Title :
Object categorization using Cartesian Genetic Programming (CGP) and CGP-Evolved Artificial Neural Network
Author :
Salahuddin, Sumayyea ; Khan, Maryam Mahsal
Author_Institution :
Dept. of Comput. Syst. Eng., Univ. of Eng. & Technol., Peshawar, Pakistan
Abstract :
In this paper, we address the problem of recognizing object categories by proposing a learning model based on evolutionary algorithm that takes unsegmented, complex images which is tolerant to 2D affine transformations such as scaling and translation in the image plane and 3D transformations of an object such as illumination changes and rotation in depth. To achieve this, first object features are extracted from an image using modified Bag of Keypoints model and then learning and classification is performed through evolutionary network classifiers i.e. Cartesian Genetic Programming (CGP) and Cartesian Genetic Programming Evolved Artificial Neural Network (CG-PANN). Our empirical evaluations show that proposed network classifiers exhibit outstanding ability of learning from fewer training examples with good accuracy. Results are compared with NEAT-Evolved Artificial Neural Network classifier which shows clearly that our network classifiers outperform and generalize better than NEAT.
Keywords :
feature extraction; genetic algorithms; image classification; neural nets; object recognition; transforms; CGP-evolved artificial neural network; Cartesian genetic programming; NEAT-evolved artificial neural network classifier; affine transformations; evolutionary algorithm; evolutionary network classifiers; image plane; learning model; modified bag of keypoints model; object categorization; object feature extraction; Accuracy; Artificial neural networks; Feature extraction; Genetic programming; Motorcycles; Training; Visualization; Bag of Keypoints; Cartesian Genetic Programming; Cartesian Genetic Programming Evolved Artificial Neural Network; Object Categorization; SIFT;
Conference_Titel :
Computer Applications and Industrial Electronics (ICCAIE), 2010 International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-9054-7
DOI :
10.1109/ICCAIE.2010.5735073