Device for automatically recognizing pictures, characters and sounds in real time

Abstract

The invention discloses a device for automatically recognizing pictures, characters and sound in real time, which comprises a data acquisition module used for acquiring picture, character or sound information of a specified target; the extraction module is used for extracting knowledge points in the picture, character or sound information; the knowledge base module is used for storing knowledge data information; the comparison module is used for comparing the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain comparison information; and the correcting module is used for correcting the knowledge points of the specified target according to the comparison information. Compared with the prior art, characters, pictures and sounds can be automatically recognized, the purpose of automatically correcting homework is achieved, and therefore the correcting time of teachers can be shortened.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a device for automatically recognizing pictures, texts and sounds in real time. Background Art

[0002] In traditional teaching systems, teachers often need to spend a lot of time marking students' homework. With the development of electronic teaching, teachers can use PC or PAD to assist in teaching. The homework submitted by students is usually uploaded to the teaching system by taking photos, and most of the homework submitted by students are answers to multiple-choice and fill-in-the-blank questions. Teachers need to manually mark homework, which consumes a lot of teachers' time and cannot improve teaching efficiency. Summary of the invention

[0003] The present invention provides a device for automatically recognizing pictures, texts and sounds in real time, which can automatically recognize texts, pictures and sounds to achieve the purpose of automatically correcting homework, thereby reducing the correction time of teachers.

[0004] In order to achieve the above object, the present invention adopts the following technical solution: a device for automatically recognizing pictures, texts and sounds in real time, comprising:

[0005] The data acquisition module is used to obtain the image, text or sound information of the specified target;

[0006] Extraction module, used to extract knowledge points from pictures, text or sound information;

[0007] Knowledge base module, used to store knowledge data information;

[0008] A comparison module is used to compare the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain comparison information;

[0009] The correction module is used to correct the knowledge points of the designated target according to the comparison information.

[0010] As a further description of the above technical solution:

[0011] The data acquisition module includes a photo taking module and a sound recording module. The photo taking module is used to take pictures and texts of the designated target, and the sound recording module is used to record sounds.

[0012] As a further description of the above technical solution:

[0013] The camera module includes a contour acquisition unit, a comparison unit, a calculation unit, a deformation unit and a recognition unit. The contour acquisition unit recognizes the text carrier in the image and obtains the contour of the carrier. The comparison unit compares the contour of the carrier with the standard contour. If the similarity exceeds a preset threshold, the carrier is judged to be a preset regular carrier. The calculation unit, when judging that the carrier is a preset regular carrier, divides the carrier into several areas and calculates the curvature corresponding to the edge of each area. The deformation unit determines the deformation value corresponding to the current area according to the minimum curvature and the curvature of the current area, and stretches the current area according to the corresponding deformation value. The recognition unit performs text recognition on the stretched image.

[0014] As a further description of the above technical solution:

[0015] The sound recording module includes a tracking submodule and a recording submodule. The tracking submodule is used to track a designated target, and the recording submodule records sound according to the target tracked by the tracking submodule.

[0016] As a further description of the above technical solution:

[0017] The extraction module includes a picture recognition module, a text recognition module and a sound recognition module. The picture recognition module is used to extract knowledge points in pictures, the text recognition module is used to extract knowledge points in texts, and the sound recognition module is used to extract knowledge points in sounds.

[0018] As a further description of the above technical solution:

[0019] The image recognition module includes a separation module, an encoding module, a matching module and a recognition module. The separation module is used to separate the text in the image into multiple rectangular text boxes, and the number of the rectangular text boxes is consistent with the number of the text in the image; the encoding module is used to encode the text in the rectangular text boxes separated by the separation module into a character string to be matched; the matching module is used to match the character string to be matched after being encoded by the encoding module with a character string in a preset character library; and the recognition module is used to identify the text corresponding to the character string to be matched according to the matching result of the matching module.

[0020] As a further description of the above technical solution:

[0021] It also includes a translation module, which is used to translate pictures, text or sound information.

[0022] As a further description of the above technical solution:

[0023] The data acquisition module, the extraction module, the knowledge base module, the comparison module and the correction module are integrated on the wearable component.

[0024] As a further description of the above technical solution:

[0025] The wearing component is glasses, a hat or a watch.

[0026] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0027] 1. In the present invention, the image, text or sound information of the specified target can be obtained through the set data acquisition module, and then the extraction module extracts the knowledge points in the image, text or sound information. The comparison module compares the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain comparison information. The correction module corrects the knowledge points of the specified target according to the comparison information to achieve the purpose of automatic correction.

[0028] 2. In the present invention, the photographing module is used to purposefully identify that the carrier of the picture and text is a preset regular carrier, and then the deformation value of the carrier is calculated according to the curvature, so that the deformed carrier is restored to the original shape of the carrier, and then the text is recognized on the stretched picture, thereby improving the recognition rate of the text and reducing the error rate of text recognition, thereby improving the accuracy of correction.

[0029] 3. In the present invention, the text in the picture is split into multiple rectangular text boxes, the number of which is consistent with the number of the text in the picture, and the text is recognized word by word, which can improve the accuracy of text recognition. Secondly, the text in the rectangular text box is encoded as a string to be matched, and the string to be matched is matched with the string in a preset text library; finally, the text corresponding to the string to be matched is identified according to the matching result, which reduces the time consumed in recognizing the text and improves the recognition performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 The present invention is a logic block diagram of a device for automatically recognizing pictures, texts and sounds in real time. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1 The present invention provides a technical solution: a device for automatically recognizing pictures, texts and sounds in real time, comprising:

[0034] The data acquisition module is used to obtain the image, text or sound information of the specified target;

[0035] Extraction module, used to extract knowledge points from pictures, text or sound information;

[0036] Knowledge base module, used to store knowledge data information;

[0037] A comparison module is used to compare the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain comparison information;

[0038] The correction module is used to correct the knowledge points of the designated target according to the comparison information.

[0039] The data acquisition module includes a photo taking module and a sound recording module. The photo taking module is used to take pictures and texts of the designated target, and the sound recording module is used to record sounds.

[0040] The camera module includes a contour acquisition unit, a comparison unit, a calculation unit, a deformation unit and a recognition unit. The contour acquisition unit recognizes the text carrier in the picture and obtains the contour of the carrier. The comparison unit compares the contour of the carrier with the standard contour. If the similarity exceeds a preset threshold, the carrier is judged to be a preset regular carrier. The calculation unit divides the carrier into several areas when it is judged that the carrier is a preset regular carrier, and calculates the arc corresponding to the edge of each area. The deformation unit determines the deformation value corresponding to the current area according to the minimum arc and the arc of the current area, and stretches the current area according to the corresponding deformation value. The recognition unit recognizes the text after stretching. The camera module purposefully identifies that the carrier of the text in the picture is a preset regular carrier, and then calculates the deformation value of the carrier according to the arc, so that the deformed carrier is restored to the original shape of the carrier, and then recognizes the text on the stretched picture, thereby improving the recognition rate of the text and reducing the error rate of text recognition, thereby improving the accuracy of correction.

[0041] The sound recording module includes a tracking submodule and a recording submodule, wherein the tracking submodule is used to track a designated target, and the recording submodule records the target tracked by the tracking submodule. When recording sound, recording errors can be prevented and the accuracy of sound recording can be improved. When translating on the spot, the accuracy of translation can be improved.

[0042] The extraction module includes a picture recognition module, a text recognition module and a sound recognition module. The picture recognition module is used to extract knowledge points in pictures, the text recognition module is used to extract knowledge points in texts, and the sound recognition module is used to extract knowledge points in sounds.

[0043] The image recognition module includes a separation module, an encoding module, a matching module and a recognition module. The separation module is used to separate the text in the image into a plurality of rectangular text frames, the number of which is consistent with the number of the text in the image; the encoding module is used to encode the text in the rectangular text frames separated by the separation module into a string to be matched; the matching module is used to match the string to be matched encoded by the encoding module with a string in a preset text library; and the recognition module is used to identify the text corresponding to the string to be matched according to the matching result of the matching module. Splitting the text in the image into a plurality of rectangular text frames, the number of which is consistent with the number of the text in the image, and identifying each word can improve the accuracy of identifying the text. Secondly, encoding the text in the rectangular text frame into a string to be matched, and matching the string to be matched with a string in a preset text library; finally, identifying the text corresponding to the string to be matched according to the matching result, which reduces the time consumed in identifying the text and improves the recognition performance.

[0044] It also includes a translation module, which is used to translate pictures, text or sound information.

[0045] The data acquisition module, the extraction module, the knowledge base module, the comparison module and the correction module are integrated on the wearable component.

[0046] The wearing part is glasses, a hat or a watch. This is convenient for users to use, and the wearing part in this embodiment is glasses.

[0047] Working principle: Through the set data acquisition module, the picture, text or sound information of the specified target can be obtained, and then the extraction module extracts the knowledge points in the picture, text or sound information. The comparison module compares the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain the comparison information. The correction module corrects the knowledge points of the specified target according to the comparison information to achieve the purpose of automatic correction. The camera module purposefully identifies that the carrier of the picture and text is a preset regular carrier, and then calculates the deformation value of the carrier according to the arc, so that the deformed carrier is restored to the original shape of the carrier, and then recognizes the text on the stretched picture, thereby improving the recognition rate of the text and reducing the error rate of text recognition, thereby improving the accuracy of correction. The text in the image is split into multiple rectangular text boxes, the number of which is consistent with the number of text in the image, and recognition is performed word by word, which can improve the accuracy of text recognition. Secondly, the text in the rectangular text box is encoded as a string to be matched, and the string to be matched is matched with the string in the preset text library; finally, the text corresponding to the string to be matched is identified based on the matching result, which reduces the time consumed in text recognition and improves recognition performance.

[0048] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A device for automatically recognizing pictures, texts and sounds in real time, characterized in that: include: The data acquisition module is used to obtain the image, text or sound information of the specified target; Extraction module, used to extract knowledge points from pictures, text or sound information; Knowledge base module, used to store knowledge data information; A comparison module is used to compare the knowledge points extracted by the extraction module with the knowledge data information in the knowledge base module to obtain comparison information; The correction module is used to correct the knowledge points of the designated target according to the comparison information.

2. The device for automatically and in real time recognizing pictures, texts and sounds according to claim 1, characterized in that: The data acquisition module includes a photo taking module and a sound recording module. The photo taking module is used to take pictures and texts of the designated target, and the sound recording module is used to record sounds.

3. The device for automatically and in real time recognizing pictures, texts and sounds according to claim 2, characterized in that: The camera module includes a contour acquisition unit, a comparison unit, a calculation unit, a deformation unit and a recognition unit. The contour acquisition unit recognizes the text carrier in the picture to obtain the contour of the carrier. The comparison unit compares the contour of the carrier with the standard contour. If the similarity exceeds a preset threshold, the carrier is judged to be a preset regular carrier. The calculation unit, when judging that the carrier is a preset regular carrier, divides the carrier into several areas and calculates the arc corresponding to the edge of each area. The deformation unit determines the deformation value corresponding to the current area according to the minimum arc and the arc of the current area, and stretches the current area according to the corresponding deformation value; The recognition unit performs text recognition on the stretched image.

4. The device for automatically and real-timely recognizing pictures, texts and sounds according to claim 1, characterized in that: The sound recording module includes a tracking submodule and a recording submodule. The tracking submodule is used to track a designated target, and the recording submodule records the sound according to the target tracked by the tracking submodule.

5. The device for automatically and real-timely recognizing pictures, texts and sounds according to claim 1, characterized in that: The extraction module includes a picture recognition module, a text recognition module and a sound recognition module. The picture recognition module is used to extract knowledge points in pictures, the text recognition module is used to extract knowledge points in texts, and the sound recognition module is used to extract knowledge points in sounds.

6. A device for automatically recognizing pictures, texts and sounds in real time according to claim 5, characterized in that: The image recognition module includes a separation module, an encoding module, a matching module and a recognition module. The separation module is used to separate the text in the image into a plurality of rectangular text frames, and the number of the rectangular text frames is consistent with the number of the text in the image; The encoding module is used to encode the text in the rectangular text box separated by the separation module into a character string to be matched; the matching module is used to match the character string to be matched after being encoded by the encoding module with the character string in a preset character library; the recognition module is used to recognize the text corresponding to the character string to be matched according to the matching result of the matching module.

7. The device for automatically recognizing pictures, texts and sounds in real time according to claim 1, characterized in that: It also includes a translation module, which is used to translate pictures, text or sound information.

8. The device for automatically recognizing pictures, texts and sounds in real time according to claim 1, characterized in that: The data acquisition module, the extraction module, the knowledge base module, the comparison module and the correction module are integrated on the wearable component.

9. The device for automatically recognizing pictures, texts and sounds in real time according to claim 1, characterized in that: The wearing component is glasses, a hat or a watch.

Images