DocumentCode :
2490781
Title :
Extraction of shoe-print patterns from impression evidence using Conditional Random Fields
Author :
Ramakrishnan, Veshnu ; Srihari, Sargur
Author_Institution :
Dept. of Comput. Sci. & Eng., State Univ. of New York, Amherst, NY
fYear :
2008
fDate :
8-11 Dec. 2008
Firstpage :
1
Lastpage :
4
Abstract :
Impression evidence in the form of shoe-prints are commonly found in crime scenes. A critical step in automatic shoe-print identification is extraction of the shoe-print pattern. It involves isolating the shoe-print foreground (impressions made by the shoe) from the remaining elements (background and noise). The problem is formulated as one of labeling the regions of a shoeprint image as foreground/background. It is formulated as a machine learning task which is approached using a probabilistic model, i.e., conditional random fields (CRFs). Since the model exploits the inherent long range dependencies that exist in the shoe-print it is more robust than other approaches, e.g., neural networks and adaptive thresholding of grey-scale images into binary. This was demonstrated using a data set of 45 shoeprint image pairs representing latent and known shoe-print images.
Keywords :
feature extraction; image matching; learning (artificial intelligence); police data processing; probability; random processes; automatic shoe-print identification; conditional random field; crime scene; image matching; image representation; impression evidence; machine learning task; probabilistic model; shoe-print image pattern extraction; shoeprint image region labeling; Chemicals; Feature extraction; Footwear; Forensics; Labeling; Layout; Machine learning; Neural networks; Robustness; Text analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location :
Tampa, FL
ISSN :
1051-4651
Print_ISBN :
978-1-4244-2174-9
Electronic_ISBN :
1051-4651
Type :
conf
DOI :
10.1109/ICPR.2008.4761881
Filename :
4761881
Link To Document :
بازگشت