Title :
Object Categorization Using Genetic Programming
Author :
Korra, Jyothi ; Devi, Susheela
Author_Institution :
Comput. Sci. & Autom., Indian Inst. of Sci., Bangalore, India
Abstract :
In Computer Vision, problem of identifying or classifying the objects present in an image is called Object Categorization. It is challenging problem, especially when the images have clutter background, occlusions or different lighting conditions. Many vision features have been proposed which aid object categorization even in such adverse conditions. Past research has shown that, employing multiple features rather than any single features leads to better recognition. Multiple Kernel Learning (MKL) framework has been developed for learning an optimal combination of features for object categorization. Existing MKL methods use linear combination of base kernels which may not be optimal for object categorization. Real-world object categorization may need to consider complex combination of kernels(non-linear) and not only linear combination. Evolving non-linear functions of base kernels using Genetic Programming is proposed in this paper. Experiment results show that non-kernel generated using genetic programming gives good accuracy as compared to linear combination of kernels.
Keywords :
computer vision; genetic algorithms; image classification; object detection; support vector machines; MKL method; computer vision; genetic programming; linear combination; multiple kernel learning framework; real world object categorization; vision feature; Accuracy; Computer vision; Feature extraction; Genetic programming; Kernel; Support vector machines; genetic programming; multiple kernel learning; non-linear kernel combination; object categorization; support vector machine;
Conference_Titel :
Genetic and Evolutionary Computing (ICGEC), 2010 Fourth International Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4244-8891-9
Electronic_ISBN :
978-0-7695-4281-2
DOI :
10.1109/ICGEC.2010.80