Is a Single Image Sufficient for Evolving Edge Features by Genetic Programming?

Typically, a single natural image is not sufficient to train a program to extract edge features in edge detection when only training images and their ground truth are provided. However, a single training image might be considered as proper training data when domain knowledge, such as used in Gaussian-based edge detection, is provided. In this paper, we employ Genetic Programming (GP) to automatically evolve Gaussian-based edge detectors to extract edge features based on training data consisting of a single image only. The results show that a single image with a high proportion of true edge points can be used to train edge detectors which are not significantly different from rotation invariant surround suppression. When the programs separately evolved from eight single images are considered as weak classifiers, the combinations of these programs perform better than rotation invariant surround suppression.

[1]  Bernard F. Buxton,et al.  Evolving edge detectors with genetic programming , 1996 .

[2]  Pierre Collet,et al.  A GP Artificial Ant for Image Processing: Preliminary Experiments with EASEA , 2001, EuroGP.

[3]  Michael Fink,et al.  Object Classification from a Single Example Utilizing Class Relevance Metrics , 2004, NIPS.

[4]  R. Poli.  Genetic programming for image analysis , 1996 .

[5]  Nicolai Petkov,et al.  Contour detection based on nonclassical receptive field inhibition , 2003, IEEE Trans. Image Process..

[6]  Mark Johnston,et al.  Soft edge maps from edge detectors evolved by genetic programming , 2012, 2012 IEEE Congress on Evolutionary Computation.

[7]  Boualem Boashash,et al.  Optimal parameters for edge detection , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[8]  Doina Bucur,et al.  Influence Maximization in Social Networks with Genetic Algorithms , 2016, EvoApplications.

[9]  Mitra Basu,et al.  Gaussian-based edge-detection methods - a survey , 2002, IEEE Trans. Syst. Man Cybern. Part C.

[10]  Yang Zhang,et al.  Evolving optimal feature extraction using multi-objective genetic programming: a methodology and preliminary study on edge detection , 2005, GECCO '05.

[11]  Nicolai Petkov,et al.  Contour and boundary detection improved by surround suppression of texture edges , 2004, Image Vis. Comput..

[12]  Dongmo Zhang,et al.  AI 2012: Advances in Artificial Intelligence , 2012, Lecture Notes in Computer Science.

[13]  Zhuowen Tu,et al.  Supervised Learning of Edges and Object Boundaries , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[14]  Moshe Sipper,et al.  Evolution of a local boundary detector for natural images via genetic programming and texture cues , 2009, GECCO.

[15]  Andrew M. Tyrrell,et al.  Design of highly parallel edge detection nodes using evolutionary techniques , 1999, Proceedings of the Seventh Euromicro Workshop on Parallel and Distributed Processing. PDP'99.

[16]  Nicolai Petkov,et al.  Edge and line oriented contour detection: State of the art , 2011, Image Vis. Comput..

[17]  Mark Johnston,et al.  Automatic Construction of Invariant Features Using Genetic Programming for Edge Detection , 2012, Australasian Conference on Artificial Intelligence.

[18]  Jun Wang,et al.  A novel genetic programming based morphological image analysis algorithm , 2010, GECCO '10.

[19]  Songde Ma,et al.  Derivative computation by multiscale filters , 1998, Image Vis. Comput..

[20]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[21]  Fredrik Bergholm,et al.  Edge Focusing , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Vinciane Lacroix.  The primary raster: a multiresolution image description , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[23]  Mark Johnston,et al.  Genetic programming for edge detection: A global approach , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[24]  Paul A. Viola,et al.  Learning from one example through shared densities on transforms , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[25]  Jerzy Rutkowski,et al.  Application of genetic programming to edge detector design , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[26]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Mark Johnston,et al.  Automatic Construction of Gaussian-Based Edge Detectors Using Genetic Programming , 2013, EvoApplications.

[28]  Riccardo Poli,et al.  Morphological algorithm design for binary images using genetic programming , 2006, Genetic Programming and Evolvable Machines.

[29]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.