Object Class Recognition Using NEAT-Evolved Artificial Neural Network

Object class recognition is a highly challenging area in computer vision and machine learning. In this paper, we introduce a novel approach to object class recognition using Neuro Evolution of Augmenting Topologies (NEAT) to evolve artificial neural networks (ANN) capable of taking advantage of the robust SIFT feature based descriptor histograms. We claim that NEAT can produce ANN classifier which exhibits outstanding ability of learning from only afew training examples without sacrificing accuracy. Our empirical evaluations against the performance of state of the art statistical machine learning method such as support vector machine show that NEAT-evolved ANN classifier outperforms by an average of 9.96% higher accuracy when presented with very small training set proving its superior ability to generalize its learning.

[1]  Risto Miikkulainen,et al.  Competitive Coevolution through Evolutionary Complexification , 2011, J. Artif. Intell. Res..

[2]  Hermann Ney,et al.  Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures , 2006, BMVC.

[3]  Javier Rodeiro Iglesias,et al.  S-means : Similarity Driven Clustering and Its application in Gravitational-Wave Astronomy Data Mining , 2007 .

[4]  John R. Koza,et al.  Genetic generation of both the weights and architecture for a neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[5]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[7]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[8]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[9]  Risto Miikkulainen,et al.  Automatic feature selection in neuroevolution , 2005, GECCO '05.

[10]  Xin Yao,et al.  EPNet for Chaotic Time-Series Prediction , 1996, SEAL.

[11]  Thomas M. Strat,et al.  Employing Contextual Information in Computer Vision , 1993 .

[12]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[13]  Risto Miikkulainen,et al.  Evolving Keepaway Soccer Players through Task Decomposition , 2003, GECCO.

[14]  Risto Miikkulainen,et al.  Evolving a real-world vehicle warning system , 2006, GECCO.

[15]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.

[16]  Martin Vingron,et al.  Support Vector Machines for Protein Fold Class Prediction , 2003 .

[17]  Derek James.  Evolving a Neural Network Active Vision System for Shape Discrimination , 2005 .

[18]  Matthew Crosby.  Evolving a Roving Eye for Go , 2008 .

[19]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[20]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[21]  Frédéric Gruau,et al.  Genetic synthesis of Boolean neural networks with a cell rewriting developmental process , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[22]  Chris Harris,et al.  Geometry from visual motion , 1993 .

[23]  Risto Miikkulainen,et al.  Evolving a Roving Eye for Go , 2004, GECCO.

[24]  Takashi Matsuyama.  Knowledge-Based Aerial Image Understanding Systems and Expert Systems for Image Processing , 1987, IEEE Transactions on Geoscience and Remote Sensing.