Authors: P. Bhuvaneswari; A. Brintha Therese
Addresses: School of Electronics Engineering, VIT University, Chennai Campus, Vandalur, Chennai-600127, India; Department of ECE, Rajarajeswari College of Engineering, Bangalore-560074, India ' School of Electronics Engineering, VIT University, Chennai Campus, Vandalur, Chennai-600127, India
Abstract: Chronic obstructive pulmonary disease (COPD) is a group of lung disease like emphysema, chronic bronchitis, asthma and some kinds of bronchiectasis. This group of diseases are expected to be one of the major causes of morbidility and the third case of mortality by 2020. If the disease is identified in the early stage itself the survival rate will be increased. In this paper a novel method is proposed to classify the disease COPD in chest X-ray images. Prior to classification essential features are to be extracted. In this regards, some structural features include number of ribs in the chest X-ray, heart shape, diaphragm shape and distance between ribs of the given X-ray image are extracted by means of various image processing techniques. Based on the above said features the input image is classified as normal or COPD with various classifiers include MLC, LDA, neural network, genetic algorithm. The maximum classification accuracy achieved is 97.9%. This work not only ends up with the classification of COPD images, it also enables the medicos to identify the heart disease cardiomegaly.
Keywords: adaptive histogram equalisation; Zernike moments; classification; neural network; genetic algorithm; feature extraction.
International Journal of Computer Aided Engineering and Technology, 2020 Vol.12 No.3, pp.301 - 317
Received: 30 Aug 2017
Accepted: 23 Oct 2017
Published online: 05 Mar 2020 *