Image retrieval method based on manifold learning data compression hash

Abstract

The invention discloses an image retrieval method based on a manifold learning data compression hash. The image retrieval method particularly includes the steps: 1 querying an original image needing to be retrieved from an image database, and storing the original image; 2 performing a certain preprocessing on the original image, extracting bottom characteristics of the original image, and recording image characteristic data; 3 performing normalization processing on the image characteristic data to obtain a normalized data matrix, connecting the normalized data matrix to one or more task layersto perform training, and performing training by the aid of one or more tasks to obtain hash codes of a trained data matrix and a tested data matrix. A single-group hash code is acquired in a manifoldlearning manner, and the method overcomes the shortcomings that multi-group hash codes occupy memory space and consume retrieval time in the prior art, so that the method improves retrieval efficiency and retrieval effects in image retrieval.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image retrieval method based on manifold learning data compression hash. Background technique [0002] Since the 1970s, research on image retrieval has begun. At that time, it was mainly based on text-based image retrieval technology (Text-based Image Retrieval, referred to as TBIR), which used text descriptions to describe the characteristics of images, such as paintings. Author, Year, Genre, Size, etc. After the 1990s, image retrieval technology that analyzes and retrieves the content semantics of images, such as image color, texture, layout, etc., has emerged, that is, Content-based Image Retrieval (CBIR) technology. CBIR is a kind of content-based retrieval (Content-based Retrieval, referred to as CBR), and CBR also includes retrieval technologies for other forms of multimedia information such as dynamic video and audio. [0003] With the rapid development of In...

AI Technical Summary

Problems solved by technology

Massive image data and the complexity of images have brought great challenges to image retrieval. How to quickly and accurately retrieve the images people need has become an urgent problem to be solved, and image retrieval has become the focus of people's attention.

[0004] However, some traditional image retrieval algorithms cannot meet people's growing needs