A novel method for underwater image segmentation based on M-band wavelet transform and human psychovisual phenomenon(HVS)

Underwater image segmentation becomes a difficult and challenging task due to various perturbations present in the water. In this paper we propose a novel method for underwater image segmentation based on M-band wavelet transform and human psychovisual phenomenon(HVS). The M-band wavelet transform captures the texture of the underwater image by decomposing the image into sub bands with different scales and orientations. The proper sub bands for segmentation are selected depending on the HVS. The HVS imitates the original visual technique of a human being and it is used to divide each sub band into Weber, De-Vries Rose and Saturation regions. A sub band is selected for segmentation depending on those three regions. The performance of the proposed method is found to be superior than that of the stare-of-the-art methods for underwater image segmentation on standard data set.

[1]  Michael Kabatek,et al.  An underwater target detection system for electro-optical imagery data , 2009, OCEANS 2009.

[2]  Hiranmoy Roy,et al.  Image thresholding using LBP and GA-based optimal parameter selection for 2D Tsallis-Havrda-Charvat entropy , 2016, 2016 Second International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN).

[3]  SANGEnfang,et al.  Underwater acoustic image segmentation based on deformable template , 2005 .

[4]  Weilin Hou,et al.  Image feature detection and matching in underwater conditions , 2010, Defense + Commercial Sensing.

[5]  Sankar K. Pal,et al.  Thresholding for edge detection using human psychovisual phenomena , 1986, Pattern Recognit. Lett..

[6]  Gershon Buchsbaum,et al.  An Analytical Derivation of Visual Nonlinearity , 1980, IEEE Transactions on Biomedical Engineering.

[7]  Chunming Li,et al.  A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI , 2011, IEEE Transactions on Image Processing.

[8]  Luc Jaulin,et al.  Color-based underwater object recognition using water light attenuation , 2012, Intell. Serv. Robotics.

[9]  Mausumi Acharyya,et al.  An adaptive approach to unsupervised texture segmentation using M-Band wavelet transform , 2001, Signal Process..

[10]  Puran Gour,et al.  Underwater Image Segmentation using CLAHE Enhancement and Thresholding , 2012 .

[11]  Peter N. Heller,et al.  Theory of regular M-band wavelet bases , 1993, IEEE Trans. Signal Process..

[12]  Xiu Li,et al.  Saliency segmentation and foreground extraction of underwater image based on localization , 2016, OCEANS 2016 - Shanghai.

[13]  Manish Soni,et al.  Segmentation of Underwater Objects using CLAHE Enhancement and Thresholding with 3-class Fuzzy C-Means Clustering , 2014 .

[14]  Mausumi Acharyya,et al.  Extraction of Noise Tolerant, Gray-Scale Transform and Rotation Invariant Features for Texture Segmentation Using Wavelet Frames , 2008, Int. J. Wavelets Multiresolution Inf. Process..

[15]  G. Padmavathi,et al.  Non linear Image segmentation using fuzzy c means clustering method with thresholding for underwater images , 2010 .

[16]  Luc Jaulin,et al.  Automatic underwater image pre-processing , 2006 .