An OCR identification-based registration information input system

Abstract

The application relates to the technical field of information recognition, and specifically discloses a registration information input system based on OCR recognition, which comprises a data acquisition module, a picture processing module, an information extraction module, an information input module and an interaction module; the picture processing module is arranged to adjust the noise reduction intensity of a pixel point in a picture through a Gaussian function, so that the picture is subjected to noise reduction processing, and the efficiency and accuracy of the information extraction module in extracting characters in the noise reduction processed picture are improved. In addition, the data acquisition module is arranged to extract characters in the noise reduction processed picture and classify the characters, so that the information input module can fill the recognized characters into input positions and compile the characters into an online registration form, the online registration form is filled, the efficiency of registration information input is improved, and the problems of complicated operation and low information input efficiency of the existing registration information input system are solved.

Description

Technical Field

[0001] This invention relates to the field of information recognition technology, specifically to a registration information entry system based on OCR recognition. Background Technology

[0002] OCR, or Optical Character Recognition, refers to the process by which electronic devices such as scanners or digital cameras examine printed characters on paper, determine the shape of the characters, and then use character recognition methods to translate the shape into computer text. In other words, for printed characters, it uses optical methods to convert the text in paper documents into black and white dot matrix image files, and then uses recognition software to convert the text in the image into text format for further editing and processing by word processing software.

[0003] Currently, most exams are registered online. Before registering online, candidates need to fill in their registration information into the registration system and then submit their application through the system. However, for offline collection of handwritten registration forms or electronic registration forms submitted by candidates, administrators need to type both the handwritten and electronic forms into the registration system separately. This data entry method is time-consuming and labor-intensive, and due to fatigue or negligence from prolonged manual review, errors can occur. Therefore, the data entry process is cumbersome and inefficient. Summary of the Invention

[0004] The purpose of this invention is to provide a registration information entry system based on OCR recognition, thereby solving the technical problems mentioned in the background section. The objective of this invention can be achieved through the following technical solutions: A registration information entry system based on OCR recognition, the registration information entry system includes a data acquisition module, an image processing module, an information extraction module, an information entry module and an interaction module; The data acquisition module is used to acquire images of the registration information form and output the image data; The image processing module is used to obtain the position coordinates (x, y) of multiple pixels in the image. i ,y i ), where i represents a pixel, and i = 1, 2, ..., n; obtain the position coordinates (X, Y) of the image center, and calculate the distance from the position coordinates (X, Y) of the image center to the position coordinates (x, y) of pixel i. i ,y i The distance is calculated, and the noise reduction intensity of pixel i is adjusted according to the distance value to perform noise reduction on the image; the noise-reduced image is then output. The information extraction module is used to extract text from the noise-reduced image, and classify the extracted text according to project keywords to obtain text information T. j， Where j is the project keyword, and j = 1, 2, ..., m; The information input module is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k In the above, k is the input position, k=1,2,......,p; the information input module is also used to summarize the content of the online registration page into an online registration form; The interaction module is used to interact with the host computer, send the online registration form to the host computer, and save the online registration form signed and confirmed by the host computer.

[0005] As a further aspect of the present invention: the image processing module includes an image processing unit, which is used to calculate the position coordinates (X,Y) of the image center to the position coordinates (x,Y) of pixel i using the following formula. i ,y i ) Distance, obtain the distance value; calculate the noise reduction intensity r of pixel i according to the following formula. i : ; Where H i The coordinates of the image center (X, Y) to the coordinates of pixel i (x, y) i ,y i The distance value of H; max This represents the maximum value of the distance.

[0006] As a further aspect of the present invention: according to the formula Calculate the distance value H.

[0007] As a further aspect of the present invention: the image processing unit is used to insert the noise reduction intensity of the pixels into the Gaussian function, and to perform noise reduction processing on the image by adjusting the noise reduction intensity; after the noise reduction processing of the image is completed, the noise reduction processing completion information is output.

[0008] As a further aspect of the present invention, the image processing module further includes an output unit, which is used to output a noise-reduced image in a set format when the analysis unit outputs noise reduction processing completion information.

[0009] As a further aspect of the present invention: the data acquisition module includes a camera device, a scanning device, or an image receiving device for acquiring images of registration information forms.

[0010] As a further aspect of the present invention: the information extraction module includes an OCR recognition unit, which is used to recognize and extract text from the noise-reduced image.

[0011] As a further aspect of the present invention: the information extraction module further includes a classification unit, which is used to classify the extracted text according to preset project keywords and output text information; the information input module further includes an information input unit, which is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k The information from the online registration page will be compiled into an online registration form.

[0012] As a further aspect of the present invention: the interactive module is used to send the online registration form and registration instructions to the host computer. After the host computer reads the registration instructions and selects the option that the registration information is correct, the online registration form is in a signed confirmation state.

[0013] As a further aspect of the present invention: when the interaction module receives an online registration form in the signature confirmation state from the host computer, the interaction module sends a reconfirmation message to the host computer through a pop-up window. When the interaction module receives a reconfirmation message from the host computer confirming that the information is correct, it saves the online registration form in the signature confirmation state.

[0014] The beneficial effects of this invention are: This invention acquires an image of the registration information form through a data acquisition module, and calculates the position coordinates (X, Y) of the image center to the position coordinates (x, Y) of pixel i through an image processing module. i ,y i The image processing unit uses the distance value of a pixel and its maximum distance value to calculate the noise reduction intensity of that pixel. This allows the image processing unit to adjust the noise reduction intensity of each pixel using a Gaussian function, thus improving the efficiency and accuracy of the information extraction module in extracting text from the noise-reduced image. Furthermore, the data acquisition module extracts and categorizes the text from the noise-reduced image, facilitating the information entry module to input the recognized text into the corresponding fields and compile it into an online registration form. This allows for the automatic input of handwritten or electronic registration forms into the online registration form, improving the efficiency of registration information entry and solving the problems of cumbersome operation and low efficiency in existing registration information entry systems. Attached Figure Description

[0015] The invention will now be further described with reference to the accompanying drawings.

[0016] Figure 1This is a structural block diagram of a registration information entry system based on OCR recognition provided by the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 As shown, this invention is a registration information entry system based on OCR recognition. In one embodiment of the present invention, a registration information entry system based on OCR recognition is provided, the registration information entry system comprising: Data acquisition module; the data acquisition module is used to acquire images of the registration information form and output image data; Image processing module; the image processing module is used to obtain the position coordinates (x, y) of multiple pixels in the image. i ,y i ), where i represents a pixel, and i = 1, 2, ..., n; obtain the position coordinates (X, Y) of the image center, and calculate the distance from the position coordinates (X, Y) of the image center to the position coordinates (x, y) of pixel i. i ,y i The distance is calculated, and the noise reduction intensity of pixel i is adjusted according to the distance value to perform noise reduction on the image; the noise-reduced image is then output. Information extraction module; the information extraction module is used to extract text from the noise-reduced image, classify the extracted text according to project keywords, and obtain text information T. j， Where j is the project keyword, and j = 1, 2, ..., m; Information entry module; the information entry module is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k In the above, k is the input position, k=1,2,......,p; the information input module is also used to summarize the content of the online registration page into an online registration form; The interaction module is used to interact with the host computer, send the online registration form to the host computer, and save the online registration form signed and confirmed by the host computer.

[0019] In one embodiment, the image processing module includes an image processing unit, which is used to calculate the position coordinates (X, Y) of the image center to the position coordinates (x, Y) of pixel i using the following formula. i ,y i ) Distance, obtain the distance value; calculate the noise reduction intensity r of pixel i according to the following formula. i : ; Where H i The coordinates of the image center (X, Y) to the coordinates of pixel i (x, y) i ,y i The distance value of H; max This represents the maximum value of the distance.

[0020] In this embodiment, according to the formula Calculate the distance value H.

[0021] Preferably, the image processing unit is used to insert the noise reduction intensity of each pixel into a Gaussian function, and to perform noise reduction processing on the image by adjusting the noise reduction intensity; after the noise reduction processing of the image is completed, it outputs noise reduction processing completion information.

[0022] Preferably, the image processing module further includes an output unit, which is used to output a noise-reduced image in a set format when the analysis unit outputs noise reduction processing completion information.

[0023] This embodiment calculates the position coordinates (X, Y) of the image center to the position coordinates (x, Y) of pixel point i by setting the image processing unit. i ,y i The distance value of a pixel is used to calculate the noise reduction intensity of that pixel based on its distance value and the maximum distance value. The image processing unit can then adjust the noise reduction intensity of the pixel using a Gaussian function to perform noise reduction on the image, thereby improving the efficiency and accuracy of the information extraction module in extracting text from the noise-reduced image.

[0024] In one embodiment of the present invention, the data acquisition module includes a camera, a scanning device, or an image receiving device for acquiring images of registration information forms. In practical applications, other devices with the function of acquiring images of registration information forms can also be used.

[0025] In this embodiment, the information extraction module includes an OCR recognition unit, which is used to recognize and extract text from the noise-reduced image. Using a mature OCR recognition unit to collect text from the image improves the convenience of information entry in the online registration system.

[0026] In this embodiment, the information extraction module further includes a classification unit, which is used to classify the extracted text according to preset project keywords and output text information; the information input module further includes an information input unit, which is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k The information from the online registration page will be compiled into an online registration form.

[0027] In this embodiment, the interaction module sends the online registration form and registration instructions to the host computer. Once the host computer reads the registration instructions and checks the option confirming the registration information is correct, the online registration form is in a signed confirmation state. The interaction module also sends images acquired by the data acquisition module to the host computer. After the host computer selects the image processing area using a rectangle, it crops the image processing area into an image format and sends it to the image processing module for noise reduction. This further improves the effectiveness of the image processing area.

[0028] Preferably, when the interaction module receives an online registration form in the signed confirmation state from the host computer, the interaction module sends a reconfirmation message to the host computer via a pop-up window. When the interaction module receives feedback from the host computer confirming that the reconfirmation is correct, it saves the online registration form in the signed confirmation state, thereby improving the rigor of the registration process.

[0029] This invention is implemented as follows: A handwritten registration form is photographed and converted into an image, or an electronic registration form is converted into an image. Then, an image processing unit obtains the position coordinates of multiple pixels in the image, as well as the position coordinates of the image center. The distance from each pixel's position coordinate to the image center coordinate is used to calculate the maximum distance value, which is then output as the noise reduction intensity. This allows for noise reduction processing of the image by adjusting the noise reduction intensity, resulting in a denoised image. An OCR recognition unit is used to identify and extract text from the denoised image. A classification unit categorizes the extracted text according to pre-set project keywords (such as name, gender, registration subject, and education level), extracting text information T from the project keyword category corresponding to the input position k. j， Text information T jInsert the information into input position k, then summarize the content of the online registration page into an online registration form. The interaction module can then send the summarized online registration form and registration instructions to a host computer such as a client or webpage. After receiving confirmation from the host computer that the registration instructions have been read and the registration information is correct, the interaction module sends a confirmation message to the host computer via a pop-up window. When the interaction module receives confirmation from the host computer, it saves the online registration form with the status "signed and confirmed," completing the entry of registration information. Subsequent registration applications need to be submitted by the host computer.

[0030] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A registration information entry system based on OCR recognition, characterized in that, The registration information entry system includes: Data acquisition module; the data acquisition module is used to acquire images of the registration information form and output image data; Image processing module; the image processing module is used to obtain the position coordinates (x, y) of multiple pixels in the image. i ,y i ), where i represents a pixel, and i = 1, 2, ..., n; obtain the position coordinates (X, Y) of the image center, and calculate the distance from the position coordinates (X, Y) of the image center to the position coordinates (x, y) of pixel i. i ,y i The distance is calculated, and the noise reduction intensity of pixel i is adjusted according to the distance value to perform noise reduction on the image; the noise-reduced image is then output. Information extraction module; the information extraction module is used to extract text from the noise-reduced image, classify the extracted text according to project keywords, and obtain text information T. j , where j is the project keyword, and j=1,2,......,m; Information entry module; the information entry module is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k In the above, k is the input position, k=1,2,......,p; the information input module is also used to summarize the content of the online registration page into an online registration form; The interaction module is used to interact with the host computer, send the online registration form to the host computer, and save the online registration form signed and confirmed by the host computer. The image processing module includes an image processing unit, which is used to calculate the position coordinates (X,Y) of the image center to the position coordinates (x,Y) of pixel i using the following formula. i ,y i ) Distance, obtain the distance value; calculate the noise reduction intensity r of pixel i according to the following formula. i : ； Where H i The coordinates of the image center (X, Y) to the coordinates of pixel i (x, y) i ,y i The distance value of H; max This represents the maximum value of the distance.

2. The registration information entry system based on OCR recognition according to claim 1, characterized in that, According to the formula Calculate the distance value H.

3. The registration information entry system based on OCR recognition according to claim 2, characterized in that, The image processing unit is used to insert the noise reduction intensity of each pixel into a Gaussian function, and to perform noise reduction processing on the image by adjusting the noise reduction intensity; after the noise reduction processing of the image is completed, it outputs noise reduction processing completion information.

4. A registration information entry system based on OCR recognition according to any one of claims 2-3, characterized in that, The image processing module also includes an output unit, which is used to output a noise-reduced image in a set format when the analysis unit outputs noise reduction processing completion information.

5. The registration information entry system based on OCR recognition according to claim 1, characterized in that, The data acquisition module includes a camera, a scanning device, or an image receiving device for collecting images of the registration information form.

6. The registration information entry system based on OCR recognition according to claim 1, characterized in that, The information extraction module includes an OCR recognition unit, which is used to recognize and extract text from the noise-reduced image.

7. The registration information entry system based on OCR recognition according to claim 6, characterized in that, The information extraction module further includes a classification unit, which is used to classify the extracted text according to preset project keywords and output text information; the information input module further includes an information input unit, which is used to input text information T j Insert into the input field L corresponding to the project keywords on the online registration page. k The information from the online registration page will be compiled into an online registration form.

8. The registration information entry system based on OCR recognition according to claim 1, characterized in that, The interactive module is used to send the online registration form and registration instructions to the host computer. After the host computer reads the registration instructions and checks the option that the registration information is correct, the online registration form will be in a signed confirmation state.

9. A registration information entry system based on OCR recognition according to claim 8, characterized in that, When the interaction module receives an online registration form in the signed confirmation state from the host computer, the interaction module sends a reconfirmation message to the host computer via a pop-up window. When the interaction module receives feedback from the host computer confirming that the reconfirmation is correct, it saves the online registration form in the signed confirmation state.

Images