Digital Image Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Histogram Based Comparative Analysis of LBP and Improved LBP Based Texture Extraction of Mammogram


Affiliations
1 Department of Electronics and Communication Engineering, Pondicherry University, Pondicherry, India
2 Department of ECE, PPG Institute of Technology, Coimbatore, India
3 Department of Electronics and Communication Engineering, Mahatma Gandhi University, India
4 Department of Electronics and Communication Engineering, Karunya University, India
     

   Subscribe/Renew Journal


Texture is an important characteristic for the analysis of many types of images and for the detection of false positives. The aim of this paper is to analyze the histogram comparisons of LBP and ILBP methods which are used for the textural extraction of a mammogram. In local binary pattern method the thresholding is done with the center pixel. In some applications, the center pixel contains more information than any other pixel. This limitation is reduced in the improved local binary pattern. It incorporates the information of the center pixel, by thresholding all the pixels with their median. A Histogram is a graphical representation showing a visual impression of the distribution of data. Because the information contained in the graph is a representation of pixel distribution as a function of tonal variation, image histograms can be analyzed for peaks and/or valleys which can then be used to determine a threshold value. The Histogram analysis shows that the improved local binary pattern contains more pixel count than the other one. So it can extract large amount of information.

Keywords

Mammogram, Thresholding, Benign, Malignant.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 150

PDF Views: 2




  • Histogram Based Comparative Analysis of LBP and Improved LBP Based Texture Extraction of Mammogram

Abstract Views: 150  |  PDF Views: 2

Authors

D. Narain Ponraj
Department of Electronics and Communication Engineering, Pondicherry University, Pondicherry, India
P. Poongodi
Department of ECE, PPG Institute of Technology, Coimbatore, India
Sweety Kunjachan
Department of Electronics and Communication Engineering, Mahatma Gandhi University, India
Litty Maria Joy
Department of Electronics and Communication Engineering, Karunya University, India

Abstract


Texture is an important characteristic for the analysis of many types of images and for the detection of false positives. The aim of this paper is to analyze the histogram comparisons of LBP and ILBP methods which are used for the textural extraction of a mammogram. In local binary pattern method the thresholding is done with the center pixel. In some applications, the center pixel contains more information than any other pixel. This limitation is reduced in the improved local binary pattern. It incorporates the information of the center pixel, by thresholding all the pixels with their median. A Histogram is a graphical representation showing a visual impression of the distribution of data. Because the information contained in the graph is a representation of pixel distribution as a function of tonal variation, image histograms can be analyzed for peaks and/or valleys which can then be used to determine a threshold value. The Histogram analysis shows that the improved local binary pattern contains more pixel count than the other one. So it can extract large amount of information.

Keywords


Mammogram, Thresholding, Benign, Malignant.