Shoeprint hole and insert feature detection and description method

Abstract

The invention discloses a shoeprint hole and insert feature detection and description method. The method comprises the steps of obtaining a shoeprint hole candidate set and extracting attribute information of the shoeprint hole candidate set; traversing the hole candidate set, and screening hole areas based on geometric and gray attributes to obtain a candidate area set; constructing a similarity matrix based on Euclidean distance by taking a long axis, a short axis, an eccentricity rate and an area as characteristics, and performing seed growth on the accurate candidate region set by adopting a seed growth algorithm after a growth rule is improved to obtain a growth region with hole characteristics; obtaining a candidate insert feature point set based on multi-scale difference Gaussian; traversing all candidate insert feature point sets, comparing a gray average value with a threshold value of the gray average value to obtain a screened insert feature initial region, performing texture consistency screening on the insert feature region, and determining a precise insert region based on a maximum extremum stable region; and carrying out boundary description on the precise embedded object region by adopting a level set algorithm.

Description

technical field [0001] The invention relates to the technical field of image feature analysis; in particular, it relates to a method for detecting and describing features of shoe print holes and embedded objects based on multi-level screening of the maximum extreme value stable region. Background technique [0002] In the literature [1], William J clarified the important role of the random features of shoe prints in the identification of suspects. At present, there is no algorithm to detect and describe the features of holes and embedded objects. The similar technical field is defect detection, including (1 ) Using the background difference method based on the mixed Gaussian model to extract the weld defect area detection algorithm of the target detection area [2]: (2) The defect detection algorithm on the surface of the copper strip extracts the area of ​​interest, and uses the Otsu method threshold value segmentation to detect the defects in the image Connected domains of ...

AI Technical Summary

Problems solved by technology

[0003] The defects of the current existing technology are: the defect detection algorithm based on machine vision technology has a better effect on images with consistent textures, while the pattern of shoe print images changes greatly, the background is complex, and there are many interference information; the defects based on deep learning Detection requires a large amount of labeled data sets, and the background of similar defects is consistent, and similar shoe print images do not have large-scale data sets

Images