Mass image infringement retrieval method and system and computer readable storage medium thereof

Abstract

The invention provides a massive image infringement retrieval method and system and a computer readable storage medium thereof. The method comprises the steps: S1, generating a bag-of-words model, extracting SIFT feature points of a template image, obtaining visual vocabularies through clustering processing, and establishing the bag-of-words model; s2, making a training set: calculating an inversedocument weight of each visual vocabulary, and positioning SIFT feature points conforming to a preset threshold value to obtain original training data bying correspondingly cutting the template image; s3, training a neural network: training a CNN network by adopting the original training data in the step S2 according to a comprehensive metric learning and hash learning method to generate binary features; and S4, retrieval judgment: constructing an inverted index system by using the bag-of-words model in the step S1, traversing entries corresponding to the visual vocabularies in the to-be-retrieved image, calculating a Hamming distance between binary features, judging whether the binary features are matched or not according to a preset threshold, and giving an infringement coefficient according to accumulated matching. The infringement image retrieval speed is increased, and meanwhile, relatively high accuracy is ensured.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an image infringement retrieval method, system and computer-readable storage medium based on SIFT and local binary features. Background technique [0002] Manual local features are crucial to image retrieval tasks, and occupied the mainstream method of image retrieval before the emergence of global feature representation represented by deep learning. The combination of local features and the bag-of-words model improves the speed and accuracy of retrieval. In the case of small images, the bag-of-words model contains fewer visual words, and generally adopts the method of local feature aggregation to obtain global features, such as VALD; When the image scale is large and there are many visual words, the inverted index system is generally used, and the direct matching of visual words is used as the retrieval basis. [0003] For infringement feature retrieval, global features perform p...

AI Technical Summary

Problems solved by technology

[0005] However, the above existing technologies are limited by high computational complexity. This geometric verification is only suitable for small-scale data and cannot meet the needs of accurate retrieval of large-scale massive data.

Images