Feature selection with equalized salience measures and its application to segmentation

Segmentation is a crucial step in computer vision in which texture plays an important role. The existence of a large amount of methods from which texture can be computed is, sometimes, a hurdle to overcome when it comes to modeling solutions for texture-based segmentation. Following the excellence of the natural vision system and its generality, this work has adopted a feature selection method based on salience of synaptic connections of a Multilayer Perceptron neural network. Unlike traditional approaches, this paper introduces an equalization scheme to salience measures which contributed to significantly improve the selection of the most suitable features and, hence, yield better segmentation. The proposed method is compared with exhaustive search according to the Jeffrey-Matusita distance criterion. Segmentation for images of natural scenes has also been provided as a probable application of the method.

[1]  Ravinder Nath,et al.  Determining the saliency of input variables in neural network classifiers , 1997, Comput. Oper. Res..

[2]  Pietro Perona,et al.  3D Photography Using Shadows in Dual-Space Geometry , 1999, International Journal of Computer Vision.

[3]  Robert B. Fisher,et al.  Acquisition of consistent range data using local calibration , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[4]  Franc¸ois Blais,et al.  Review of 20 years of range sensor development , 2003, IS&T/SPIE Electronic Imaging.

[5]  Richard Szeliski,et al.  A layered approach to stereo reconstruction , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[6]  Pietro Perona,et al.  What do planar shadows tell about scene geometry? , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[7]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[8]  Dong-Chen He,et al.  Texture discrimination based on an optimal utilization of texture features , 1988, Pattern Recognit..

[9]  Pietro Perona,et al.  3D photography on your desk , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[10]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[11]  Andrew Zisserman,et al.  Automatic reconstruction of piecewise planar models from multiple views , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[12]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[13]  Giovanna Castellano,et al.  Variable selection using neural-network models , 2000, Neurocomputing.

[14]  K. Ruba Soundar,et al.  Texture image segmentation using combined features from spatial and spectral distribution , 2006, Pattern Recognit. Lett..

[15]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[16]  Tom Heskes,et al.  Partial Retraining: A New Approach to Input Relevance Determination , 1999, Int. J. Neural Syst..

[17]  Tom Heskes,et al.  Input Selection with Partial Retraining , 1997, ICANN.

[18]  Asheer K. Bachoo,et al.  Texture detection for segmentation of iris images , 2005 .

[19]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[20]  Wen Gao,et al.  Unsupervised Texture Classification: Automatically Discover and Classify Texture Patterns , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[21]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[22]  E. O. Brigham,et al.  The Fast Fourier Transform , 1967, IEEE Transactions on Systems, Man, and Cybernetics.

[23]  Wilson S. Geisler,et al.  Texture segmentation using Gabor modulation/demodulation , 1987, Pattern Recognit. Lett..

[24]  A. Ardeshir Goshtasby,et al.  A paintbrush laser range scanner , 2006, Comput. Vis. Image Underst..

[25]  Wright-Patterson Afb,et al.  Feature Selection Using a Multilayer Perceptron , 1990 .

[26]  Anil K. Jain,et al.  Feature Selection: Evaluation, Application, and Small Sample Performance , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Xing Chen,et al.  A laser range scanner designed for minimum calibration complexity , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[28]  E. Brigham,et al.  The fast Fourier transform , 2016, IEEE Spectrum.

[29]  Richard Szeliski,et al.  Geometrically Constrained Structure from Motion: Points on Planes , 1998, SMILE.

[30]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[31]  Reinhold Huber,et al.  Feature selection for ERS-1/2 InSAR classification: high dimensionality case , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[32]  Tom Heskes,et al.  A theoretical comparison of batch-mode, on-line, cyclic, and almost-cyclic learning , 1996, IEEE Trans. Neural Networks.

[33]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[34]  Anil K. Jain,et al.  Texture Analysis , 2018, Handbook of Image Processing and Computer Vision.

[35]  Patrick Gallinari,et al.  FEATURE SELECTION WITH NEURAL NETWORKS , 1999 .