Analysis of breath sounds for the purpose of diagnosing respiratory pathology is of great interest in recent years. In this paper, classification of normal, wheeze, rhonchi, line and coarse crackles using breath sound signal recording is performed using signal processing and machine learning tools. Breath sounds were filtered from noise and segmented into breath cycles followed by feature extraction. AR Coefficients and Mel Frequency Cepstral Coefficients (MFCC) features were extracted from breath sound cycles. The extracted features are then classified using Support Vector Machine (SVM) classifier. A mean classification accuracy of 88.72% and 89.68% was reported for the features AR coefficients and MFCC features respectively. The individual classification accuracy for healthy (control subjects), wheeze, rhonchi, fine and coarse crackles are 93.75%, 87.50%, 91.66%, 87.50% and 91.66% respectively for the MFCC features. Similarly, the individual classification accuracy for healthy control, wheeze, rhonchi, fine and coarse crackles are 93.75%, 87.50%, 87.50%, 87.50% and 83.33% respectively for the AR coefficient features. The experimental result shows that the proposed method from an overall point of view can be considered as a reliable system to be used as a Computerized Decision Support System (CDSS).