article identification method, apparatus, electronic device, and computer-readable medium | |
Soma et al. | An efficient and contrast-enhanced video de-hazing based on transmission estimation using HSL color model | |
CN108537786B (en) | Method and apparatus for processing image | |
CN110765304A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
CN110555799A (en) | Method and apparatus for processing video | |
JP2023535662A (en) | Method, apparatus, apparatus, medium and computer program for restoring video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |