Unsupervised Segmentation using Fuzzy Logicbased Texture Spectrum for MRI Brain Images
Textures are replications, symmetries and
combinations of various basic patterns, usually with some random
variation one of the gray-level statistics. This article proposes a
new approach to Segment texture images. The proposed approach
proceeds in 2 stages. First, in this method, local texture information
of a pixel is obtained by fuzzy texture unit and global texture
information of an image is obtained by fuzzy texture spectrum.
The purpose of this paper is to demonstrate the usefulness of fuzzy
texture spectrum for texture Segmentation.
The 2nd Stage of the method is devoted to a decision process,
applying a global analysis followed by a fine segmentation,
which is only focused on ambiguous points. The above Proposed
approach was applied to brain image to identify the components
of brain in turn, used to locate the brain tumor and its Growth
rate.
[1] Rosenfield and A.C.Kak," Digital image processing", 2nd edition.
[2] L.N., Wang F.Z., Mapps D.J., Robinson P., Jenkins D., Clegg W.W.,
"Nano-scale positioning for magnetic recording". European Journal of
Sensors and Actuators, Vol. A81, Nos. 1-3, April 2000, pp 313-316.
[3] F. Liu and R. W. Picard. Periodicity, directionality, and randomness:
Wold features for image modeling and retrieval. Technical report, MIT
Media Laboratory and Modeling Group, technical Report No.320, 1994.
[4] S.-F. Chang. Compressed-domain techniques for image/video indexing
and manipulation. In International Conference on Image Processing,
Special Session on Digital Library and Video-On Demand. I.E.E.E.,
October 1995.
[5] Wang,"A new statistical approach for texture analysis".
[6] P.Brodatz texture -A photographic Album for arucs and designers,
renhold.
[7] Shifeng Weng, Changshui Zhang and Zhonglin Lin. Exploring the
structure of supervised data by Discriminant Isometric Mapping. Pattern
Recognition, 38(4), Pages 599-601, 2005.
[8] Lee, J. S, 1981, Refined filtering of image noise using local statistics,
Computer Graphics and Image Processing, vol. 15, pp. 380-389.
[9] He, D. C. and W. Li, 1991, Texture features based on texture spectrum,
Pattern Recognition, vol. 24, no. 5, pp. 391-399.
[10] Ulaby, F. T., F. Kouyate, B. Brisco, and T. H. L. Williams, 1986,
Textural information in SAR images, IEEE Trans. Geosci. Remote
Sensing, vol. GE-24, no. 2, pp. 235-245
[1] Rosenfield and A.C.Kak," Digital image processing", 2nd edition.
[2] L.N., Wang F.Z., Mapps D.J., Robinson P., Jenkins D., Clegg W.W.,
"Nano-scale positioning for magnetic recording". European Journal of
Sensors and Actuators, Vol. A81, Nos. 1-3, April 2000, pp 313-316.
[3] F. Liu and R. W. Picard. Periodicity, directionality, and randomness:
Wold features for image modeling and retrieval. Technical report, MIT
Media Laboratory and Modeling Group, technical Report No.320, 1994.
[4] S.-F. Chang. Compressed-domain techniques for image/video indexing
and manipulation. In International Conference on Image Processing,
Special Session on Digital Library and Video-On Demand. I.E.E.E.,
October 1995.
[5] Wang,"A new statistical approach for texture analysis".
[6] P.Brodatz texture -A photographic Album for arucs and designers,
renhold.
[7] Shifeng Weng, Changshui Zhang and Zhonglin Lin. Exploring the
structure of supervised data by Discriminant Isometric Mapping. Pattern
Recognition, 38(4), Pages 599-601, 2005.
[8] Lee, J. S, 1981, Refined filtering of image noise using local statistics,
Computer Graphics and Image Processing, vol. 15, pp. 380-389.
[9] He, D. C. and W. Li, 1991, Texture features based on texture spectrum,
Pattern Recognition, vol. 24, no. 5, pp. 391-399.
[10] Ulaby, F. T., F. Kouyate, B. Brisco, and T. H. L. Williams, 1986,
Textural information in SAR images, IEEE Trans. Geosci. Remote
Sensing, vol. GE-24, no. 2, pp. 235-245
@article{"International Journal of Medical, Medicine and Health Sciences:54745", author = "G.Wiselin Jiji and L.Ganesan", title = "Unsupervised Segmentation using Fuzzy Logicbased Texture Spectrum for MRI Brain Images", abstract = "Textures are replications, symmetries and
combinations of various basic patterns, usually with some random
variation one of the gray-level statistics. This article proposes a
new approach to Segment texture images. The proposed approach
proceeds in 2 stages. First, in this method, local texture information
of a pixel is obtained by fuzzy texture unit and global texture
information of an image is obtained by fuzzy texture spectrum.
The purpose of this paper is to demonstrate the usefulness of fuzzy
texture spectrum for texture Segmentation.
The 2nd Stage of the method is devoted to a decision process,
applying a global analysis followed by a fine segmentation,
which is only focused on ambiguous points. The above Proposed
approach was applied to brain image to identify the components
of brain in turn, used to locate the brain tumor and its Growth
rate.", keywords = "Fuzzy Texture Unit, Fuzzy Texture Spectrum, andPattern Recognition, segmentation.", volume = "1", number = "5", pages = "248-3", }