Studying the Kidney Textural Using Statistical Features and Local Binary Pattern
Keywords:
Local Binary Pattern, Watershed segmentation, Geometrical Features, Statistical FeaturesAbstract
The structural of image either medical or any other images is describe by their texture, thus the texture is consider as the characteristic information of the image. In this search the Computed tomography (CT) images is used, the images size are 512×512 of (12) images for different kidney cases, four for Cyst, four for Fibrosis and four for Stone case. The watershed segmentation used to segment the Cyst, Fibrosis and Stone from the healthy texture as well as, the “Local Binary Pattern” (LBP) which is a texture descriptor used for locating the Cyst, Fibrosis and stone from the rest images, finally the textural spectrum is used as statistical features, more over the geometrical features are calculated in order to describe the shape and geometry of Cyst, Fibrosis and Stone of the Kidney by finding the irregularity value. The texture features accuracy which are obtained in this search are, for the Fibrosis, the Local Binary Pattern is 89.91%, the Textural Spectrum 92.65% and Local Binary with the Textural Spectrum is 94.55%. For the Cyst texture features accuracy are, the Local Binary Pattern is 93.65%, the Textural Spectrum 94.56% and Local Binary with the Textural Spectrum is 96%. And for the Stone the texture features accuracy are, the Local Binary Pattern is 88.4%, the Textural Spectrum 91.36% and Local Binary with the Textural Spectrum is 95%.
References
[2] A. K. Jain, “Fundamentals of Digital Image Processing”, Englewood Cliffs, Prentice Hall. 1989.
[3] B. Vijayalakshmi1 & V. Subbiah Bharathi, “Texture Classification Using Combined Statistical Approach”, International Journal of Applied Computing, 4(1), pp. 7-11. 2011.
[4] B. S. Manjunath, W. Y. Ma, “Texture Features for Browsing and Retrieval of Image Data”, IEEE Transactions on Pattern Analysis and Machine, Volume 18, Issue 8, pp. 837–842. 1996.
[5] S. BEUCHER, “The Watershed Transformation Applied To Image Segmentation”, Scanning microscopy. Supplement 6. Prentice Hall 2000.
[6] X. Zhang, L. Chen, L. Pan and L. Xiong, “Study on the Image Segmentation Based On ICA and Watershed Algorithm,” Fifth International Conference on Intelligent Computation Technology and Automation, pp. 978-912, IEEE. 2012.
[7] R. C.Gonzalez and R.E.Woods, (Digital Image Processing), Third Edition. Pearson Prentice Hall 2008.
[8] S. Mazhir, “Studying the Effect of Cold Plasma on Living Tissues Using Images Texture analysis”, Diyala Journal for Pure Science. vol. 13. No.2. 2017.
[9] Ch. Chuan, “Thyroid Nodule Segmentation and Component Analysis in Ultrasound Images” Proceeding: Asia-Pacific Signal and Information Processing Association. 2009.
[10] U S N Raju, A Sridhar Kumar, B Mahesh, B Eswara Reddy, “Texture Classification With High Order Local Pattern Descriptor: Local Derivative Patter”, GJCST, Vol.10, Issue 8 Ver. 1, pp72. 2010.
[11] A. H.Ali, E. M.Hadi, and S. N. Mazhir, “Diagnosis of liver Tumor from CT Images Using Unsupervised Classification with Geometrical and Statistical features”, IJACSSE, Vol.5, Issue3. 2015.
.jpg)
