Image segmentation using a hybrid gradient based watershed transform

A watershed transform segmentation method based on hybrid gradient that combines intensity and texture visual cues is proposed. Firstly a bilateral filtering method derived from robust statistics is used to extract the intensity gradient. Secondly a Gabor filter bank is applied to extract texture features. With a smoothing post process, the texture gradient is extracted. Then by morphological dilation and normalization process texture and intensity gradients are fused to form the hybrid gradient. At last the marked watershed transform on the hybrid gradient image is carried out to segment the image. The experiment results show that the proposed method is effective in generating accurate primitive-objects boundaries and meanwhile reducing the over segmentation of image.

[1]  Jitendra Malik,et al.  Contour and Texture Analysis for Image Segmentation , 2001, International Journal of Computer Vision.

[2]  Hassan Ghassemian,et al.  Texture-Gradient-Based Contour Detection , 2006, EURASIP J. Adv. Signal Process..

[3]  Adam C. Winstanley,et al.  Complementary texture and intensity gradient estimation and fusion for watershed segmentation , 2011, Machine Vision and Applications.

[4]  D. Crookes,et al.  MPEG-2 to H.264 Transcoding for DVB-H Applications , 2007, International Machine Vision and Image Processing Conference (IMVIP 2007).

[5]  Guillermo Sapiro,et al.  Robust anisotropic diffusion , 1998, IEEE Trans. Image Process..

[6]  Sankar K. Pal,et al.  Segmentation of multispectral remote sensing images using active support vector machines , 2004, Pattern Recognit. Lett..

[7]  Scott T. Acton,et al.  On the Convergence of Bilateral Filter for Edge-Preserving Image Smoothing , 2007, IEEE Signal Processing Letters.

[8]  Eli Saber,et al.  Survey of contemporary trends in color image segmentation , 2012, J. Electronic Imaging.

[9]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Maria Petrou,et al.  On the choice of the parameters for anisotropic diffusion in image processing , 2013, Pattern Recognit..

[11]  David R. Bull,et al.  Combined morphological-spectral unsupervised image segmentation , 2005, IEEE Transactions on Image Processing.

[12]  Gabriel Cristóbal,et al.  A comparison study of Gabor and log-Gabor wavelets for texture segmentation , 2011, 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA).

[13]  Cedric Nishan Canagarajah,et al.  Image segmentation using a texture gradient based watershed transform , 2003, IEEE Trans. Image Process..

[14]  P. Corcoran,et al.  Watershed Segmentation Using a Multiscale Ramp Edge Merging Strategy , 2007, International Machine Vision and Image Processing Conference (IMVIP 2007).

[15]  Mila Nikolova,et al.  Markovian reconstruction using a GNC approach , 1999, IEEE Trans. Image Process..

[16]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[17]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  Guifeng Zhang,et al.  An Edge Embedded Marker-Based Watershed Algorithm for High Spatial Resolution Remote Sensing Image Segmentation , 2010, IEEE Transactions on Image Processing.

[19]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[20]  David A. Clausi,et al.  Designing Gabor filters for optimal texture separability , 2000, Pattern Recognit..