CN111950353A

CN111950353A - Seal text recognition method and device and electronic equipment

Info

Publication number: CN111950353A
Application number: CN202010619489.6A
Authority: CN
Inventors: 高亚南
Original assignee: Shenzhen Emperor Technology Co Ltd
Current assignee: Shenzhen Emperor Technology Co Ltd
Priority date: 2020-06-30
Filing date: 2020-06-30
Publication date: 2020-11-17
Anticipated expiration: 2040-06-30
Also published as: CN111950353B

Abstract

The embodiment of the disclosure provides a seal text recognition method and device and electronic equipment, and belongs to the technical field of image processing. The method comprises the following steps: receiving a stamp picture to be identified; acquiring a position point parameter of a text box of a target seal contained in the seal picture, wherein the position point parameter at least comprises a vertex coordinate of the text box; extracting a characteristic layer corresponding to the text box of the target seal in the seal picture according to the position point parameter of the text box; rotating and adjusting the characteristic layer to a standard pose; and performing text recognition on the text information in the feature map layer. Therefore, the position point parameters of the text box are obtained firstly, and then the corresponding characteristic image layer is adjusted to the standard pose in a rotating mode, so that the accuracy of text recognition in the seal can be improved to a great extent, and the text box in different angles and directions can be recognized accurately and quickly.

Description

Seal text recognition method and device and electronic equipment

Technical Field

The present disclosure relates to the field of image processing technologies, and in particular, to a method and an apparatus for recognizing a stamp text, and an electronic device.

Background

The prior art is mostly directed at the recognition scheme of seal text in the invoice, mainly is that various card certificates of structural identification, such as: identity card, bank card, driving license, passport, visa, real estate card. In the text recognition process, the element to be recognized is fixed in position, the element position is located only by template matching, text recognition is performed through each line of slicing, various rotation angles may exist in other seals such as passports and the like, the situation that the text is not easy to locate due to the fact that the types of the seals are various is caused, and the accuracy of text recognition is low.

Therefore, the existing seal text recognition scheme has the technical problems that the accuracy rate of seal text recognition is low and the adaptability is poor.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method and an apparatus for recognizing a stamp text, and an electronic device, which at least partially solve the problems in the prior art.

In a first aspect, an embodiment of the present disclosure provides a method for recognizing a stamp text, including:

receiving a stamp picture to be identified;

acquiring a position point parameter of a text box of a target seal contained in the seal picture, wherein the position point parameter at least comprises a vertex coordinate of the text box;

extracting a characteristic layer corresponding to the text box of the target seal in the seal picture according to the position point parameter of the text box;

rotating and adjusting the characteristic layer to a standard pose;

and performing text recognition on the text information in the feature map layer.

According to a specific implementation manner of the embodiment of the present disclosure, the step of performing text recognition on the text information in the feature map layer includes:

extracting a target feature sequence corresponding to the text information in the feature layer;

inputting the target characteristic sequence into a long-term and short-term memory network structure for characteristic matching;

the textual information is identified by a time-series classification loss function.

According to a specific implementation manner of the embodiment of the present disclosure, the step of extracting the feature layer corresponding to the text box of the target seal in the seal picture according to the position point parameter of the text box includes:

carrying out affine transformation according to the vertex coordinates of the text box;

and acquiring pixel characteristics corresponding to the position of the text box in a preset layer of the seal picture, wherein the preset layer is a layer where the characteristics of a layer before the output layer are located.

According to a specific implementation manner of the embodiment of the present disclosure, the location point parameters at least include vertex coordinates and a deflection included angle of the text box;

the step of rotationally adjusting the feature layer to a standard pose comprises:

determining a deflection angle between the characteristic image layer and a reference horizontal axis according to the vertex coordinates of the text box;

and rotating and adjusting all pixels of the characteristic image layer to be flush with the reference horizontal axis according to the deflection angle.

According to a specific implementation manner of the embodiment of the present disclosure, the step of rotationally adjusting all pixels of the feature layer to be flush with the reference horizontal axis according to the deflection angle includes:

extracting a date frame of the characteristic map layer;

determining a yaw angle between the date frame and the reference horizontal axis;

and adjusting all pixel areas of the overall feature layer containing the date frame to be flush with the reference horizontal axis according to the deflection angle.

According to a specific implementation manner of the embodiment of the present disclosure, the step of receiving the stamp picture to be recognized includes:

receiving an initial picture, wherein the initial picture comprises a pixel area where at least one target seal is located;

outputting a seal detection model to the initial picture, and detecting a pixel area where each target seal contained in the initial picture is located;

and generating the seal picture containing one target seal according to the pixel region where each target seal is located.

According to a specific implementation manner of the embodiment of the present disclosure, the location parameters at least include vertex pixels, head and tail pixels, and boundary pixels of the text box;

the step of obtaining the position point parameter of the text box of the target seal contained in the seal picture comprises the following steps:

inputting the stamp picture into a text box positioning model, wherein the text box positioning model comprises a first volume block, a second volume block and a third volume block;

obtaining a first output branch, a second output branch and a third output branch through the multilayer feature fusion effect from top to bottom among the first convolution block, the second convolution block and the third convolution block;

and recognizing boundary pixels positioned in a boundary frame of the text frame in the stamp picture according to the first output branch, recognizing head and tail pixels positioned at the head and/or tail of the text frame according to the second output branch, and recognizing vertex pixels positioned at the vertex position of the text frame according to the third output branch.

According to a specific implementation manner of the embodiment of the present disclosure, the stamp picture is a square picture, the single-side size range of the stamp picture is 256 to 400, the number of channels of the first volume block is 32, the number of channels of the second volume block is 64, and the number of channels of the third volume block is 128;

the step of obtaining a first output branch, a second output branch and a third output branch by a multilayer feature fusion effect from top to bottom among the first convolution block, the second convolution block and the third convolution block comprises:

performing convolution processing on the stamp picture through the first convolution block to obtain a first feature map with dimension of 128 × 32;

performing convolution processing on the first feature map through the second convolution block to obtain a second feature map with the dimension of 64x 64;

performing convolution processing on the second feature map through the third convolution block to obtain a third feature map with the dimension of 32 × 128;

performing upsampling processing on the third feature map to obtain a fourth feature map with dimension of 64 × 128;

merging the fourth feature map and the second feature map to obtain a fifth feature map with dimension of 64 × 192;

and performing convolution processing on the fifth feature map sequentially by using a convolution layer comprising 32 convolution layers of 1 × 1 filters, 32 convolution layers of 3 × 3 filters and 32 convolution layers of 3 × 3 filters to obtain the first output branch, the second output branch and the third output branch.

In a second aspect, an embodiment of the present disclosure provides a stamp text recognition apparatus, including:

the receiving module is used for receiving a stamp picture to be identified;

the acquisition module is used for acquiring the position point parameters of the text box of the target seal contained in the seal picture, wherein the position point parameters at least comprise the vertex coordinates of the text box;

the extraction module is used for extracting a characteristic image layer corresponding to the text box of the target seal in the seal picture according to the position point parameter of the text box;

the rotating module is used for rotating and adjusting the characteristic layer to a standard pose;

and the recognition module is used for performing text recognition on the text information in the feature map layer.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the stamp text recognition method in the first aspect or any implementation manner of the first aspect.

In a fourth aspect, an embodiment of the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for stamp text recognition in the first aspect or any implementation manner of the first aspect.

In a fifth aspect, the present disclosure also provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the stamp text recognition method in the foregoing first aspect or any implementation manner of the first aspect.

According to the stamp text recognition scheme in the embodiment of the disclosure, for a received stamp picture to be recognized, a text box of a target stamp is positioned by acquiring a position parameter of the text box, then a feature image layer corresponding to the text box is rotated and adjusted to a standard pose according to the position parameter of the text box, and then text recognition is performed on text information in the feature image layer. Therefore, the position point parameters of the text box are obtained firstly, and then the corresponding characteristic image layer is adjusted to the standard pose in a rotating mode, so that the accuracy of text recognition in the seal can be improved to a great extent, and the text box in different angles and directions can be recognized accurately and quickly.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for recognizing a stamp text according to an embodiment of the present disclosure;

fig. 2 and fig. 3 are schematic flow diagrams of each specific implementation of a stamp text recognition method according to an embodiment of the present disclosure;

fig. 4 is a partial schematic flow chart of another stamp text recognition method according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a text box positioning model related to a seal identification method according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a stamp text recognition apparatus according to an embodiment of the present disclosure;

fig. 7 is a schematic view of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. 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 is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present disclosure, and the drawings only show the components related to the present disclosure rather than the number, shape and size of the components in actual implementation, and the type, amount and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.

In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.

The embodiment of the disclosure provides a seal text recognition method. The stamp text recognition method provided by the embodiment may be executed by a computing device, and the computing device may be implemented as software, or implemented as a combination of software and hardware, and the computing device may be integrally disposed in a server, a terminal device, or the like.

Referring to fig. 1, a schematic flow chart of a method for identifying a stamp text according to an embodiment of the present disclosure is shown. As shown in fig. 1, the method mainly comprises the following steps:

s101, receiving a stamp picture to be identified;

the method for identifying the seal text provided by the embodiment is applied to the identification scenes of the seal text on corresponding pictures such as passports and invoices, and particularly aims at the scenes with high difficulty in identifying the seal text caused by various seal types, seal positions, seal angles and the like on passport pages. The stamp text recognition method provided by the embodiment is mainly used for recognizing text information in a stamp picture to be recognized so as to collect or count parameter information in a stamp.

The provided seal text recognition is applied to electronic equipment, and the electronic equipment is externally connected with or internally provided with an image acquisition device, so that the electronic equipment can acquire a seal picture to be recognized in advance through the image acquisition device and then perform text recognition operation in the acquired seal picture by using the provided method. In specific implementation, an image acquisition device may be arranged in front of a passage through which a user holds a passport for identity authentication, the user attaches a page where a seal to be identified in the passport is located to an image acquisition port of the image acquisition device, and the electronic device acquires a passport page picture acquired by the image acquisition device and serves as a seal picture to be identified in subsequent seal text identification.

The stamp picture in the embodiment mainly performs text recognition on a text box in a stamp on the picture, and preferably, the stamp picture to be recognized is a stamp slice only including a pixel area where the stamp is located, the stamp picture only includes stamp pixels to be currently subjected to text recognition, and does not include other stamp pixels or interference pixels, the text recognition calculation amount is small, and the accuracy is high.

For the condition that the received initial image contains a plurality of stamp pixels or other interference pixels, the outline position information of each stamp in the initial image can be obtained through an example segmentation algorithm, then the stamp image corresponding to each stamp is obtained by combining the outline position information, and the single stamp image is used as an input image of the stamp text identification process.

The practical segmentation algorithm referred to herein is that the electronic device automatically frames out different example regions from a picture by using a target detection method, and then performs pixel-by-pixel labeling in the different example regions by using a semantic segmentation method. Example segmentation algorithms employed in the present embodiment may include Mask-RCNN algorithm, YOACT algorithm, cascaded Mask-RCNN algorithm, and the like. After the contour position information of each seal in the picture to be identified is obtained according to the steps, the pixel characteristics pointed by the contour position information of each seal can be extracted, and the seal slice corresponding to the seal is obtained. Therefore, the stamp slice corresponding to each stamp only contains the pixel characteristics corresponding to the stamp, and does not contain other interference pixels which may influence text recognition.

S102, obtaining position point parameters of a text box of a target seal contained in the seal picture, wherein the position point parameters at least comprise vertex coordinates of the text box;

when text recognition is carried out, a text box in a stamp picture needs to be positioned, so that the position point parameters of the text box of a target stamp need to be acquired. Coordinate data corresponding to a specific pixel such as a vertex pixel, a head-tail pixel, or a boundary pixel of the text box. As shown in fig. 2 and fig. 3, the vertex pixel (e.g., a shown in fig. 2) may be a pixel corresponding to a vertex position of the stamp, for example, four vertex pixels of a rectangular stamp, the head and tail pixels (e.g., B shown in fig. 2) may be pixels corresponding to a head position or a tail position of the stamp, and the boundary pixel (e.g., C shown in fig. 2) may be a pixel of an edge region within the text box.

The electronic equipment can also be pre-loaded with a trained text box positioning model, and the text box positioning model can extract and fuse the pixel characteristics of the input stamp picture so as to obtain the site parameters of various specific pixels in the text box in the input stamp picture. Inputting the stamp picture into a text box positioning model in the electronic equipment, and rapidly acquiring various site parameters of the text box in the stamp picture through feature extraction and algorithm matching of the text box positioning model.

S103, extracting a characteristic layer corresponding to the text box of the target seal in the seal picture according to the position point parameter of the text box;

after the position point parameters of the text box are obtained according to the steps, the text box can be quickly positioned according to the parameters of various specific position points such as vertex pixels, head and tail pixels or boundary pixels in the text box, and then the characteristic image layer corresponding to the text box is extracted. As shown in fig. 3, the head or tail boundary pixels can predict 2 vertex coordinates, respectively. All feature pixels in the stamp picture form a feature layer of the text box, and the boundary pixels are used for predicting the vertex coordinates. The boundary pixels are defined as all pixels inside the dark frame at two ends, and the weighted average of all the boundary pixel predicted values is used for predicting two vertexes at two ends of a short edge of the head or the tail. And (3) predicting 2 vertexes by the boundary pixels of the head part and the tail part respectively to obtain 4 vertex coordinates finally.

In a specific embodiment, the step of positioning the text box in the stamp picture according to the location parameter of the text box may include:

determining an initial pixel area of the text box according to the vertex pixel;

correcting the initial pixel area to a standard pose according to the head and tail pixels;

marking the text box in the initial pixel area corrected to the standard pose according to the edge pixels.

According to the vertex pixels of the text box, a minimum bounding box corresponding to the text box can be generated, for example, a minimum bounding rectangle box, and the pixel regions located in the minimum bounding rectangle box are the initial pixel regions of the text box. Then, the initial pixel area is corrected according to the head and tail pixels of the text box, so that the initial pixel area is in a standard pose, and the standard pose is usually set to form an angle of 0 degree with the horizontal axis. And finally, screening out edge pixels from the corrected initial pixel area, wherein other pixel areas in the initial pixel area are the text box. Therefore, the text box corresponding to the pixel of the text information can be quickly positioned from the stamp picture.

After the position of the text box is determined, all pixel features corresponding to the text box are extracted from the picture, a feature layer containing all pixel features is obtained, and the subsequent text recognition process carries out corresponding operation on the feature layer.

S104, rotating and adjusting the feature layer to a standard pose;

considering that various stamping angles may exist during stamping, correspondingly, the text box of the target stamp on the stamp picture may have various directions. In order to improve the accuracy of text recognition, firstly, the feature layer corresponding to the text box is adjusted to a standard pose in a rotating manner according to the position point parameters of the text box. For example, a Region Of Interest rotation (ROI Rotate for short) rotation correction operation may be adopted to Rotate and adjust the feature layer corresponding to the acquired Region Of Interest.

According to a specific implementation manner of the embodiment of the present disclosure, the location parameter may at least include a vertex coordinate and a deflection included angle of the text box;

the rotation adjusting step may include:

Further, the step of adjusting all pixels of the feature map layer to be flush with the reference horizontal axis by rotating according to the deflection angle includes:

extracting a date frame in the feature map layer;

And rotating the feature map in any direction to the horizontal direction through the ROI Rotate correction operation. The ROI Rotate correction operation is mainly performed according to a text box of a date, namely, the rotation of the whole seal is realized when the included angle between the long edge of the text box of the date and a horizontal axis is adjusted to be 0.

Specifically, the region of interest of the feature map of "3 x3, 32" in fig. 5 corresponding to the 4 vertices is marked as ROI, the ROI is rotated to the horizontal direction, the ROI is rotated to the ROI in the horizontal direction, the feature sequences of the respective texts are obtained, wherein the four vertices of the ROI are sequential and can distinguish between 0 degree and 180 degrees, and the feature sequences of the respective texts are input into the LSTM. Wherein, 4 vertexes correspond to an ROI, a text box and a feature sequence of a text instance.

And S105, performing text recognition on the text information in the feature map layer.

After the text box is positioned in the stamp picture and the corresponding feature image layer is adjusted to the standard pose, text recognition can be carried out on text information in the feature image layer. The text Recognition may be performed in various ways, for example, according to an Optical Character Recognition (OCR) method.

According to a specific implementation manner of the embodiment of the present disclosure, as shown in fig. 4, the text recognition step may include:

s401, extracting a target feature sequence of the corresponding text information in the feature layer;

and the characteristic map layer corresponds to the pixel characteristic of the previous layer of the text box position, the speed limit characteristic of the text information in the text box is a partial characteristic sequence in the characteristic map layer, a target characteristic sequence corresponding to the text information in the characteristic map layer is extracted, the target characteristic sequence is fixed in height and variable in width, and the text information mainly comprises the entry and exit date, the country, the airport and other information.

Optionally, the step of extracting the target feature sequence of the corresponding text information in the feature layer includes:

and acquiring pixel characteristics corresponding to the position of the text frame in a preset layer of the seal picture, wherein the preset layer is the layer where the previous layer of characteristics of the seal picture is located.

Affine transformation is carried out according to the 4 vertex positions of the text box of the output layer to obtain the position of the text box corresponding to the feature map of the previous layer, and then the same operation is carried out: and rotating the text box on the feature map in any direction to the horizontal direction through the ROI Rotate correction operation.

S402, inputting the target characteristic sequence into a long-short term memory network structure for characteristic matching;

and S403, identifying the text information through a time-series classification loss function.

The electronic equipment is also loaded with a Long Short-Term Memory network (LSTM), the characteristic sequence is input into the LSTM, text recognition is carried out through a (CTC) loss function, end-to-end text recognition is achieved, and the seal text recognition speed is increased.

Of course, in other embodiments, other image text information identification methods can be used to quickly and accurately collect or identify text information in the stamp image.

According to the stamp text recognition method in the embodiment of the disclosure, for the received stamp picture to be recognized, the feature layer corresponding to the target stamp is extracted by obtaining the site parameter of the text box, the feature layer is rotated and adjusted to the standard pose according to the site parameter of the text box, and then text recognition is performed on the text information in the text box. Therefore, the text box is accurately positioned and rotationally adjusted to the standard pose, the accuracy of text recognition in the seal can be greatly improved, and the text box at different angles and directions can be accurately and quickly recognized.

On the basis of the foregoing embodiment, according to a specific implementation manner of the embodiment of the present disclosure, the location parameters at least include vertex pixels, head and tail pixels, and boundary pixels of the text box;

the step of obtaining the location parameter of the text box of the target stamp included in the stamp picture in step S103 may include:

As shown in fig. 5, the text box location model used may include a first convolution block conv block1, a second convolution block conv block2 and a third convolution block conv block3, wherein conv block1, conv block2, conv block3 are modified vgg16 convolution blocks with channel numbers of 32, 64, 128 respectively, wherein the filter size in convolution blocks conv block1, conv block2, conv block3 is still 3x 3. And/2 represents a picture image with a step size of 2, such as dimension 256x256x3, where 256x256 represents the length and width of the picture and 3 represents 3 color channels of r, g, and b of the picture.

In specific implementation, the stamp picture is a square picture, the single-side size range of the stamp picture is 256 to 400, the number of channels of the first rolling block is 32, the number of channels of the second rolling block is 64, and the number of channels of the third rolling block is 128;

Specifically, as shown in fig. 5, a square picture with a single-sided size ranging from 256 to 400 is initially input, for example, 256 × 256 is passed through a conv block 132,/2 filter of 3 × 3, where 32 represents 32 filters of 3 × 3,/2 represents a step size of the filter of 2, to obtain a 128 × 128x32 feature map, where 128 × 128 represents the length and width of the feature map, 32 represents the number of channels of the feature map, how many filters obtain a feature map of how many channels, then passed through conv block 264,/2 filter of 3x3 to obtain a 64 × 64x64 feature map, passed through conv block 3128,/2 to obtain a 32x32x128 feature map, passed through upsampling of the 32x32x128 feature map to obtain a 64x64x128 feature map, then passed through channel merging with feature map 64x64x64 obtained by conv block 264,/2 to obtain a 64x64x128 feature map, that is further passed through multi-layer merging with feature map 1, i.e through top merging with conv block 853, 32, namely 32 filters of 1x1, obtain a 64x64x32 characteristic diagram, then obtain a 64x64x32 characteristic diagram through 3x3,32, namely 32 filters of 3x3, then obtain a 64x64x32 characteristic diagram through 3x3,32, and finally obtain 3 output branches.

The first output branch 1x1, 1 represents 1 filter of 1x1 to obtain a feature map of 64x64x1, the feature map indicates whether each pixel is in a text bounding box, if yes, 1, otherwise 0, the second output branch 1x1, 2 represents 2 filters of 1x1 to obtain a feature map of 64x64x2, the feature map indicates whether each pixel belongs to the head or the tail of the text box, 64x64x2 wherein 2 represents the channel number of the feature map, the first channel represents whether each pixel belongs to the head of the text box, if yes, 1, if no, the second channel represents whether each pixel belongs to the tail of the text box, if yes, 1, if no, 0, the third output branch 1x1, 4 represents a feature map of 64x64x4 obtained by 4 filters of 1x1, feature maps of 4 channels, each channel respectively represents whether each pixel is one of 4 vertices, if so, it is 1, otherwise it is 0.

Therefore, the vertex pixel, the boundary pixel and the head and tail pixels of the text box in the stamp picture can be quickly and accurately identified.

In the method for positioning a text box in a stamp provided by this embodiment, the size of the received stamp picture is small, the number of convolution layers is small, the number of filters in each layer is also small, and the text box in any direction can be quickly positioned by predicting the positions of four vertices of the text box.

To sum up, according to the stamp text recognition method provided by the embodiment of the present disclosure, the text box in any direction is quickly positioned by predicting the positions of the four vertices of the text box, and then the ROI Rotate correction operation is performed, and when the date text box is obtained, the entire stamp is rotated to the horizontal direction according to the date text box, so that the text box in any direction is quickly recognized, and the text detection and the text recognition are performed in sequence, and the targets of each stage are relatively clear, and a lightweight network structure can be designed in each stage, so that the accuracy is relatively high, and the speed is relatively high.

Corresponding to the above method embodiment, referring to fig. 6, the embodiment of the present disclosure further provides a stamp text recognition apparatus 60, including:

the receiving module 601 is used for receiving a stamp picture to be identified;

an obtaining module 602, configured to obtain a location parameter of a text box of a target stamp included in the stamp picture, where the location parameter at least includes a vertex coordinate of the text box;

an extracting module 603, configured to extract, according to the location parameter of the text box, a feature layer corresponding to the text box of the target seal in the seal picture;

a rotating module 604, configured to rotate and adjust the feature layer to a standard pose;

and the recognition module 605 is configured to perform text recognition on the text information in the feature map layer.

The apparatus shown in fig. 6 may correspondingly execute the content in the above method embodiment, and details of the part not described in detail in this embodiment refer to the content described in the above method embodiment, which is not described again here.

Referring to fig. 7, an embodiment of the present disclosure also provides an electronic device 70, including:

at least one processor; and the number of the first and second groups,

the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the stamp text recognition method of the preceding method embodiment.

The disclosed embodiment also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the seal text recognition method in the foregoing method embodiment.

The disclosed embodiments also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the stamp text recognition method in the aforementioned method embodiments.

Referring now to FIG. 7, a schematic diagram of an electronic device 70 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 7, the electronic device 70 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 701 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage means 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the electronic apparatus 70 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Generally, the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touch pad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, or the like; an output device 707 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 708 including, for example, magnetic tape, hard disk, etc.; and a communication device 709. The communication means 709 may allow the electronic device 70 to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device 70 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure 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 flow chart. In such embodiments, the computer program may be downloaded and installed from a network via the communication means 709, or may be installed from the storage means 708, or may be installed from the ROM 702. The computer program, when executed by the processing device 701, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure 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 disclosure, 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 contrast, in the present disclosure, a computer readable signal medium may comprise 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: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, enable the electronic device to implement the schemes provided by the method embodiments.

Alternatively, the computer readable medium carries one or more programs, which when executed by the electronic device, enable the electronic device to implement the schemes provided by the method embodiments.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

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 disclosure. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.

The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present disclosure should be covered within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A stamp text recognition method is characterized by comprising the following steps:

receiving a stamp picture to be identified;

rotating and adjusting the characteristic layer to a standard pose;

2. The method of claim 1, wherein the step of text recognition of the text information in the feature map layer comprises:

extracting a target feature sequence of corresponding text information in the feature layer;

3. The method according to claim 2, wherein the step of extracting the feature layer corresponding to the text box of the target stamp from the stamp picture according to the position parameter of the text box comprises:

and acquiring pixel characteristics corresponding to the position of the text box in a preset layer of the seal picture, wherein the preset layer is the layer where the previous layer of characteristics of the seal picture is located.

4. The method of claim 1, wherein the location parameters include at least vertex coordinates and deflection angles of the text box;

5. The method according to claim 4, wherein the step of rotating all pixels of the feature layer to be aligned with the reference horizontal axis according to the deflection angle comprises:

extracting a date frame of the characteristic map layer;

6. The method according to any one of claims 1 to 5, characterized in that said step of receiving a stamp picture to be identified comprises:

7. The method of claim 6, wherein the location parameters include at least vertex pixels, head-to-tail pixels, and boundary pixels of the text box;

8. The method according to claim 7, wherein the stamp picture is a square picture, the single side size range of the stamp picture is 256 to 400, the number of lanes of the first volume block is 32, the number of lanes of the second volume block is 64, and the number of lanes of the third volume block is 128;

9. A stamp text recognition apparatus, comprising:

the receiving module is used for receiving a stamp picture to be identified;

10. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the stamp text recognition method of any one of the preceding claims 1-8.