Robust Shoeprint Retrieval Method Based on Local‐to‐Global Feature Matching for Real Crime Scenes |
| |
Authors: | Junjian Cui MEng Xiaorui Zhao MEng Nini Liu MSc Sergey Morgachev MA Daixi Li MEng |
| |
Institution: | 1. Dalian Everspry Sci & Tech Co., Ltd., No. 31 Xixian Street, High‐Tech Industrial Zone, Dalian, 116085, China;2. Corresponding author: Junjian Cui, M.Eng.;3. E‐mail: |
| |
Abstract: | In this study, an automatic and robust crime scene shoeprint retrieval method is proposed. As most shoeprints left at crime scenes are randomly partial and noisy, crime scene shoeprint retrieval is a challenging task. To handle partial, noisy shoeprint images, we employ denoising deep belief network (DBN) to extract local features and use spatial pyramid matching (SPM) to obtain a local‐to‐global matching score. In this study, 536 query shoeprint images from crime scenes and a large scale database containing 34,768 shoeprint images are used to evaluate the retrieval performance. Experimental results show that the proposed method outperforms other state‐of‐the‐art methods in terms of retrieval accuracy, feature dimension, and retrieval speed. The proposed method achieves a cumulative match score (CMS) of 65.67% at top 10 which is 5.60% higher than the second best performing method. |
| |
Keywords: | forensic science shoeprint image shoeprint retrieval real crime scene deep belief network spatial pyramid matching |
|
|