A method and system for verifying the unity of witnesses and certificates based on neural network

Abstract

The invention discloses a verification method and system for verifying the integration of person and certificate. The verification method is used to verify whether the person on the ID card and the person on the photographed image are the same person, and collects the ID card of the person respectively. The ID card image and the photographed image; face detection is carried out on the ID card image and the photographed image, the ID card face position coordinates and the photographed face position coordinates are obtained, and through the same affine transformation, Obtain the ID card transformation image and the photo transformation image of the same size; Utilize the improved convolutional neural network algorithm to extract the eigenvectors of the ID card transformation image and the photo transformation image, verify the people on the ID card and the photos on the photo image is a person. By using the improved convolutional neural network algorithm to extract the eigenvectors of the transformed image of the ID card and the transformed image of the photo, the difference in the face image caused by the dark and crowded environment improves the accuracy of the verification result.

Description

technical field [0001] The present invention relates to the field of face recognition, in particular to a method and system for verifying the integration of witnesses and certificates based on a neural network. Background technique [0002] The traditional face detection algorithm is based on the edge features, linear features and diagonal features of the face image, and recognizes according to the gray level change of the image. There are problems of missed detection and false detection, and the detection effect in the case of multiple poses is relatively low. Poor, the detection accuracy is low. [0003] The traditional face detection algorithm is still designed based on simple artificial features, such as the local binary pattern LBP (Local Binary Pattern) feature algorithm, which generally divides the face image into blocks, and performs LBP histogram statistics on each sub-image. And connect the histograms of all blocks end to end to form a vector, which is the feature...

AI Technical Summary

Problems solved by technology

Due to the limitations of age, emotion, temperature and lighting conditions, coverings and other factors, the shape of the face is very unstable. Even when viewed from different angles, the image features of the face are also very different. Applying the LBP feature The algorithm will lead to inaccurate detection results

[0004] At present, face recognition based on neural network only extracts some features of the face from the image of the face. Because the face will change with age, emotion, temperature and light conditions, coverings and other factors, the shape of the face will change. It is very unstable. Only by using the extracted face features to verify whether the face image of the ID card and the life photo image of the face are the same person will lead to inaccurate verification results. Therefore, there is an urgent need for a method that can accurately judge the identity card Method and system for verifying whether the face image of the person's face image and the face image of the life photo are the same person

Images