Paper Details: Downloads: 481
Serial Number: P1151053407
Title: Auto Detection of Tubercle Bacilli Based on Wavelets
Authors: S.Kezia and V.Vijaya Kumar and I.Shanti Prabha
Abstract: Tuberculosis (TB) is one of the deadliest diseases in the world. One problem in processing fluorescent Tubercle bacilli images is the presence of speckle noise which is multiplicative and is a major limitation on image quality. The effect of speckle noise can be reduced by a quality of segmentation. For this the present paper proposes a new segmentation technique, based on wavelet transforms, morphological operations and edge operators. To shade the surrounding particles and to enhance the brightness of the bacilli of the image, morphological transforms are used prior to the segmentation. This improves the quality of the proposed segmentation scheme in detecting edges of the bacilli even in the presence of speckle noise. The experimental result indicates the efficiency of the proposed method in the presence of high speckle noise.
Keywords: Speckle noise, image quality, edges of bacilli, edge operators.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 11
Issue: 3
Submission Date: 12/29/2010 12:00:00 AM
Review Date: 2/12/2011 12:00:00 AM
Publishing Date: 4/1/2011 12:00:00 AM
Article Downloads: 481
Download:

Facebook