CN111178355A - Seal identification method and device and storage medium - Google Patents
Seal identification method and device and storage medium Download PDFInfo
- Publication number
- CN111178355A CN111178355A CN201911378424.0A CN201911378424A CN111178355A CN 111178355 A CN111178355 A CN 111178355A CN 201911378424 A CN201911378424 A CN 201911378424A CN 111178355 A CN111178355 A CN 111178355A
- Authority
- CN
- China
- Prior art keywords
- image area
- image
- stamp
- graph
- neural network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06V30/28—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet
- G06V30/287—Character recognition specially adapted to the type of the alphabet, e.g. Latin alphabet of Kanji, Hiragana or Katakana characters
Abstract
The application discloses a seal identification method, a seal identification device and a storage medium. The seal identification method comprises the following steps: acquiring an image to be identified, wherein the image to be identified comprises a seal graph; determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing a seal graph in an image to be recognized; and identifying characters in the stamp graph in the first image area according to the determined first image area information.
Description
Technical Field
The present application relates to image recognition technologies, and in particular, to a method and an apparatus for recognizing a stamp, and a storage medium.
Background
At present, when the Chinese characters in the circular seal are identified, the position of the circular seal is firstly positioned, and then the Chinese characters in the circular seal are read according to the determined position of the circular seal. At present, the problem of red circular stamp position is usually solved by estimating the position of the center of a circle by a physical method, for example, by using color models such as HSI or RGB, and then calculating the position by estimating the radius through the circle boundary points. However, if the circular stamp and the document font are in the same color (e.g., a document carrying a red circular stamp is a black and white copy), the above algorithm is no longer applicable or less effective.
Aiming at the technical problem that the position of the seal in the image cannot be accurately determined when the colors of the seal and the document are consistent in the prior art, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the disclosure provides a seal identification method, a seal identification device and a storage medium, which at least solve the technical problem that the position of a seal in an image cannot be accurately determined when the colors of the seal and a document are consistent in the prior art.
According to an aspect of the embodiments of the present disclosure, there is provided a stamp identification method, including: acquiring an image to be identified, wherein the image to be identified comprises a seal graph; determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing the stamp graph in the image to be recognized; and identifying characters in the stamp graph in the first image area according to the determined first image area information.
According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium including a stored program, wherein the method described above is performed by a processor when the program is executed.
According to another aspect of the embodiments of the present disclosure, there is also provided a stamp recognition apparatus including: the image acquisition module is used for acquiring an image to be identified, wherein the image to be identified comprises a seal graph; the first image area information determining module is used for determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing a stamp graph in an image to be recognized; and the character recognition module is used for recognizing characters in the stamp graph in the first image area according to the determined first image area information.
According to another aspect of the embodiments of the present disclosure, there is also provided a stamp recognition apparatus including: a processor; and a memory coupled to the processor for providing instructions to the processor for processing the following processing steps: acquiring an image to be identified, wherein the image to be identified comprises a seal graph; determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing a seal graph in an image to be recognized; and identifying characters in the stamp graph in the first image area according to the determined first image area information.
The convolution neural network based on deep learning replaces the method for estimating the circle center position by using color models such as HSI or RGB in the prior art, so that even under the condition that the seal graph is consistent with the character color in the document, the image area containing the seal graph can be accurately positioned. Therefore, the technical problem that the position of the seal in the image cannot be accurately determined when the colors of the seal and the document are consistent in the prior art is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
fig. 1 is a hardware block diagram of a computing device for implementing the method according to embodiment 1 of the present disclosure;
fig. 2 is a schematic flow chart of a stamp identification method according to a first aspect of embodiment 1 of the present disclosure;
FIG. 3 is a schematic diagram of an image to be recognized including a stamp pattern according to embodiment 1 of the present disclosure;
fig. 4 is a schematic diagram of a first image area and first image area information according to embodiment 1 of the present disclosure;
fig. 5A is a schematic diagram of a first neural network according to embodiment 1 of the present disclosure;
fig. 5B is a schematic diagram of output data of the first neural network according to embodiment 1 of the present disclosure;
fig. 6 is a schematic diagram of a denoised first image region according to embodiment 1 of the disclosure;
FIG. 7 is a schematic view of a center point and an outer edge radius of a stamp graphic according to embodiment 1 of the present disclosure;
fig. 8 is a schematic diagram of a first image area and a sector area containing text according to embodiment 1 of the present disclosure;
FIGS. 9 and 10 are schematic views respectively showing the image region after flattening the fan region shown in FIG. 8;
FIG. 11 is a schematic view of a stamp identification apparatus according to embodiment 2 of the present disclosure; and
fig. 12 is a schematic view of a stamp recognition apparatus according to embodiment 3 of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. It is to be understood that the described embodiments are merely exemplary of some, and not all, of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
According to the present embodiment, there is also provided a method embodiment of a stamp identification method, it should be noted that the steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that here.
The method embodiments provided by the present embodiment may be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Fig. 1 shows a hardware block diagram of a computing device for implementing the stamp recognition method. As shown in fig. 1, the computing device may include one or more processors (which may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computing device may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuitry may be a single, stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computing device. As referred to in the disclosed embodiments, the data processing circuit acts as a processor control (e.g., selection of a variable resistance termination path connected to the interface).
The memory can be used for storing software programs and modules of application software, such as program instructions/data storage devices corresponding to the seal identification method in the embodiments of the present disclosure, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the seal identification method of the application program is implemented. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory located remotely from the processor, which may be connected to the computing device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device is used for receiving or transmitting data via a network. Specific examples of such networks may include wireless networks provided by communication providers of the computing devices. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computing device.
It should be noted here that in some alternative embodiments, the computing device shown in fig. 1 described above may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that FIG. 1 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in a computing device as described above.
Under the operating environment, according to a first aspect of the present embodiment, there is provided a seal identification method implemented by the computing device shown in fig. 1. Fig. 2 shows a flow diagram of the method, which, with reference to fig. 2, comprises:
s202: acquiring an image to be identified, wherein the image to be identified comprises a seal graph of a seal;
s204: determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing a seal graph in an image to be recognized; and
s206: and identifying characters in the seal in the first image area according to the determined first image area information.
The detailed map 3 exemplarily shows a specific example of an image to be recognized including a stamp pattern. As described in the background art, when identifying a chinese character in a circular stamp, a position of the circular stamp is first located, and then the chinese character in the circular stamp is read according to the determined position of the circular stamp. At present, the problem of red circular stamp position is usually solved by estimating the position of the center of a circle by a physical method, for example, by using color models such as HSI or RGB, and then calculating the position by estimating the radius through the circle boundary points. However, if the circular stamp and the document font are in the same color (e.g., a document carrying a red circular stamp is a black and white copy), the above algorithm is no longer applicable or less effective.
In view of the above, the present disclosure proposes a method of identifying a stamp, which may be performed, for example, by the computing device shown in fig. 1. First, a computing device acquires an image to be recognized. Referring to fig. 3, the image to be recognized includes a stamp pattern of the stamp. But the stamp graphics are consistent with the color of the document font and are all black.
Then, the computing device determines first image area information by using a preset first neural network, wherein the first image area information is used for indicating a first image area containing a seal pattern in the image to be recognized. For example, the region information may be information of a rectangular region including the stamp pattern (including the position and size of the rectangular region, and the like). Thus, by means of the deeply learned convolutional neural network, the computing device can accurately recognize the region information of the image region containing the stamp pattern even if the stamp pattern coincides with the color of the document font.
Therefore, the computing equipment can perform character recognition in the area according to the determined area information, so as to recognize characters on the stamp.
In summary, the convolutional neural network based on deep learning replaces the method of estimating the circle center position by using color models such as HSI or RGB in the prior art, so that even if the stamp image and the text color in the document are consistent, the image area containing the stamp image can be accurately located. Therefore, the technical problem that the position of the seal in the image cannot be accurately determined when the colors of the seal and the document are consistent in the prior art is solved.
Optionally, the stamp is a circular stamp, and the operation of determining the first image area information by using a preset first neural network includes: and determining the area information of a rectangular area circumscribed with the circular stamp graph of the circular stamp in the image to be recognized as first image area information by utilizing a first neural network. Referring to fig. 3 and 4, the technical solution of the present disclosure can identify a circular stamp. Specifically, referring to fig. 4, the technical solution of the present disclosure can recognize area information of a circumscribed square of a circular stamp, i.e., (x, y, w, h), in an image to be recognized using a first neural network. Where (x, y) may be used to indicate the coordinate position of the left vertex of the circumscribed square, for example. w may be used to indicate the width of the circumscribed square and h may be used to indicate the height of the circumscribed square. Thus, the region information set in this way is information that can be recognized and output by the convolutional neural network model. Therefore, people can conveniently identify the area position of the circular stamp in the image by using the convolutional neural network.
Specifically, the method can be used for positioning the circumscribed square of the circular stamp through a specific deep convolutional neural network model. The specific deep convolutional neural network model is obtained by training a plurality of training sample images containing the circular seal. The training sample image contains one or more circular stamps, but the circular stamps are required to be not overlapped, the stamps can be in any color, and the mark data (English: label) corresponding to each image is one or more positions, wherein the positions are (x, y, w, h). So that the deep convolutional neural network model specified in the embodiment of the present application can be trained.
Because the training data adopted by the deep convolutional neural network model when the model is trained is a sample image containing a circular seal, and the marking data is the position of the circumscribed square of the circular seal in the training sample, after the image to be recognized is input into the deep convolutional neural network model, the convolutional neural network model can cross the circumscribed square position of one or more circular seals in the image to be recognized.
Optionally, the operation of determining the first image area information by using a preset first neural network includes: and determining the first image area information by utilizing a preset master-RCNN convolutional neural network.
Specifically, one reasonable structure of the deep convolutional neural network model of the present embodiment includes: a convolution layer, a pooling layer, and a full-link layer. A large number of experiments prove that when the following network structure (shown in figure 5A. a faster-cnn network structure is adopted), the circular seal position detection by using the deep convolution neural network model has better accuracy.
In the process of identifying the circular seal, the main functions of each layer in the network structure are as follows:
1) a convolutional neural network layer (CNN layer) for extracting a feature map for the input image using convolutional layer + relu activation function + pooling layer, which is used for subsequent candidate regional network layers and fully-connected layers. Specifically, for an image matrix of size 3 × m × n (e.g., an RGB image matrix), the convolutional neural network layer convolves the three channels RGB. Wherein the convolution layer comprises a plurality of 3 x 3 convolution kernels and the image matrix is zero padded prior to the convolution operation to ensure that the matrix size of the input and output are the same. Each pooling layer is used to halve the width and height of the image matrix, i.e. to change the m n matrix to (m/2) × (n/2). So that 4 pooling layers can eventually turn the size of the feature map to (m/16) × (n/16). And the convolution kernel of the last convolutional layer may be 256, for example, thus outputting 256 (m/16) × (n/16) feature maps.
2) A candidate area network layer (Region pro-possible Networks layer), which is mainly used for generating candidate regions. For example, the candidate area network layer first convolves the feature map with a convolution layer having 256 convolution kernels of 3 × 3, and then generates 36 feature maps with a size of (m/16) × (n/16) by using a convolution layer composed of 36 convolution kernels of 1 × 1 (and a step size of 1), which represents the positions and sizes of 9 (m/16) × (n/16) candidate areas. And generating 18 characteristic graphs with the size of (m/16) × (n/16) by using the convolution layer formed by 18 convolution kernels with the 1 × 1 (and the step size of 1), and representing the positive and negative classification of the 9 × 16 × n/16 candidate areas. And the candidate area network layer further selects a predetermined number of candidate areas (for example, 300) from the 9 × m (16) × (n/16) candidate areas according to a preset step, and generates 300 candidate areas in a form of 256 × m (16) × (n/16) according to a feature map output from the convolutional neural network layer (CNN layer).
3) A RoI pooling layer that uses candidate regions generated by the candidate regional network layer and the final feature map of the cnn layer to obtain a regional candidate feature map of fixed size (e.g., (m/16) × (n/16) candidate regions are converted to 7 × 7 candidate regions), and then performs target identification and localization using full join operations,
4) and a Classifier layer which performs full-join operation on the ROI pooling layer to form a feature map with a fixed size, performs specific category classification by using softmax, and simultaneously performs a bounding box regression operation by using Smooth L1 Loss to obtain the accurate position of the object. Specifically, fig. 5B shows a schematic diagram of the form of output data of the faster ═ RCNN neural network. Referring to fig. 5B, the fully-connected layer 2 outputs a multidimensional vector, where every two values of the multidimensional vector correspond to a candidate region, and are used to indicate that the candidate region contains an integral of a stamp image and an integral that does not contain a stamp image. For example, a1 is used to indicate that candidate region 1 contains an integral of a stamp graphic, b1 is used to indicate that candidate region 1 does not contain an integral of a stamp graphic, a2 is used to indicate that candidate region 2 contains an integral of a stamp graphic, and b2 is used to indicate that candidate region 2 does not contain an integral of a stamp graphic. Therefore, the output of each softmax classifier also corresponds to the probability that each candidate area contains the seal graph and the probability that the candidate area does not contain the seal graph. For example, c1 indicates the probability that candidate region 1 contains a stamp graphic, d1 indicates the probability that candidate region 1 does not contain a stamp graphic, c2 indicates the probability that candidate region 2 contains a stamp graphic, d2 indicates the probability that candidate region 2 does not contain a stamp graphic, and so on. Furthermore, the output of the bounding box regression in the fully connected layer 3 is a multidimensional vector, where every fourth value in the vector corresponds to a candidate region, e.g., (x1, y1, w1, h1) for indicating the position and size of the candidate region 1 and (x2, y2, w2, h2) for indicating the position and size of the candidate region 2. In this way, the candidate areas matching the stamp image and their positions and sizes can thus be determined.
Optionally, after determining the first image area information by using a preset first neural network, the method further includes: and in the first image area, denoising by using the color difference between the stamp graph and the background character. Specifically, fig. 6 shows a schematic diagram of the first image region after the denoising process. In an actual copy, although the stamp image in the copy is no longer red, but black, the shade of the color thereof is still different from that of the text in the copy (see fig. 3 and 4). Therefore, the computing device can perform denoising processing by using the color difference between the stamp graph and the background character, so as to remove noise (such as literal characters and the like) in the first image area. Specifically, the gray level distribution in the first image region may be counted by a histogram, then a gray level threshold between the gray level values of the background character and the stamp graphic is determined according to the condition of the gray level distribution, and then the gray level value of the pixel lower than the gray level threshold is set to be white, thereby removing the noise of the background character. Of course, other denoising methods can be used, such as a method of denoising using bm3d (block-matching and 3d filtering, 3-dimensional matched filtering). This is not further enumerated here.
Optionally, the operation of recognizing the text in the stamp graphic in the first image area according to the determined first image area information includes: determining the central position of the circular stamp graph and the radius of the outer edge of the circular stamp graph according to the first image area information; identifying text in the stamp graphic within a second image area defined by the determined center position and the radius.
Specifically, referring to fig. 7, the computing device may determine the center position (x, y) of the circular stamp pattern and the radius r of the outer edge of the circular stamp pattern from the determined circumscribed square. Therefore, according to the determined central position (x, y) and the radius r, the circular image area defined by the outer edge of the circular stamp can be determined. Therefore, characters in the stamp graph can be recognized in the circular image area more accurately.
Further optionally, the operation of recognizing the text in the stamp image within the area defined by the determined center position and the radius further includes: determining a fan-shaped image area containing characters in the seal graph in the second image area by utilizing a preset second neural network; converting the fan-shaped image area into an image area which can be recognized by an OCR model; and recognizing the converted image area by using an OCR model, and determining characters in the stamp graph.
Specifically, referring to FIG. 8, the computing device utilizes a second neural network to determine fan-shaped image regions 101 and 102 within the second image region 100 that contain text in the stamp graphic.
Then, referring to fig. 9 and 10, the computing device geometrically flattens the fan-shaped image areas 101 and 102 to generate the image areas shown in fig. 9 and 10 that can be recognized using an OCR model. The computing device then performs character recognition on the image regions shown in fig. 9 and 10 using an OCR model to determine the characters in the stamp image. In this way, the existing OCR technology can be used for recognizing the character information distributed in a sector shape in the bank.
Optionally, the operation of locating a sector image area containing characters in the stamp in the defined area by using a preset second neural network includes: and determining a sector image area containing characters in the stamp in the limited area by using a preset PSENET neural network.
Further, it is to be specifically noted that:
advantages of Psenet:
the Psenet neural network can locate text of any shape, and the text in the circular seal belongs to one of any shapes.
In contrast, existing regression-based text detection methods have difficulty finding arbitrarily shaped text, and most pixel-based segmentation detectors that are difficult to fully enclose in a rectangle may not separate text instances that are very close to each other.
The PSENET network structure and the processing flow in this embodiment are substantially as follows:
first, its backbone network is resnet-34 (since it is a deep convolutional network with a fixed structure, it will not be described more).
Next, a method of operation similar to fpn (regional candidate network) can generate a series of fpn feature maps.
Third, the later algorithm processing flow:
3-1: dividing fpn feature maps into two classes, and upsampling all feature maps except the first feature map to the scale of the first feature map;
3-2: adding feature maps of different scales;
3-3: and performing convolution processing of 1 x1, and outputting a plurality of prediction results.
Further, referring to fig. 1, according to a second aspect of the present embodiment, there is provided a storage medium. The storage medium comprises a stored program, wherein the method of any of the above is performed by a processor when the program is run.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
Fig. 11 shows a stamp identification apparatus 1100 according to the first aspect of the present embodiment, the apparatus 1100 corresponding to the method according to the first aspect of embodiment 1. Referring to fig. 11, the apparatus 1100 includes: an image obtaining module 1110, configured to obtain an image to be identified, where the image to be identified includes a stamp pattern; a first image area determining module 1120, configured to determine first image area information by using a preset first neural network, where the first image area information is used to indicate a first image area containing a stamp image in an image to be recognized; and a character recognition module 1130 for recognizing characters in the stamp image in the first image area according to the determined first image area information.
Optionally, the stamp graphic is a circular stamp graphic, and the first image region determining module 1120 includes: and the first image area determining submodule is used for determining area information of a square area circumscribed with the circular seal graph in the image to be recognized as first image area information by utilizing a first neural network.
Optionally, the first image region determining module 1120 includes: and the first image area determining submodule is used for determining first image area information by utilizing a preset fast-RCNN convolutional neural network.
Optionally, the apparatus further comprises: and the denoising module is used for denoising the seal graph and the background character in the first image region by utilizing the color difference of the seal graph and the background character.
Optionally, the word recognition module includes: the circular characteristic determination submodule is used for determining the central position of a circular seal graph and the radius of the outer edge of the circular seal graph according to the first image area information; and a character recognition sub-module for recognizing characters in the stamp image within a second image area defined by the determined center position and radius.
Optionally, the character recognition sub-module further includes: the sector image area determining unit is used for determining a sector image area containing characters in the stamp graph in the second image area by utilizing a preset second neural network; the image area conversion module is used for converting the fan-shaped image area into an image area which can be recognized by adopting an OCR model; and the character recognition unit is used for recognizing the converted image area by using the OCR model and determining characters in the seal.
Optionally, the sector image area determination unit includes: and the sector image area determining subunit is used for determining a sector image area containing characters in the stamp in the defined area by utilizing a preset PSENET neural network.
In summary, the convolutional neural network based on deep learning replaces the method of estimating the circle center position by using color models such as HSI or RGB in the prior art, so that even if the stamp graphics are consistent with the text colors in the document, the image area containing the stamp graphics can be accurately located. Therefore, the technical problem that the position of the seal in the image cannot be accurately determined when the colors of the seal and the document are consistent in the prior art is solved.
Example 3
Fig. 12 shows a stamp identification apparatus 1200 according to the present embodiment, which apparatus 1200 corresponds to the method according to the first aspect of embodiment 1. Referring to fig. 12, the apparatus 1200 includes: a processor 1210; and a memory 1220, coupled to the processor 1210, for providing instructions to the processor 1210 for processing the following processing steps: acquiring an image to be identified, wherein the image to be identified comprises a seal graph; determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing a seal graph in an image to be recognized; and identifying characters in the stamp graph in the first image area according to the determined first image area information.
Optionally, the stamp pattern is a circular stamp pattern, and the operation of determining the first image area information by using a preset first neural network includes: and determining the area information of a square area circumscribed with the circular stamp graph in the image to be recognized as first image area information by utilizing the first neural network.
Optionally, the operation of determining the first image area information by using a preset first neural network includes: and determining the first image area information by utilizing a preset master-RCNN convolutional neural network.
Optionally, after determining the first image area information by using a preset first neural network, the method further includes: and in the first image area, denoising by using the color difference between the stamp graph and the background character.
Optionally, the operation of recognizing the text in the stamp graphic in the first image area according to the determined first image area information includes: determining the central position of the circular stamp graph and the radius of the outer edge of the circular stamp graph according to the first image area information; and identifying text in the stamp graphic within a second image area defined by the determined center position and radius.
Optionally, the operation of recognizing the text in the stamp image in the second image area defined by the determined center position and the radius further includes: determining a fan-shaped image area containing characters in the seal graph in the second image area by utilizing a preset second neural network; converting the fan-shaped image area into an image area which can be recognized by an OCR model; and identifying the converted image area by using an OCR model to determine characters in the seal.
Optionally, the operation of locating a sector image area containing characters in the stamp in the defined area by using a preset second neural network includes: and determining a sector image area containing characters in the stamp in the limited area by using a preset PSENET neural network.
In summary, the convolutional neural network based on deep learning replaces the method of estimating the circle center position by using color models such as HSI or RGB in the prior art, so that even if the stamp image and the text color in the document are consistent, the image area containing the stamp image can be accurately located. Therefore, the technical problem that the position of the seal in the image cannot be accurately determined when the colors of the seal and the document are consistent in the prior art is solved.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, which can store program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A seal identification method is characterized by comprising the following steps:
acquiring an image to be identified, wherein the image to be identified comprises a seal graph;
determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing the stamp graph in the image to be recognized; and
and identifying characters in the stamp graph in the first image area according to the determined first image area information.
2. The method according to claim 1, wherein the stamp pattern is a circular stamp pattern, and the operation of determining the first image area information using a preset first neural network comprises:
and determining the area information of a square area circumscribed with the circular seal graph in the image to be identified as the first image area information by utilizing the first neural network.
3. The method of claim 2, wherein the operation of determining the first image area information using the preset first neural network comprises: and determining the first image area information by utilizing a preset master-RCNN convolutional neural network.
4. The method according to claim 1, wherein after determining the first image area information by using the preset first neural network, the method further comprises: and in the first image area, carrying out denoising treatment by using the color difference between the stamp graph and the background character.
5. The method of claim 2, wherein the act of identifying text in the stamp graphic in the first image region based on the determined first image region information comprises:
determining the central position of the circular stamp graph and the radius of the outer edge of the circular stamp graph according to the first image area information; and
identifying text in the stamp graphic within a second image area defined by the determined center position and radius.
6. The method of claim 4, wherein the act of identifying text in the stamp graphic within a second image area defined by the determined center position and radius further comprises:
determining a fan-shaped image area containing characters in the seal graph in the second image area by utilizing a preset second neural network;
converting the fan-shaped image area into an image area which can be recognized by an OCR (optical character recognition) model; and
and identifying the converted image area by using an OCR model, and determining characters in the seal.
7. The method of claim 6, wherein the operation of locating a sector image area containing text in the stamp within the defined area using a preset second neural network comprises: and determining a sector image area containing characters in the stamp in the limited area by utilizing a preset PSENET neural network.
8. A storage medium comprising a stored program, wherein the method of any one of claims 1 to 7 is performed by a processor when the program is run.
9. A seal identification device, comprising:
the image acquisition module is used for acquiring an image to be identified, wherein the image to be identified comprises a seal graph;
the first image area determining module is used for determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing the stamp graph in the image to be recognized; and
and the character recognition module is used for recognizing characters in the seal graph in the first image area according to the determined first image area information.
10. A seal identification device, comprising:
a processor; and
a memory coupled to the processor for providing instructions to the processor for processing the following processing steps:
acquiring an image to be identified, wherein the image to be identified comprises a seal graph;
determining first image area information by utilizing a preset first neural network, wherein the first image area information is used for indicating a first image area containing the stamp graph in the image to be recognized; and
and identifying characters in the stamp graph in the first image area according to the determined first image area information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378424.0A CN111178355A (en) | 2019-12-27 | 2019-12-27 | Seal identification method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378424.0A CN111178355A (en) | 2019-12-27 | 2019-12-27 | Seal identification method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178355A true CN111178355A (en) | 2020-05-19 |
Family
ID=70654086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911378424.0A Pending CN111178355A (en) | 2019-12-27 | 2019-12-27 | Seal identification method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178355A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950356A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal text positioning method and device and electronic equipment |
| CN112507946A (en) * | 2020-12-18 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing image |
| CN112766275A (en) * | 2021-04-08 | 2021-05-07 | 金蝶软件（中国）有限公司 | Seal character recognition method and device, computer equipment and storage medium |
| CN112784835A (en) * | 2021-01-21 | 2021-05-11 | 恒安嘉新（北京）科技股份公司 | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium |
| WO2021115490A1 (en) * | 2020-06-22 | 2021-06-17 | 平安科技（深圳）有限公司 | Seal character detection and recognition method, device, and medium for complex environments |
| CN113033325A (en) * | 2021-03-04 | 2021-06-25 | 杭州睿胜软件有限公司 | Image processing method and device, intelligent invoice recognition equipment and storage medium |
| CN113378821A (en) * | 2021-07-02 | 2021-09-10 | 人民中科(济南)智能技术有限公司 | Official seal character recognition method, system, equipment and storage medium based on deep learning |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3022236U (en) * | 1995-08-31 | 1996-03-22 | 耀元電子股▲ふん▼有限公司 | A seal matching system similar to a neural network |
| JPH11110411A (en) * | 1997-10-03 | 1999-04-23 | Ebaretto Sogo Kenkyusho:Kk | System for making document including seal impression or signature into data base |
| WO2005064524A1 (en) * | 2003-12-30 | 2005-07-14 | Ruizhen Liu | Digital seal system |
| CN107944452A (en) * | 2017-12-12 | 2018-04-20 | 深圳市创业印章实业有限公司 | A kind of circular stamp character recognition method |
| CN109145723A (en) * | 2018-07-09 | 2019-01-04 | 长江大学 | A kind of seal recognition methods, system, terminal installation and storage medium |
| CN109376658A (en) * | 2018-10-26 | 2019-02-22 | 信雅达系统工程股份有限公司 | A kind of OCR method based on deep learning |
| CN109657666A (en) * | 2018-11-23 | 2019-04-19 | 汉王科技股份有限公司 | A kind of circular stamp recognition methods and device |
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
| CN110443250A (en) * | 2019-07-31 | 2019-11-12 | 天津车之家数据信息技术有限公司 | A kind of classification recognition methods of contract seal, device and calculate equipment |
-
2019
- 2019-12-27 CN CN201911378424.0A patent/CN111178355A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3022236U (en) * | 1995-08-31 | 1996-03-22 | 耀元電子股▲ふん▼有限公司 | A seal matching system similar to a neural network |
| JPH11110411A (en) * | 1997-10-03 | 1999-04-23 | Ebaretto Sogo Kenkyusho:Kk | System for making document including seal impression or signature into data base |
| WO2005064524A1 (en) * | 2003-12-30 | 2005-07-14 | Ruizhen Liu | Digital seal system |
| CN107944452A (en) * | 2017-12-12 | 2018-04-20 | 深圳市创业印章实业有限公司 | A kind of circular stamp character recognition method |
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
| CN109145723A (en) * | 2018-07-09 | 2019-01-04 | 长江大学 | A kind of seal recognition methods, system, terminal installation and storage medium |
| CN109376658A (en) * | 2018-10-26 | 2019-02-22 | 信雅达系统工程股份有限公司 | A kind of OCR method based on deep learning |
| CN109657666A (en) * | 2018-11-23 | 2019-04-19 | 汉王科技股份有限公司 | A kind of circular stamp recognition methods and device |
| CN110443250A (en) * | 2019-07-31 | 2019-11-12 | 天津车之家数据信息技术有限公司 | A kind of classification recognition methods of contract seal, device and calculate equipment |
Non-Patent Citations (1)
| Title |
|---|
| 阳哲;: "卷积神经网络在印章编号识别中的应用", 现代计算机(专业版) * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021115490A1 (en) * | 2020-06-22 | 2021-06-17 | 平安科技（深圳）有限公司 | Seal character detection and recognition method, device, and medium for complex environments |
| CN111950356A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal text positioning method and device and electronic equipment |
| CN111950356B (en) * | 2020-06-30 | 2024-04-19 | 深圳市雄帝科技股份有限公司 | Seal text positioning method and device and electronic equipment |
| CN112507946A (en) * | 2020-12-18 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing image |
| CN112784835A (en) * | 2021-01-21 | 2021-05-11 | 恒安嘉新（北京）科技股份公司 | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium |
| CN112784835B (en) * | 2021-01-21 | 2024-04-12 | 恒安嘉新（北京）科技股份公司 | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium |
| CN113033325A (en) * | 2021-03-04 | 2021-06-25 | 杭州睿胜软件有限公司 | Image processing method and device, intelligent invoice recognition equipment and storage medium |
| WO2022183907A1 (en) * | 2021-03-04 | 2022-09-09 | 杭州睿胜软件有限公司 | Image processing method and apparatus, intelligent invoice recognition device, and storage medium |
| CN112766275A (en) * | 2021-04-08 | 2021-05-07 | 金蝶软件（中国）有限公司 | Seal character recognition method and device, computer equipment and storage medium |
| CN112766275B (en) * | 2021-04-08 | 2021-09-10 | 金蝶软件（中国）有限公司 | Seal character recognition method and device, computer equipment and storage medium |
| CN113378821A (en) * | 2021-07-02 | 2021-09-10 | 人民中科(济南)智能技术有限公司 | Official seal character recognition method, system, equipment and storage medium based on deep learning |
| CN113378821B (en) * | 2021-07-02 | 2023-02-28 | 人民中科(济南)智能技术有限公司 | Official seal character recognition method, system, equipment and storage medium based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178355A (en) | Seal identification method and device and storage medium | |
| CN110874594B (en) | Human body appearance damage detection method and related equipment based on semantic segmentation network | |
| CN107944450B (en) | License plate recognition method and device | |
| CN110659647A (en) | Seal image identification method and device, intelligent invoice identification equipment and storage medium | |
| CN111259889A (en) | Image text recognition method and device, computer equipment and computer storage medium | |
| CN109409377B (en) | Method and device for detecting characters in image | |
| CN112418216A (en) | Method for detecting characters in complex natural scene image | |
| CN107545223B (en) | Image recognition method and electronic equipment | |
| CN112699775A (en) | Certificate identification method, device and equipment based on deep learning and storage medium | |
| CN110443235B (en) | Intelligent paper test paper total score identification method and system | |
| CN110782466A (en) | Picture segmentation method, device and system | |
| CN112434715B (en) | Target identification method and device based on artificial intelligence and storage medium | |
| CN110781890A (en) | Identification card identification method and device, electronic equipment and readable storage medium | |
| CN108256520B (en) | Method for identifying coin year, terminal equipment and computer readable storage medium | |
| CN115272887A (en) | Coastal zone garbage identification method, device and equipment based on unmanned aerial vehicle detection | |
| CN112132750B (en) | Video processing method and device | |
| CN109658523A (en) | The method for realizing each function operation instruction of vehicle using the application of AR augmented reality | |
| CN112767412A (en) | Vehicle component level segmentation method and device and electronic equipment | |
| CN110633666A (en) | Gesture track recognition method based on finger color patches | |
| CN112561793B (en) | Planar design space conversion method and system | |
| Callier et al. | Automatic road area extraction from printed maps based on linear feature detection | |
| Chiang et al. | Extracting road vector data from raster maps | |
| CN113343965A (en) | Image tilt correction method, apparatus and storage medium | |
| CN113963004A (en) | Sampling method and device and electronic equipment | |
| CN113807315A (en) | Method, device, equipment and medium for constructing recognition model of object to be recognized |
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 |