Multi-task layered image retrieval method based on depth self-coding convolution neural network

Abstract

The invention discloses a multi-task layered image retrieval method based on a depth self-coding convolution neural network. The method is characterized by mainly comprising a multi-task end-to-end convolution neural network for deep learning and training recognition, a rapid visual segmentation detection and positioning method of a region-of-interest secondary screening module based on an RPN network, a coarse search of a full-graph sparse hash code, an area sensing semantic feature and matrix h accurate comparison and search based on the maximum response, and a region-of-interest selectivitycomparison algorithm. According to the method, the end-to-end training can be achieved, the interest region with higher quality can be automatically selected, the automation degree and the intelligent level of search by images can be effectively improved, and the image retrieval requirements of the big data age can be met by using little storage space at a high search speed.

Description

technical field [0001] The present invention relates to the application of computer vision, pattern recognition, information retrieval, multi-task learning, similarity measurement, deep self-encoding convolutional neural network and deep learning technology in the field of image retrieval, in particular to a deep self-encoding convolutional neural network A Multi-Task Hierarchical Image Retrieval Method. Background technique [0002] The purpose of image retrieval is to retrieve similar images by analyzing the input query image content, providing users with a search technology for image information retrieval, which includes image processing, computer vision, multi-task learning, pattern recognition and cognitive psychology and other disciplines. Its related technologies mainly include image representation acquisition and similarity measurement. In the context of the big data era, image retrieval, video detection, Internet, shopping search engines and other fields have been...

AI Technical Summary

Problems solved by technology

[0013] Aiming at the problems of low level of automation and intelligence, lack of deep learning, difficulty in obtaining accurate retrieval results, large storage space consumption of retrieval technology, slow retrieval speed and difficulty in meeting image retrieval requirements in the era of big data in the existing image search technology , the present invention proposes an end-to-end image retrieval method through layered depth search based on a deep self-encoding convolutional neural network, and uses a deep learning method to improve the level of automation and intelligence in the retrieval system while enabling image recognition and feature acquisition The perfect combination of retrieval efficiency and retrieval efficiency enables the entire retrieval system to obtain accurate retrieval results. The use of sparse coding reduces the system's dependence on memory and speeds up retrieval, thus meeting the image retrieval requirements in the era of big data.

[0014] To realize the above invention, several core problems must be solved: 1) Aiming at the difficult problem of image feature extraction, using the powerful feature representation ability of deep self-encoding convolutional neural network to realize feature adaptive extraction; 2) Aiming at large-scale image retrieval For the problem of slow speed, design a multi-task layering method, use the query image to quickly compare the image in the database; 3) for the multi-target image scene semantic retrieval, design a secondary screening algorithm for the region of interest to multi-target image Detection and segmentation; 4) Using the advantages of end-to-end deep networks, design an end-to-end deep self-encoding convolutional neural network to integrate detection, recognition, and feature extraction into one network

Images