LOSGSR: Learned Opinion Score Guided Shoeprint Retrieval

Abstract

As a kind of forensic evidence, a shoeprint conveys many important human characteristics, and it plays a vital role in forensic investigations. Millions of shoeprints are acquired from crime scenes, and it is a challenging task to retrieve the most similar shoeprints for a query shoeprint. Most shoeprint retrieval methods sort shoeprint images by feature similarities with respect to the query shoeprint; however, the results are not always what the investigator expects because the retrieval algorithm cannot determine what the investigator prefers based on only the content of the query shoeprint. This paper proposes a method to guide the shoeprint retrieval process to approximate what the user wants by applying learned opinion scores. Additionally, this paper improves shoeprint retrieval effectiveness by implementing the following four perspectives: 1) using the opinion scores of multiple examples to guide the results to meet the forensic experts' expectations; 2) proposing a learning-based method to refine opinion scores, which corrects the labeled opinion scores of multiple examples and their neighbors; 3) using a manifold ranking method to propagate the opinion scores to other dataset shoeprints; and 4) introducing a coefficient matrix to prevent the tendency of the ranking scores to become low values. The experiments show that the cumulative match scores of the proposed method are more than 96.6% in the top 2% of the dataset composed of 10,096 crime scene shoeprints. INDEX TERMS k nearest neighbors, opinion scores, shoeprint image retrieval, manifold ranking, multiple examples.

Crime Scene Shoeprint Image Retrieval: A Review

“…The method can achieve good performance on shoeprints with periodic patterns. Wang et al [72][73][74][75] divided a shoeprint image into two different regions and extracted features in these regions by using the Wavelet Fourier-Mellin transform. Experiments were conducted on a database containing 10,096 shoeprints, and the accuracy at the top 2% was about 96.6%.…”

Quantitative evaluation of footwear evidence: Initial workflow for an end‐to‐end system

“…Developing high-performance computer-based systems that can discriminate impressions made by different footwear, with very small error rates, has been of great interest for some time. A survey of the literature reveals that nearly all of the research on the use of algorithms for footwear impression comparisons have database retrieval as their focus and are primarily concerned with discriminating between different outsole design patterns [5][6][7][8][9].…”