Random structure conformal Hash information retrieval method

Abstract

The invention relates to a random structure conformal Hash information retrieval method. The random structure conformal Hash information retrieval method is characterized by including the steps of (1) protecting important structures of high dimensional data, conducting dimensionality reduction on original high dimensional data through a provided objective function, and accordingly obtaining low dimensional data; (2) calculating a basic dimensionality matrix and a low dimensionality matrix of the original high dimensional data through obtained updating rules of basic operators U and the low dimensional data V; (3) setting a threshold value, converting low dimensionality real number expressions in a training set into binary codes, and calculating Hash codes of a testing sample through probability statistics disaggregated model logistic regression; (4) calculating the Hamming distance, namely XOR operation, between the training data and the testing sample, and obtaining final results. By means of the random structure conformal Hash information retrieval method, on the basis that distribution of random data and the local and overall structures of the high dimensional data are protected, a Hash function is successfully obtained through the multivariable logistic regression, surpassing sample expansion can be achieved, and the random structure conformal Hash information retrieval method is suitable for computer visions, data mining, machine learning or similar searching fields.

Description

technical field [0001] The invention belongs to the technical field of computer information data processing, and in particular relates to a random structure shape-preserving hash information retrieval method for computer vision, data mining, machine learning or similar search. Background technique [0002] Similarity search is a problem to be solved in information retrieval, machine learning, pattern recognition and data mining. In general, effective similarity search methods build index structures in the metric space, and early research on similarity search can be traced back to the 1970s. Specifically, when the dimensionality is lower than or equal to 20, some methods based on data structures such as KD-tree, VP-tree and R+tree can solve the problem of similarity search. However, with the increase of data dimensions, the difficulty of how to effectively implement similarity search in the field of information data processing continues to increase. The existing methods ado...

AI Technical Summary

Problems solved by technology

Due to the effect of sparse coding, in order to ensure the sparsity of the obtained representation, the non-negative local coordinate factorization (NLCF) adds local coordinate constraints

[0013] In summary, the deficiencies of the existing technology can be summarized as follows: First, the existing NMF algorithm cannot solve the problem of protecting the local and overall structure of the original high-dimensional data, so the obtained low-dimensional data cannot be maximized. Inherit the characteristics of high-dimensional data; second, the existing hash algorithm based on random projection has to generate a lot of hash tables to obtain a certain retrieval effect, and the simple linear hash function cannot map out the potential between data points. Third, when the codeword is very long, the learning-based hash algorithm cannot achieve effective results

Images