Title :
Hierarchical invariant sparse modeling for image analysis
Author :
Bar, Leah ; Sapiro, Guillermo
Author_Institution :
Tel Aviv Univ., Tel Aviv, Israel
Abstract :
Sparse representation theory has been increasingly used in signal processing and machine learning. In this paper we introduce a hierarchical sparse modeling approach which integrates information from the image patch level to derive a mid-level invariant image and pattern representation. The proposed framework is based on a hierarchical architecture of dictionary learning for sparse coding in a cortical (log-polar) space, combined with a novel pooling operator which incorporates the Rapid transform and max pooling to attain rotation and scale invariance. The invariant sparse representation of patterns here presented - can be used in different object recognition tasks. Promising results are obtained for three applications - 2D shapes classification, texture recognition and object detection.
Keywords :
feature extraction; image classification; image coding; image representation; image texture; learning (artificial intelligence); object detection; object recognition; support vector machines; 2D shape classification; dictionary learning; hierarchical invariant sparse modeling; image analysis; invariant image representation; machine learning; max pooling; object detection; object recognition task; pattern representation; pooling operator; rapid transform; rotation invariance; scale invariance; signal processing; sparse coding; sparse representation theory; texture recognition; Dictionaries; Feature extraction; Manganese; Testing; Training; Transforms; Vectors; Feature extraction; dictionary learning; hierarchical models; invariant representation; sparse coding;
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location :
Brussels
Print_ISBN :
978-1-4577-1304-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2011.6116125