Content extraction method of picture table based on computer vision and natural language processing

Abstract

The invention discloses a method for extracting the content of a picture table based on computer vision and natural language processing, comprising step 1: inputting the picture into a table frame recognition model, identifying the table frame, and calculating the coordinates of each cell in the table; step 2: extracting the coordinates of each cell Text content; step 3, according to the extracted text content, mark according to three types of key, value, and mixed value, construct a table content classification data set, and train a cell content classification model based on the data set; step 4 according to table coordinates, unit The grid coordinates and the category of each cell text are used to infer the table layout; step 5 organizes the data in the table in JSON format according to the layout information of the table, the content of the cell and the category information. The invention introduces natural language processing technology to mark the content category of each cell in the table, and then combines the cell position information to reason the table layout, and finally output the table content in a structured manner.

Description

technical field [0001] The invention relates to the technical field of table data extraction, in particular to a method for extracting table content from pictures based on computer vision and natural language processing. Background technique [0002] The application of information extraction based on computer vision and natural language processing technology is becoming more and more widespread, such as recognizing text from pictures, extracting entities such as names, place names, and phone numbers from text, and extracting key information from invoices, insurance policies, and other forms. Wait. At the same time, major cloud vendors also provide identification services based on cloud platforms for form data such as bills and contracts. [0003] Existing techniques for extracting tabular data mainly focus on two aspects. First, through traditional image processing methods, such as erosion, expansion, edge detection, contour recognition, etc., first identify the table in t...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a table content extraction method based on computer vision and natural language processing, using border detection, OCR, text classification, etc. Technology, develop table border recognition, table content extraction, table content classification, table layout reasoning modules, realize data extraction from image tables and convert the extracted data into structured data in JSON format

Images