Shoeprint image retrieval method based on segmented weighting

Abstract

The invention provides a shoeprint image retrieval method based on segmented weighting. The shoeprint image retrieval method based on segmented weighting comprises the steps of 1, image preprocessing,on the basis of a trained U-Net convolutional neural network model, converting an obtained shoeprint on-site photo into an on-site binary image with shoeprint information reserved; 2, feature extraction: splitting the on-site binary image and the image in a shoe sample library into an upper sub-image and a lower sub-image, and inputting the upper sub-image and the lower sub-image into a twin network for feature extraction to obtain two mutually independent sub-features; 3, calculating a feature weight matrix: respectively calculating a pixel number proportion containing shoeprint informationin the two mutually independent sub-features so as to obtain a weight matrix of the field binary image; and 4, realizing feature fusion and similarity measurement. The technical problem of how to quickly and accurately retrieve the style corresponding to the shoeprint on-site picture in the shoe sample library is solved, the characteristics that the on-site shoeprint noise influence is large and part of information is lost are comprehensively considered, and the shoeprint retrieval accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of retrieval, in particular to a method for retrieving shoe print images based on segment weighting. Background technique [0002] Shoeprints are one of the most common clues in crime scenes, and corresponding shoeprint identification is an important issue in forensic identification. The current shoe print recognition mainly has the following three challenges: (1) The shoe prints left on the scene contain complex environmental factors: according to the medium containing the shoe prints, they can be divided into leather, wood, soil, ceramics, etc. The production mechanism can be divided into two categories: additive and subtractive, such as Figure 1a shown. (2) The shoe prints left on the scene are often incomplete, so part of the information will be lost, such as Figure 1b shown. (3) The on-site shoe prints and the shoe prints in the shoe sample library come from different modalities. The former is a gr...

AI Technical Summary

Problems solved by technology

The current shoe print recognition mainly has the following three challenges: (1) The shoe prints left on the scene contain complex environmental factors: according to the medium containing the shoe prints, they can be divided into leather, wood, soil, ceramics, etc. The production mechanism can be divided into two categories: additive and subtractive, such as Figure 1a shown

(2) The shoe prints left on the scene are often incomplete, so part of the information will be lost, such as Figure 1b shown

Therefore, when it is transferred to the shoe print retrieval task, its network depth is small, and it is not easy to fit the distribution of complex shoe print data

Images