Image retrieval system and method

Abstract

The invention discloses an image retrieval system and method, and relates to the field of image identification. The image retrieval system comprises an image reading module, an image noise elimination module, an image segmentation module, a characteristic quantity calculation module, a screening module, a retrieval module, and a feedback module. The image reading module is used for reading image information; the image noise elimination module is used for eliminating the image noise; the image segmentation module is used for segmenting the image; the characteristic quantity calculation module is used for calculating the characteristic quantity of an unit image; the screening module is used for screening the characteristic quantity; the retrieval module is used for retrieving similar images based on the characteristic quantity; and the feedback module is used for feeding back a retrieval result. Aiming at the problems such as poor accuracy, poor retrieval speed and poor learnability of an existing image retrieval system and method, an improved system is provided; the improved system provided by the invention not only enables the retrieval result to be more accurate and the efficiency to be higher, but also has a learning capability and can improve the retrieval quality continuously.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image retrieval system and method. 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. [0003] Content-based image retrieval searches according to the image, its content semantics and context, and uses the semantic features of the image as clues to detect other images with similar characteristics from the image database. Because the size of images is generally larger than pure text...

AI Technical Summary

Problems solved by technology

[0005] 1. The accuracy is still not high: because the image information will be disturbed by various noises during the transmission process, it will cause the image to be distorted when it reaches the retrieval system

As a result, even if the subsequent search is very accurate, the final search results are still unsatisfactory

[0006] 2. Slow retrieval speed: Due to the extremely complex content-based image retrieval method, the retrieval system often performs a lot of complex calculations when searching for a complex image

resulting in a very slow retrieval process

And because the existing image retrieval systems generally only provide one retrieval mode, users will not treat them differently when retrieving complex images and simple images, and eventually the retrieval of simple images becomes slow and abnormal.

[0007] 3. No learning ability and insufficient personalization: conventional image retrieval systems and methods will not provide customized services for individual users

There is also no record and analysis of users' retrieval habits, which leads to the problem of retrieval of similar images of the same type has been retained, not only the retrieval efficiency has not been improved, but the retrieval accuracy has also been stagnant

Images