High-efficiency similar picture identification method based on picture mining technology

Abstract

The invention discloses a high-efficiency similar picture identification method based on a picture mining technology. The high-efficiency similar picture identification method comprises the following implementation processes of: performing unified conversion of formats of pictures, wherein the pictures are pictures in a picture database; and the picture database P is {P1, P2, P3, P4, ......, Pn}, and includes n pictures; performing segmentation according to a certain rule, and performing calculation of a characteristic value of a segmented part; and warehousing and storing the pictures, wherein when the pictures are warehoused, the characteristic values thereof together with picture contents are stored in a characteristic value database; the characteristic value database D is {T1, T2, T3, T4, ......, Tn}; and the characteristic value stored by the Ti in the D corresponds to a Pi picture in the P. Compared with the prior art, the high-efficiency similar picture identification method based on the picture mining technology disclosed by the invention has the advantages that: zooming and gray calculation of pictures are unnecessary; the characteristic value extraction efficiency is increased; and the high-efficiency similar picture identification method is high in practicability, wide in application range and easy to popularize.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an efficient similar picture recognition method based on picture mining technology. Background technique [0002] Due to the continuous development of computer technology and information technology, image recognition technology is used more and more widely: such as fingerprint recognition, iris recognition, handwritten Chinese character recognition, traffic sign recognition, gesture recognition, face recognition, robot vision, etc. , and with the needs of the socialization of practical activities, there are more and more types of things that need to be classified and identified, and the content of the identified objects is becoming more and more complex. Image recognition not only plays a very important role in the fields of agriculture, industry, medicine and high-tech industries, but also has penetrated more and more into our lives. [0003] In image processing, the calculat...

AI Technical Summary

Problems solved by technology

This process needs to scale the image, calculate the gray level, calculate the average value, calculate the hash value, etc., so it takes a lot of time

and can be overly complex for some applications