Abstract
This paper addresses the problem in mug shot searching in suspect database. The objective is to improve the efficiency of the suspect identification process. The input is a sketch constructed by a witness. The output is the mug shot ranking for the suspect database. In the system, local and global feature measurements between sketch and mug shot faces are adopted. The local distance measurement compares facial primitives individually while the global distance measurement compares the geometric distances among feature points on the face. All mug shots are ranked based on the combined results. Experimental results show that 70% accuracy is achieved by considering the top 15% ranks.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IAPR Conference on Machine Vision Applications, MVA 2002 |
| Publisher | IAPR Conference on Machine Vision Applications |
| Pages | 500-503 |
| Number of pages | 4 |
| ISBN (Print) | 4901122029 |
| Publication status | Published - 11 Dec 2002 |
| Event | 8th IAPR Conference on Machine Vision Applications, MVA 2002 - Nara, Japan Duration: 11 Dec 2002 → 13 Dec 2002 Conference number: 212352 https://dblp.org/db/conf/mva/mva2002.html (Conference proceedings) |
Conference
| Conference | 8th IAPR Conference on Machine Vision Applications, MVA 2002 |
|---|---|
| Country/Territory | Japan |
| City | Nara |
| Period | 11/12/02 → 13/12/02 |
| Other | Conference Proceedings |
| Internet address |
|
User-Defined Keywords
- Computer vision
- Image retrieval
- Machine vision
- Search engines
Fingerprint
Dive into the research topics of 'A Human Face Image Searching System using Sketch'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver