Categorization and Reorientation of Images Based on Low Level Features英文文献资料.docVIP

Journal of Intelligent Learning Systems and Applications, 2011, 3, **-** 1 doi:10.4236/jilsa.2011.31001 Published Online February 2011 (http://www.SciRP.org/journal/jilsa) Categorization and Reorientation of Images Based on Low Level Features Rajen Bhatt , Gaurav Sharma , Abhinav Dhall , Naresh Kumar , Santanu Chaudhury 1 1 1 1 2 1 Samsung India Software Center, Noida, India; 2 Electrical Engineering Department, Indian Institution of Technology Delhi, New Delhi, India. Email: rajen.bhatt@, schaudhury@ Received June 22 , 2010; revised July 29 , 2010; accepted September 23 , 2010 nd th rd ABSTRACT A hierarchical system to perform automatic categorization and reorientation of images using content analysis is pre- sented. The proposed system first categorizes images to some a priori defined categories using rotation invariant features. o o o o At the second stage, it detects their correct orientation out of {0 , 90 , 180 , and 270 } using category specific model. The system has been specially designed for embedded devices applications using only low level color and edge features. Ma- chine learning algorithms optimized to suit the embedded implementation like support vector machines (SVMs) and scalable boosting have been used to develop classifiers for categorization and orientation detection. Results are pre- sented on a collection of about 7000 consumer images collected from open resources. The proposed system finds it ap- plications to various digital media products and brings pattern recognition solutions to the consumer electronics domain. Keywords: Categorization, Digital Co