An image similarity measurement method based on kernel preserving

Abstract

The invention provides an image similarity measurement method based on kernel preserving. The method comprises the steps that firstly a loss function is defined, then the loss function is simplified by defining a kernel function, a regularization function is added into the loss function to obtain a complete objective function, finally, the objective function is optimized and solved to obtain a final reconstruction transformation matrix, and two indexes including the accuracy rate and the regularization mutual information amount are adopted to measure the performance of the final reconstructiontransformation matrix. According to the method, the kernel function is defined to minimize a reconstruction error, and the similarity learning is carried out on original image data samples, so that better global relationships among the image data samples are reserved, and based on the similarity information, more accurate clustering is carried out on the images by using a spectral clustering algorithm. The method has universality and can be used for clustering, classifying, recommending systems and other problems, an effective basic module is provided for a method based on similarity learning, and meanwhile great potential is achieved in the application of image mapping to low dimension.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to an image similarity measurement method based on kernel preservation. Background technique [0002] Nowadays, high-dimensional data such as text, images, and videos can be easily obtained from cheap sensors or networks. How to extract useful information from massive high-dimensional data has become a key technology. Among them, high-dimensional data similarity is the input information of many high-dimensional data analysis methods, such as spectral clustering, nearest neighbor classification, image segmentation, person re-identification, image retrieval, image dimensionality reduction and graph-based classification methods; at the same time, it is also the input information of machine The basic problems of learning, pattern recognition and data mining, so the measurement accuracy of high-dimensional data similarity directly affects the performance of the subsequent processing of th...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that existing methods cannot handle data well, especially the correlation structure of image data in high dimensions, the present invention proposes an image similarity measurement method based on kernel preservation, which includes proposing a new objective function and Design a new optimization method, compared with the prior art, the present invention has a greater improvement in the accuracy of similarity measurement

Images