Scientific and technical literature picture extraction method based on Faster-RCNN

Abstract

The invention discloses a scientific and technological literature picture extraction method based on a Fast-RCNN. The method comprises the following steps of 1) acquiring the scientific and technological literature data by using a web crawler and preprocessing the scientific and technological literature data; 2) dividing a data set, making a label for the data in the training set, and not processing the data in the test set; 3) inputting the data in the training set into a convolution layer, and extracting the feature mapping of the pictures; (4) mapping and inputting the obtained features into an RPN module to obtain the proposal feature maps with fixed sizes; 5) classifying the specific categories by utilizing the softmax to obtain the accurate position of a target, calculating a loss function, and updating the parameters of the whole network to obtain a training model; 6) utilizing the training model to detect the data in the data set, and outputting the detected pictures. The scientific and technological literature picture extraction method is high in detection speed and high in accuracy, facilitates the further analysis and understanding of the scientific and technological literature pictures, and has the higher practical application value.

Description

technical field [0001] The invention relates to the field of computer application technology and the field of target detection, in particular to a method for extracting pictures of scientific and technological documents based on Faster-RCNN. Background technique [0002] The pictures in scientific and technological literature contain the important ideas and results of the literature. Analyzing and understanding the pictures in scientific and technological literature will help researchers better understand the literature. In order to extract pictures from documents, most of the previous methods are based on manual feature extraction. The accuracy of extraction depends on the quality of feature extraction, and the effect on different scientific and technological documents is not robust. In addition, although the direct use of a simple convolutional neural network (CNN) training model can separate and extract pictures in scientific and technological literature, the accuracy rat...

AI Technical Summary

Problems solved by technology

In order to extract pictures from documents, most of the previous methods are based on manual feature extraction, the accuracy of extraction depends on the quality of feature extraction, and the effect on different scientific and technological documents is not robust

In addition, although the direct use of a simple convolutional neural network (CNN) training model can separate and extract pictures in scientific literature, the accuracy rate is still not high

Images