A Texture Segmentation Using Modified Hill-Climbing Approach

Image segmentation is crucial to object-oriented remote sensing imagery analysis. In this paper, a newly modified texture segmentation algorithm is proposed using spectral, shape and intensity features. This algorithm is a robust technique that can be applied directly to the color images. The image is preprocessed using Adaptive Switching Median Filter, which removes the impulse noises and keeping the fine details of the image intact in the most efficient manner. Also, the preprocessed image is smoothened using morphological operators, which reduces the false detection of abnormal cells. Then, the preprocessed image is transformed into HSV (Hue, Saturation and value) color space representation in order to analyze and establish a color contrast gradient. The multiscale morphological gradient in the intensity channel of the preprocessed image is obtained and multiplied with the color contrast gradient. The shape feature is extracted from the preprocessed image based on the descriptors such as compactness, convexness, rectangularity and eccentricity, moment invariants. Based on these spectral, shape and intensity features, markers are extracted for this image and given as input to the watershed algorithm which uses a Hill-Climbing approach to identify and label the neighborhood pixels. This algorithm may reduce the computational complexity by avoiding the process of computing lower-complete image.

[1]  Moncef Gabbouj,et al.  An efficient watershed segmentation algorithm suitable for parallel implementation , 1995, Proceedings., International Conference on Image Processing.

[2]  Josef Kittler,et al.  Automatic watershed segmentation of randomly textured color images , 1997, IEEE Trans. Image Process..

[3]  Trygve Randen,et al.  Texture segmentation using filters with optimized energy separation , 1999, IEEE Trans. Image Process..

[4]  Hsi-Chia Hsin,et al.  Texture segmentation using modulated wavelet transform , 2000, IEEE Trans. Image Process..

[5]  G. Willhauck,et al.  Comparison of object oriented classification techniques and standard image analysis for the use of change detection between SPOT multispectral satellite images and aerial photos. , 2000 .

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

[7]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[8]  Liangpei Zhang,et al.  Classification of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Fang Liu,et al.  Spectral Clustering Ensemble Applied to SAR Image Segmentation , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Huseyin Gokhan Akcay,et al.  Automatic Detection of Geospatial Objects Using Multiple Hierarchical Segmentations , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Hui Zhou,et al.  A Novel Hierarchical Method of Ship Detection from Spaceborne Optical Image Based on Shape and Texture Features , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Hong Huo,et al.  A Novel Texture-Preceded Segmentation Algorithm for High-Resolution Imagery , 2010, IEEE Transactions on Geoscience and Remote Sensing.