On-the-spot shoe sole trace pattern image retrieval method based on multiple feedback mechanism

Abstract

The invention discloses a sole trace pattern image retrieval method based on a multi-feedback mechanism, comprising the following steps: step 1, sorting and outputting sole trace pattern images pre-stored in a sample image library according to the degree of similarity between the spectrum characteristics of binary charts of sole trace pattern images acquired on site and the features of the images in the sample image library; step 2, selecting at least two of the output sole trace pattern images pre-stored in the sample image library according to a predetermined standard, averaging the spectrum characteristics of the selected sole trace pattern images according to the spectrum characteristics of the selected sole trace pattern images, and working out the average spectrum characteristic; step 3, calculating the score of similarity between the average spectrum characteristic and the spectrum characteristic of the binary chart of each sole trace pattern image pre-stored in the sample image library; and step 4, outputting the sole trace pattern images pre-stored in the sample image library according to the score of similarity from high to low.

Description

technical field [0001] The present invention relates to the fields of image processing and recognition, computer vision, machine learning and public security, and in particular, relates to an on-site shoe sole trace pattern image retrieval method based on a multiple feedback mechanism. Background technique [0002] At present, the shoe sole pattern retrieval at home and abroad is mainly divided into three categories: label-based, pattern-based and feature-based retrieval methods. [0003] Recently, the Fourier transform is used to classify the complete or partial shoe sole trace patterns, which can solve the scaling and rotation problems of the image, and encode the frequency domain information. In 2005, Philip deChazal proposed an automatic shoe sole pattern retrieval system based on Fourier transform. The specific method is: perform Fourier transform on the sole trace picture, and calculate its power spectral density as a feature for matching. Without considering the nois...

AI Technical Summary

Problems solved by technology

[0007] Although there are fully automatic retrieval systems for shoe sole patterns in the prior art, these systems are all to retrieve artificially synthesized clear shoe sole trace images, and in practical applications, there are many shoe sole trace images that need to be retrieved. It is the shoe sole trace image collected on site, and in many cases, the shoe sole trace image collected on site is of low quality, incomplete, or unclear, so the above mentioned sole trace retrieval method has many limitations in practical application

Images