An experimental evaluation of echo state network for colour image segmentation

Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms have been developed, but achieving accurate segmentation still remains a challenging task. Recently, reservoir computing (RC) has drawn much attention in machine learning as a new model of recurrent neural networks (RNN). Echo State Network (ESN) represents one efficient realization of RC, which is initially designed to facilitate learning in Recurrent Neural Networks. In this paper we investigate the viability of ESN as feature extractor for pixel classification based colour image segmentation. Extensive experiments are conducted on real world colour image datasets and the global ESN reservoir parameters are varied to identify their operating ranges that allow the use of the reservoir nodes internal activations as new pixel features for the colour image segmentation task. A simple feed forward neural network is used to realize the ESN readout function and classify these new features. The experimental results show that the proposed method achieves high performance image segmentation comparing with state-of-the-art techniques. In addition, a set of empirically derived guidelines for setting the reservoir global parameters are proposed.

[1]  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.

[2]  P. Sivakumar,et al.  A REVIEW ON IMAGE SEGMENTATION TECHNIQUES , 2016 .

[3]  D. Suganthi.  fMRI SEGMENTATION USING ECHO STATE NEURAL NETWORK , 2008 .

[4]  Xiangyang Wang,et al.  LS-SVM-based image segmentation using pixel color-texture descriptors , 2012, Pattern Analysis and Applications.

[5]  Abdelkader Benyettou,et al.  Novel Approach Using Echo State Networks for Microscopic Cellular Image Segmentation , 2016, Cognitive Computation.

[6]  Dirk P. Kroese,et al.  Kernel density estimation via diffusion , 2010, 1011.2602.

[7]  Marco Wiering,et al.  2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) , 2011, IJCNN 2011.

[8]  Kannan,et al.  ON IMAGE SEGMENTATION TECHNIQUES , 2022 .

[9]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  K. K. Rahini,et al.  Review of Image Segmentation Techniques: A Survey , 2014 .

[11]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

[12]  Bai Huifeng,et al.  Traffic-load prediction based on echo state network improved by Bayesian theory in 10G-EPON , 2015 .

[13]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[14]  Petia Koprinkova-Hristova,et al.  Clustering of spectral images using Echo state networks , 2013, 2013 IEEE INISTA.

[15]  Haiyang Li,et al.  Dynamic particle swarm optimization and K-means clustering algorithm for image segmentation , 2015 .

[16]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[17]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Tanish Zaveri,et al.  Deep learning feature map for content based image retrieval system for remote sensing application , 2016 .

[19]  Michal Irani,et al.  What Is a Good Image Segment? A Unified Approach to Segment Extraction , 2008, ECCV.

[20]  Benjamin Schrauwen,et al.  The spectral radius remains a valid indicator of the Echo state property for large reservoirs , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[21]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[22]  Komal Arora,et al.  A Study Analysis on the Different Image Segmentation Techniques , 2014 .

[23]  Ronen Basri,et al.  Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Jianfei Cai,et al.  A benchmark for semantic image segmentation , 2013, 2013 IEEE International Conference on Multimedia and Expo (ICME).

[25]  Yun Zhang,et al.  Incorporating Adaptive Local Information Into Fuzzy Clustering for Image Segmentation , 2015, IEEE Transactions on Image Processing.

[26]  Muhammad Khan,et al.  A Survey: Image Segmentation Techniques , 2014 .

[27]  Stefan J. Kiebel,et al.  Re-visiting the echo state property , 2012, Neural Networks.

[28]  Ronen Basri,et al.  Texture segmentation by multiscale aggregation of filter responses and shape elements , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[29]  Shu-Xian Lun,et al.  A novel model of leaky integrator echo state network for time-series prediction , 2015, Neurocomputing.

[30]  Jianfei Cai,et al.  Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation , 2015, J. Vis. Commun. Image Represent..