Description

Lung X-ray images were used for the identification of the tuberculosis in the persons. The regions affected by tuberculosis are different in intensity compared with other regions. The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. Chest radiographs account for more than half of all radiological examinations; the chest is the “mirror of health and disease”. This thesis is about techniques for computer analysis of chest radiographs. It describes methods for texture analysis and segmenting the lung fields and rib cage in a chest film. It includes a description of an automatic system for detecting regions with abnormal texture that is applied to a database of images from a tuberculosis screening program. The input images were divided into patches. The features were extracted from the patches based on the statistical measures. The extracted features were then classified using mi-SVM classification algorithm. The score value for the abnormality in the input images was measured. The performance of the process is measured in terms of accuracy of the process.