Title :
Distinct Multicolored Region Descriptors for Object Recognition
Author :
Naik, Sarif Kumar ; Murthy, C.A.
Author_Institution :
Indian Stat. Inst., Kolkata
fDate :
7/1/2007 12:00:00 AM
Abstract :
The problem of object recognition has been considered here. Color descriptions from distinct regions covering multiple segments are considered for object representation. Distinct multicolored regions are detected using edge maps and clustering. Performance of the proposed methodologies has been evaluated on three data sets and the results are found to be better than existing methods when a small number of training views is considered.
Keywords :
edge detection; image colour analysis; image representation; image segmentation; object recognition; pattern clustering; distinct multicolored region descriptor; edge detection; object recognition; object representation; pattern clustering; Brightness; Data mining; Image edge detection; Image representation; Image retrieval; Image segmentation; Indexing; Object recognition; Principal component analysis; Shape; Object representation; image representation.; object descriptor; object matching; object recognition; Algorithms; Artificial Intelligence; Color; Colorimetry; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2007.1029
