Cross-domain Image Matching With Deep Feature Maps

Abstract

We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convolutional neural nets are surprisingly effective descriptors for this specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to s

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keykong2018cross

Related papers

• Crisp: Leveraging Tread Depth Maps For Enhanced Crime-scene Shoeprint Matching (2024)2.26
• Cross-domain Visual Matching Via Generalized Similarity Measure And Feature Learning (2016)15.54
• The Devil Is In The Middle: Exploiting Mid-level Representations For Cross-domain Instance Matching (2017)0.00
• Snap And Find: Deep Discrete Cross-domain Garment Image Retrieval (2019)0.00
• Co-occurrence Of Deep Convolutional Features For Image Search (2020)9.76
• Local Feature Matching Using Deep Learning: A Survey (2024)18.68
• Differential Geometric Retrieval Of Deep Features (2017)2.26
• Modality-aware Feature Matching: A Comprehensive Review Of Single- And Cross-modality Techniques (2025)0.00