Non Destructive Testing (NDT) is an analysis technique used to inspect metal sheets and components without harming the product. NDT do not cause any change after inspection; this technique saves money and time in product evaluation, research and troubleshooting. In this study the objective is to perform NDT using soft computing techniques. Digital images are taken; Gray Level Co-occurrence Matrix (GLCM) extracts features from these images. Extracted features are then fed into the classifiers which classifies them into images with and without cracks. Three major classifiers: Neural networks, Support Vector Machine (SVM) and Linear classifiers are taken for the classification purpose. Performances of these classifiers are assessed and the best classifier for the given data is chosen.