Matching Composite Sketches to Face Photos: A Component-Based Approach

• Published in: IEEE transactions on information forensics and security Vol. 8; no. 1; pp. 191 - 204
• Main Authors: Hu Han, Klare, B. F., Bonnen, K., Jain, A. K.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.01.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Active shape model; Applied sciences; Artificial intelligence; Component-based face representation; composite sketch; Computer science; control theory; systems; Exact sciences and technology; Face recognition; Facial; Forensic engineering; forensic sketch; Galleries; heterogeneous face recognition; Image fusion; Image matching; Image representation; Law enforcement; Matching; Media coverage; modality gap; Pattern recognition. Digital image processing. Computational geometry; Similarity; Sketches; Software; Software engineering; Witnesses; Computer vision; Filtering; Prototype; Forensic science; Similarity; Image processing; Face recognition; composite sketch; Sex; Software component; Case based reasoning; Freehand sketch; Image segmentation; Experimental result; Image matching; modality gap; Multiscale method; Holism; heterogeneous face recognition; Facies; forensic sketch; Component-based face representation; Metric; Pattern extraction

The problem of automatically matching composite sketches to facial photographs is addressed in this paper. Previous research on sketch recognition focused on matching sketches drawn by professional artists who either looked directly at the subjects (viewed sketches) or used a verbal description of t...