CN112200202A

CN112200202A - Text detection method and device, electronic equipment and storage medium

Info

Publication number: CN112200202A
Application number: CN202011185740.9A
Authority: CN
Inventors: 毕研广; 胡志强
Original assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2021-01-08

Abstract

The disclosure relates to a text detection method and apparatus, an electronic device and a storage medium, wherein the method comprises: performing target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, wherein each text line comprises a plurality of character boundary points; and aiming at any text line, performing linear fitting on the plurality of character boundary points included in the text line to obtain a target boundary box corresponding to the text line. The embodiment of the disclosure can improve the detection precision of text detection on the image to be detected.

Description

Text detection method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer vision technologies, and in particular, to a text detection method and apparatus, an electronic device, and a storage medium.

Background

Optical Character Recognition (OCR) is an important research direction of computer vision, aiming at recognizing words from image data. OCR recognition typically involves two operations, a first step of text detection, i.e. detecting the area in which text is located in the image data, and a second step of character recognition, i.e. recognizing the characters in the area in which text is located. Text detection is the basis of OCR recognition, and therefore, accurate and efficient text detection is the key of OCR recognition.

Disclosure of Invention

The disclosure provides a text detection method and device, an electronic device and a storage medium.

According to an aspect of the present disclosure, there is provided a text detection method including: performing target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, wherein each text line comprises a plurality of character boundary points; and aiming at any text line, performing linear fitting on the plurality of character boundary points included in the text line to obtain a target boundary box corresponding to the text line.

In a possible implementation manner, the obtaining a plurality of text lines in the image to be detected by performing target detection on the image to be detected includes: determining the positions of a plurality of characters in the image to be detected in the vertical direction by carrying out target detection on the image to be detected; and determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction.

In a possible implementation manner, the determining the positions of the plurality of characters in the image to be detected in the vertical direction by performing target detection on the image to be detected includes: performing target detection on the image to be detected by using an anchor-frame-free target detection network, and determining a plurality of vertical line segments in the image to be detected, wherein the upper end point and the lower end point of each vertical line segment are used for indicating the boundary points of upper characters and lower characters in the vertical direction; the determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction comprises: determining the plurality of text lines according to the distance between the adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction, wherein each text line comprises a plurality of vertical line segments.

In one possible implementation manner, in a plurality of vertical line segments included in the same text line, a distance between adjacent vertical line segments is smaller than or equal to a first threshold; in a plurality of vertical line segments included in the same text line, the degree of offset in the vertical direction of adjacent vertical line segments is equal to or less than a second threshold value.

In a possible implementation manner, the obtaining, for any one of the text lines, a target bounding box corresponding to the text line by performing linear fitting on the multiple character boundary points included in the text line includes: performing linear fitting on the character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual error corresponding to the fitting boundary line is less than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line; and determining the target boundary frame according to the fitted boundary line.

In a possible implementation manner, the linearly fitting the multiple text boundary points included in the text line to obtain a fitted boundary line includes: performing linear fitting on the character boundary points to obtain a first fitted straight line; and determining the first fitting straight line as the fitting boundary line when the fitting residual corresponding to the first fitting straight line is less than or equal to the third threshold value.

In one possible implementation, the method further includes: determining whether an inflection point exists in the character boundary points under the condition that the fitting residual error corresponding to the first fitting straight line is larger than the third threshold, wherein the fitting residual error corresponding to the second fitting straight line is smaller than or equal to the third threshold, and the second fitting straight line are respectively obtained by performing straight line fitting on other character boundary points on two sides of the inflection point; determining the fitting boundary line according to the second fitting straight line and the third fitting straight line under the condition that the inflection point exists; and under the condition that the inflection point does not exist, performing curve fitting on the character boundary points to obtain a fitting curve, and determining the fitting curve as the fitting boundary line.

In one possible implementation, the method further includes: and performing character recognition on the text lines according to the target boundary boxes corresponding to the text lines.

According to an aspect of the present disclosure, there is provided a text detection apparatus including: the target detection module is used for carrying out target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, wherein each text line comprises a plurality of character boundary points; and the boundary determining module is used for performing linear fitting on the plurality of character boundary points included in the text line aiming at any text line to obtain a target boundary box corresponding to the text line.

In one possible implementation, the object detection module includes: the first determining submodule is used for determining the positions of a plurality of characters in the image to be detected in the vertical direction by carrying out target detection on the image to be detected; and the second determining submodule is used for determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction.

In a possible implementation manner, the first determining submodule is specifically configured to: performing target detection on the image to be detected by using an anchor-frame-free target detection network, and determining a plurality of vertical line segments in the image to be detected, wherein the upper end point and the lower end point of each vertical line segment are used for indicating the boundary points of upper characters and lower characters in the vertical direction; the second determining submodule is specifically configured to: determining the plurality of text lines according to the distance between the adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction, wherein each text line comprises a plurality of vertical line segments.

In one possible implementation, the boundary determining module includes: the linear fitting submodule is used for performing linear fitting on the character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual error corresponding to the fitting boundary line is smaller than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line; and the boundary determining submodule is used for determining the target boundary frame according to the fitted boundary line.

In one possible implementation, the linear fitting submodule includes: the linear fitting unit is used for performing linear fitting on the character boundary points to obtain a first fitted straight line; and a first determining unit, configured to determine the first fitted straight line as the fitted boundary line when a fitted residual corresponding to the first fitted straight line is equal to or less than the third threshold.

In one possible implementation, the linear fitting sub-module further includes: a second determining unit, configured to determine whether an inflection point exists in the multiple character boundary points when a fitting residual corresponding to the first fitted straight line is greater than the third threshold, where the fitting residual is less than or equal to the third threshold, and the second fitted straight line are obtained by respectively performing straight line fitting on other character boundary points on both sides of the inflection point; a third determining unit configured to determine the fitted boundary line from the second fitted straight line and the third fitted straight line if the inflection point exists; and the curve fitting unit is used for performing curve fitting on the character boundary points under the condition that the inflection point does not exist to obtain a fitting curve, and determining the fitting curve as the fitting boundary line.

In one possible implementation, the apparatus further includes: and the character recognition module is used for performing character recognition on the text lines according to the target boundary boxes corresponding to the text lines.

According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

In the embodiment of the disclosure, the target detection is performed on the image to be detected to obtain the plurality of text lines in the image to be detected, and since the plurality of character boundary points included in each text line can reflect the region position of the text line, for any text line, the target boundary box with higher accuracy corresponding to the text line can be obtained by performing linear fitting on the plurality of character boundary points included in the text line, so that the detection accuracy of the text detection on the image to be detected is effectively improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

FIG. 1 shows a flow diagram of a text detection method according to an embodiment of the present disclosure;

FIG. 2 shows a schematic diagram of an image to be detected according to an embodiment of the present disclosure;

FIG. 3 illustrates a schematic diagram of determining a plurality of vertical segments in an image to be detected according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of a plurality of lines of text in an image to be detected, according to an embodiment of the present disclosure;

FIG. 5 illustrates a schematic diagram of a target bounding box according to an embodiment of the present disclosure;

FIG. 6 illustrates a schematic diagram of a target bounding box according to an embodiment of the present disclosure;

FIG. 7 shows a block diagram of a text detection apparatus according to an embodiment of the present disclosure;

FIG. 8 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure;

fig. 9 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

Fig. 1 shows a flow diagram of a text detection method according to an embodiment of the present disclosure. The method may be performed by an electronic device such as a terminal device or a server, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and the like, and the method may be implemented by a processor calling a computer readable instruction stored in a memory. Alternatively, the method may be performed by a server. As shown in fig. 1, the method may include:

in step S11, a plurality of text lines in the image to be detected is obtained by performing target detection on the image to be detected, where each text line includes a plurality of text boundary points.

In step S12, for any text line, a target bounding box corresponding to the text line is obtained by performing linear fitting on a plurality of character boundary points included in the text line.

In practical application, the image to be detected may be a hospital bill, a physical examination report, a diagnosis report, etc. in a medical direction, a financial report form, an insurance document, etc. in a financial direction, or may be in other forms, which is not specifically limited by the present disclosure. Each text line in the image to be detected may be composed of characters with different numbers and sizes, the length-width ratio variation range of the text line itself is large, and for a long text line, non-rigid deformation may occur, resulting in bending distortion of the text line, resulting in increased difficulty in text detection of the image to be detected. Fig. 2 shows a schematic diagram of an image to be detected according to an embodiment of the present disclosure. As shown in fig. 2, the image to be detected has a non-rigid deformation, so that a long text line in the image to be detected has a bending distortion.

In a possible implementation manner, obtaining a plurality of text lines in an image to be detected by performing target detection on the image to be detected includes: and carrying out target detection on the image to be detected by using the anchor-frame-free target detection network to obtain a plurality of text lines.

In the related art, an anchor frame-carrying target detection network is usually adopted to perform target detection on an image to be detected, and a bounding box corresponding to a text line in the image to be detected is directly obtained. However, in practical application, the length-width ratio change range of different text lines in an image to be detected is large, so that a large number of anchor frames with different sizes need to be involved in a target detection network with the anchor frames in advance, and the network training and detection speed is low; in addition, because the text line in the image to be detected may have bending distortion in practical application, the accuracy of the bounding box corresponding to the text line obtained by directly regressing the preset anchor box in the target detection network with the anchor box is low.

In the embodiment of the disclosure, the target detection is performed on the image to be detected by using the anchor-frame-free target detection network, that is, the anchor frame design is not required in the network training stage, so that the detection efficiency can be effectively improved.

In a possible implementation manner, obtaining a plurality of text lines in an image to be detected by performing target detection on the image to be detected includes: determining the positions of a plurality of characters in the image to be detected in the vertical direction by performing target detection on the image to be detected; and determining a plurality of text lines according to the positions of the plurality of texts in the vertical direction.

In the embodiment of the disclosure, the anchor-frame-free target detection network may be used to locate characters in an image to be detected and determine boundaries of the characters, where the anchor-frame-free target detection network includes classification branches and regression branches. The classification branch is utilized to position a plurality of characters in the image to be detected, for example, for a certain pixel point in the image to be detected, the classification branch is utilized to judge whether the pixel point corresponds to a character pixel point or a background pixel point. And regressing the classification result of the classification branch by using the regression branch, for example, determining upper and lower boundary points of the characters, and further obtaining the positions of the characters in the vertical direction.

In one possible implementation manner, determining the positions of a plurality of characters in the image to be detected in the vertical direction by performing target detection on the image to be detected includes: performing target detection on an image to be detected by using an anchor-frame-free target detection network, and determining a plurality of vertical line segments in the image to be detected, wherein the upper end point and the lower end point of each vertical line segment are used for indicating the boundary points of upper characters and lower characters in the vertical direction; determining a plurality of text lines according to the positions of the plurality of texts in the vertical direction, wherein the determining comprises the following steps: and determining a plurality of text lines according to the distance between the adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction, wherein each text line comprises a plurality of vertical line segments.

FIG. 3 illustrates a schematic diagram of determining a plurality of vertical line segments in an image to be detected according to an embodiment of the present disclosure. As shown in fig. 3, for the text line "seen under the mirror" in the image to be detected: "the upper and lower word boundary points of a plurality of words can be located by using the classification branch in the anchor-free target detection network, and a plurality of vertical line segments (regression line segments) corresponding to the text line are regressed by using the regression branch in the anchor-free target detection network according to the upper and lower word boundary points of the plurality of words, wherein the upper and lower end points of each vertical line segment are used for indicating the upper and lower word boundary points of the words in the vertical direction.

In a possible implementation manner, because the vertical lines obtained by regression of the plurality of text pixel points are similar or overlapped, redundant vertical lines can be filtered by a non-maximum suppression method.

In a possible implementation manner, after the vertical line segments corresponding to the whole image of the image to be detected are obtained by using the anchor-frame-free target detection network, a plurality of text lines in the image to be detected are determined according to factors such as the distance between adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction.

In one possible implementation manner, among a plurality of vertical line segments included in the same text line, the distance between adjacent vertical line segments is smaller than or equal to a first threshold; in a plurality of vertical line segments included in the same text line, the degree of shift in the vertical direction of adjacent vertical line segments is equal to or less than a second threshold value.

When the distance between adjacent vertical line segments is less than or equal to a first threshold, or the offset degree of the adjacent vertical line segments in the vertical direction is less than or equal to a second threshold, it may be determined that the adjacent vertical line segments correspond to the same text line. When the distance between adjacent vertical line segments is greater than a first threshold, or the offset degree of the adjacent vertical line segments in the vertical direction is greater than a second threshold, it may be determined that the adjacent vertical line segments correspond to different text lines.

FIG. 4 shows a schematic diagram of a plurality of lines of text in an image to be detected according to an embodiment of the present disclosure. As shown in fig. 4, a plurality of text lines in the image to be detected can be obtained according to the distance between adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction. In fig. 4, the "Guangdong-West institute of technology", "pathology research laboratory", and "affiliated hospital pathology department" are three different lines of text because the vertical line segment corresponding to the "broad-east-West institute of technology" is shifted from the line segment between the "pathology research laboratory" and the "affiliated hospital pathology department" to a large extent in the vertical direction.

In a possible implementation manner, for any text line, obtaining a target bounding box corresponding to the text line by performing linear fitting on a plurality of character boundary points included in the text line includes: performing linear fitting on a plurality of character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual corresponding to the fitting boundary line is less than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line; and determining a target boundary frame according to the fitted boundary line.

And aiming at any text line in the determined image to be detected, performing linear fitting on a plurality of character boundary points included in the text line to obtain a fitting boundary line. For example, linear fitting is performed on upper end points of a plurality of vertical line segments included in the text line to obtain an upper fitting boundary line; and performing linear fitting on lower end points of a plurality of vertical line segments included in the text line to obtain a lower fitting boundary line. When the fitting residuals of the upper fitting boundary line and the lower fitting boundary line are both less than or equal to the third threshold, the target boundary box of the text line can be determined according to the upper fitting boundary line and the lower fitting boundary line.

In one possible implementation, the fitting residual refers to an average offset distance between each text boundary point before fitting and the fitting boundary line after fitting.

In one possible implementation manner, performing linear fitting on a plurality of text boundary points included in a text line to obtain a fitted boundary line includes: performing linear fitting on the character boundary points to obtain a first fitted straight line; and determining the first fitting straight line as a fitting boundary line when the fitting residual corresponding to the first fitting straight line is less than or equal to a third threshold value.

For example, straight line fitting is performed on upper end points of a plurality of vertical line segments included in the text line, so that a first upper fitting straight line is obtained; and performing straight line fitting on lower end points of a plurality of vertical straight line segments included in the text line to obtain a first lower fitting straight line.

And when the fitting residual errors of the first upper fitting straight line and the first lower fitting straight line are less than or equal to a third threshold value, determining the first upper fitting straight line as an upper fitting boundary line, and determining the first lower fitting straight line as a lower fitting boundary line.

And determining that the target boundary frame corresponding to the obtained text line is a quadrangle according to the upper fitting boundary line and the lower fitting boundary line because the upper fitting boundary line and the lower fitting boundary line are both straight lines. FIG. 5 illustrates a schematic diagram of a target bounding box according to an embodiment of the present disclosure.

In one possible implementation, the method further includes: determining whether an inflection point exists in the character boundary points under the condition that the fitting residual error corresponding to the first fitting straight line is larger than a third threshold, wherein the fitting residual errors corresponding to the second fitting straight line are smaller than or equal to the third threshold, and the second fitting straight line are obtained by respectively performing straight line fitting on other character boundary points on two sides of the inflection point; and determining a fitting boundary line according to the second fitting straight line and the third fitting straight line under the condition that the inflection point exists.

For example, after straight line fitting is performed on a plurality of character boundary points included in a text line to obtain a first fitted straight line, a fitted residual corresponding to the first fitted straight line is determined, where the first fitted straight line may be a first upper fitted straight line or a first lower fitted straight line.

And under the condition that the fitting residual error corresponding to the first fitting straight line is greater than a third threshold value, traversing the plurality of character boundary points, and determining whether an inflection point exists in the character boundary points, so that the corresponding fitting residual errors are less than or equal to the third threshold value for the second fitting straight line and the third fitting straight line which are obtained by performing straight line fitting on other character boundary points on two sides of the inflection point.

For example, the fitted residuals of the first up-fitted straight line and the first down-fitted straight line are both greater than the third threshold. And traversing upper end points of a plurality of vertical straight line segments included in the text line, and obtaining a second upper fitting straight line and a third upper fitting straight line under the condition that inflection points exist in the plurality of upper end points. And traversing lower end points of a plurality of vertical straight line segments included in the text line, and obtaining a second lower fitting straight line and a third lower fitting straight line under the condition that inflection points exist in the lower end points.

And determining an upper fitting boundary line (broken line) according to the second upper fitting straight line and the third upper fitting straight line, determining a lower fitting boundary line (broken line) according to the second lower fitting straight line and the third lower fitting straight line, and determining that the target boundary box corresponding to the obtained text line is a polygon according to the upper fitting boundary line and the lower fitting boundary line. FIG. 6 illustrates a schematic diagram of a target bounding box according to an embodiment of the present disclosure.

By determining the inflection point, a target boundary box with higher precision can be determined for a longer text line with bending distortion in the image to be detected, so that the accuracy of text detection on the image to be detected is effectively improved.

In one possible implementation, the method further includes: and under the condition that no inflection point exists, performing curve fitting on the character boundary points to obtain a fitting curve, and determining the fitting curve as a fitting boundary line.

Under the condition that the fitting residual error corresponding to the first fitting straight line is larger than the third threshold value and no inflection point exists in the character points, curve fitting can be performed on the character boundary points to obtain a fitting curve, and then the fitting curve is determined as a fitting boundary line. And further determining a target boundary box of the text line according to the fitted boundary line in the form of a curve.

Through curve fitting, a target boundary box with higher precision can be determined for a longer text line with bending distortion in the image to be detected, so that the accuracy of text detection on the image to be detected is effectively improved.

The method is adopted to determine and obtain the target boundary box of each text line in the image to be detected, and further obtain the text detection result corresponding to the image to be detected.

And performing character recognition on each text line according to a target boundary box corresponding to each text line included in a text detection result of the image to be detected, so as to obtain a text recognition result of the image to be detected.

In the embodiment of the disclosure, the plurality of text lines in the image to be detected are obtained by performing the target detection on the image to be detected, and since the plurality of character boundary points included in each text line can reflect the region position of the text line, for any text line, the target boundary box with higher accuracy corresponding to the text line can be obtained by performing the linear fitting on the plurality of character boundary points included in the text line, so that the detection accuracy of the text detection on the image to be detected is effectively improved.

According to the embodiment of the disclosure, the detection precision of text detection on the image to be detected can be effectively improved aiming at the image to be detected with a large amount of dense characters, the image to be detected with long-line characters, the image to be detected with text line distortion and the like.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

In addition, the present disclosure also provides a text detection apparatus, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any one of the text detection methods provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding descriptions in the methods section are not repeated.

Fig. 7 shows a block diagram of a text detection apparatus according to an embodiment of the present disclosure. As shown in fig. 7, the apparatus 70 includes:

the target detection module 71 is configured to perform target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, where each text line includes a plurality of text boundary points;

and a boundary determining module 72, configured to perform linear fitting on a plurality of character boundary points included in a text line to obtain a target boundary box corresponding to the text line, for any text line.

In one possible implementation, the object detection module 71 includes:

the first determining submodule is used for determining the positions of a plurality of characters in the image to be detected in the vertical direction by carrying out target detection on the image to be detected;

and the second determining submodule is used for determining a plurality of text lines according to the positions of the plurality of texts in the vertical direction.

In a possible implementation manner, the first determining submodule is specifically configured to:

performing target detection on an image to be detected by using an anchor-frame-free target detection network, and determining a plurality of vertical line segments in the image to be detected, wherein the upper end point and the lower end point of each vertical line segment are used for indicating the boundary points of upper characters and lower characters in the vertical direction;

the second determination submodule is specifically configured to:

and determining a plurality of text lines according to the distance between the adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction, wherein each text line comprises a plurality of vertical line segments.

In one possible implementation manner, among a plurality of vertical line segments included in the same text line, the distance between adjacent vertical line segments is smaller than or equal to a first threshold;

in a plurality of vertical line segments included in the same text line, the degree of shift in the vertical direction of adjacent vertical line segments is equal to or less than a second threshold value.

In one possible implementation, the boundary determining module 72 includes:

the linear fitting submodule is used for performing linear fitting on a plurality of character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual error corresponding to the fitting boundary line is smaller than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line;

and the boundary determining submodule is used for determining a target boundary frame according to the fitted boundary line.

In one possible implementation, the linear fitting submodule includes:

the linear fitting unit is used for performing linear fitting on the character boundary points to obtain a first fitting linear line;

and a first determining unit, configured to determine the first fitted straight line as a fitted boundary line when a fitted residual corresponding to the first fitted straight line is equal to or less than a third threshold value.

In one possible implementation, the linear fitting sub-module further includes:

the second determining unit is used for determining whether an inflection point exists in the character boundary points under the condition that the fitting residual error corresponding to the first fitting straight line is larger than a third threshold, wherein the corresponding fitting residual errors are smaller than or equal to the third threshold, the second fitting straight line and the second fitting straight line are respectively obtained by straight line fitting of other character boundary points on two sides of the inflection point;

a third determining unit, configured to determine a fitting boundary line according to the second fitted straight line and the third fitted straight line in the case where an inflection point exists;

and the curve fitting unit is used for performing curve fitting on the character boundary points under the condition that no inflection point exists to obtain a fitting curve and determining the fitting curve as a fitting boundary line.

In one possible implementation, the apparatus 70 further includes:

and the character recognition module is used for performing character recognition on the plurality of text lines according to the target boundary boxes corresponding to the plurality of text lines.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

The disclosed embodiments also provide a computer program product comprising computer readable code, which when run on a device, a processor in the device executes instructions for implementing a text detection method as provided in any of the above embodiments.

The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed cause a computer to perform the operations of the text detection method provided in any of the above embodiments.

The electronic device may be provided as a terminal, server, or other form of device.

FIG. 8 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure. As shown in fig. 8, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Referring to fig. 8, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a Complementary Metal Oxide Semiconductor (CMOS) or Charge Coupled Device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as a wireless network (WiFi), a second generation mobile communication technology (2G) or a third generation mobile communication technology (3G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

Fig. 9 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure. As shown in fig. 9, electronic device 1900 may be provided as a server. Referring to fig. 9, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as the Microsoft Server operating system (Windows Server), stored in the memory 1932^TM) Apple Inc. of the present application based on the graphic user interface operating System (Mac OS X)^TM) Multi-user, multi-process computer operating system (Unix)^TM) Free and open native code Unix-like operating System (Linux)^TM) Open native code Unix-like operating System (FreeBSD)^TM) Or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions 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). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

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 instructions, which comprises one or more executable instructions for implementing the specified logical function(s). 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 computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like. Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A text detection method, comprising:

performing target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, wherein each text line comprises a plurality of character boundary points;

and aiming at any text line, performing linear fitting on the plurality of character boundary points included in the text line to obtain a target boundary box corresponding to the text line.

2. The method according to claim 1, wherein the obtaining of the plurality of text lines in the image to be detected by performing the target detection on the image to be detected comprises:

determining the positions of a plurality of characters in the image to be detected in the vertical direction by carrying out target detection on the image to be detected;

and determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction.

3. The method according to claim 2, wherein the determining the position of the plurality of characters in the image to be detected in the vertical direction by performing the target detection on the image to be detected comprises:

performing target detection on the image to be detected by using an anchor-frame-free target detection network, and determining a plurality of vertical line segments in the image to be detected, wherein the upper end point and the lower end point of each vertical line segment are used for indicating the boundary points of upper characters and lower characters in the vertical direction;

the determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction comprises:

determining the plurality of text lines according to the distance between the adjacent vertical line segments and/or the offset degree of the adjacent vertical line segments in the vertical direction, wherein each text line comprises a plurality of vertical line segments.

4. The method according to claim 3, wherein, of the plurality of vertical line segments included in the same text line, a distance between adjacent vertical line segments is equal to or less than a first threshold value;

in a plurality of vertical line segments included in the same text line, the degree of offset in the vertical direction of adjacent vertical line segments is equal to or less than a second threshold value.

5. The method according to any one of claims 1 to 4, wherein the obtaining, for any one of the text lines, a target bounding box corresponding to the text line by performing linear fitting on the plurality of literal boundary points included in the text line includes:

performing linear fitting on the character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual error corresponding to the fitting boundary line is less than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line;

and determining the target boundary frame according to the fitted boundary line.

6. The method of claim 5, wherein said linearly fitting said plurality of literal boundary points included in said line of text to obtain a fitted boundary line comprises:

performing linear fitting on the character boundary points to obtain a first fitted straight line;

and determining the first fitting straight line as the fitting boundary line when the fitting residual corresponding to the first fitting straight line is less than or equal to the third threshold value.

7. The method of claim 6, further comprising:

determining whether an inflection point exists in the character boundary points under the condition that the fitting residual error corresponding to the first fitting straight line is larger than the third threshold, wherein the fitting residual error corresponding to the second fitting straight line is smaller than or equal to the third threshold, and the second fitting straight line are respectively obtained by performing straight line fitting on other character boundary points on two sides of the inflection point;

determining the fitting boundary line according to the second fitting straight line and the third fitting straight line under the condition that the inflection point exists;

and under the condition that the inflection point does not exist, performing curve fitting on the character boundary points to obtain a fitting curve, and determining the fitting curve as the fitting boundary line.

8. The method according to any one of claims 1 to 7, further comprising:

and performing character recognition on the text lines according to the target boundary boxes corresponding to the text lines.

9. A text detection apparatus, comprising:

the target detection module is used for carrying out target detection on an image to be detected to obtain a plurality of text lines in the image to be detected, wherein each text line comprises a plurality of character boundary points;

and the boundary determining module is used for performing linear fitting on the plurality of character boundary points included in the text line aiming at any text line to obtain a target boundary box corresponding to the text line.

10. The apparatus of claim 9, wherein the target detection module comprises:

and the second determining submodule is used for determining the plurality of text lines according to the positions of the plurality of texts in the vertical direction.

11. The apparatus of claim 10, wherein the first determination submodule is specifically configured to:

the second determining submodule is specifically configured to:

12. The apparatus according to claim 11, wherein, of the plurality of vertical line segments included in the same text line, a distance between adjacent vertical line segments is equal to or less than a first threshold;

13. The apparatus of any of claims 9 to 12, wherein the boundary determination module comprises:

the linear fitting submodule is used for performing linear fitting on the character boundary points included in the text line to obtain a fitting boundary line, wherein a fitting residual error corresponding to the fitting boundary line is smaller than or equal to a third threshold value, and the fitting boundary line comprises an upper fitting boundary line and a lower fitting boundary line;

and the boundary determining submodule is used for determining the target boundary frame according to the fitted boundary line.

14. The apparatus of claim 13, wherein the linear fitting sub-module comprises:

the linear fitting unit is used for performing linear fitting on the character boundary points to obtain a first fitted straight line;

and a first determining unit, configured to determine the first fitted straight line as the fitted boundary line when a fitted residual corresponding to the first fitted straight line is equal to or less than the third threshold.

15. The apparatus of claim 14, wherein the linear fitting sub-module further comprises:

a second determining unit, configured to determine whether an inflection point exists in the multiple character boundary points when a fitting residual corresponding to the first fitted straight line is greater than the third threshold, where the fitting residual is less than or equal to the third threshold, and the second fitted straight line are obtained by respectively performing straight line fitting on other character boundary points on both sides of the inflection point;

a third determining unit configured to determine the fitted boundary line from the second fitted straight line and the third fitted straight line if the inflection point exists;

and the curve fitting unit is used for performing curve fitting on the character boundary points under the condition that the inflection point does not exist to obtain a fitting curve, and determining the fitting curve as the fitting boundary line.

16. The apparatus of any one of claims 9 to 15, further comprising:

and the character recognition module is used for performing character recognition on the text lines according to the target boundary boxes corresponding to the text lines.

17. An electronic device, comprising: a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any one of claims 1 to 8.

18. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 8.