Multi-Layer Feature Based Shoeprint Verification Algorithm for Camera Sensor Images

Abstract

As a kind of forensic evidence, shoeprints have been treated as important as fingerprint and DNA evidence in forensic investigations. Shoeprint verification is used to determine whether two shoeprints could, or could not, have been made by the same shoe. Successful shoeprint verification has tremendous evidentiary value, and the result can link a suspect to a crime, or even link crime scenes to each other. In forensic practice, shoeprint verification is manually performed by forensic experts; however, it is too dependent on experts’ experience. This is a meaningful and challenging problem, and there are few attempts to tackle it in the literatures. In this paper, we propose a multi-layer feature-based method to conduct shoeprint verification automatically. Firstly, we extracted multi-layer features; and then conducted multi-layer feature matching and calculated the total similarity score. Finally, we drew a verification conclusion according to the total similarity score. We conducted extensive experiments to evaluate the effectiveness of the proposed method on two shoeprint datasets. Experimental results showed that the proposed method achieved good performance with an equal error rate (EER) of 3.2% on the MUES-SV1KR2R dataset and an EER of 10.9% on the MUES-SV2HS2S dataset.

Walk This Way: Footwear Recognition Using Images & Neural Networks

“…Wang et al [7] proposed a multi-layer feature extractor model to compute the similarity values of two shoe prints on each layer. This method showed the success of the multi-layered Convolutional Neural Network (CNN), especially in the area of an occluded or partial image recognition.…”

“…this technique creates sharp images by using the closest 4x4 neighborhood of known pixels. The MLPs use seven (7) features that were calculated to train and classify the images. The first feature calculated is the number of objects in the shoe print, for this, the OpenCV's findContours() function was used.…”

“…Furthermore the same outsole pattern can be found on several different footwear brands and models. If the outsole pattern of a shoe can be determined from its mark, then this can significantly narrow the search for a particular suspect [7].…”

“…There currently are techniques with remarkable accuracy in terms of recognizing the evidence shoe. The issue is that the majority of them take more than a few days to process, making them not very reliable in time-sensitive investigations [7].…”

“…Furthermore, these techniques require training and specific resources in order to extract the shoe print. These reasons make the whole shoe print recognition process very costly and challenging depending on the case [7]. The techniques used nowadays extract the layout of the shoe using lifting, casing and/or 3D-imaging to minimize the clutter and partial occlusion problem [8].…”