DocumentCode :
1337253
Title :
Grouping-based nonadditive verification
Author :
Amir, Arnon ; Lindenbaum, Michael
Author_Institution :
Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel
Volume :
20
Issue :
2
fYear :
1998
fDate :
2/1/1998 12:00:00 AM
Firstpage :
186
Lastpage :
192
Abstract :
Verification is the final decision stage in many object recognition processes. It is carried out by evaluating a score for every hypothesis and choosing the hypotheses associated with the highest score. This paper suggests a grouping-based verification paradigm, relying on the observation that a group of data features belonging to a hypothesized object instance should be a “good group”. Therefore, it should support perceptual grouping information available from the image by grouping relations. The proposed score, which is the joint likelihood of these grouping cues, quantifies this observation in a probabilistic framework. Experiments with synthetic and real images show that the proposed method performs better in difficult cases
Keywords :
image recognition; object recognition; probability; data features; grouping-based nonadditive verification; hypothesis scores; joint likelihood; object recognition processes; Additives; Humans; Image segmentation; Layout; Object recognition; Particle measurements; Reliability theory;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.659936
Filename :
659936
Link To Document :
بازگشت