If I want to perform quality inspection of ceramic tiles then what is the better technique in computer vision to find out the surface defects on the tiles
I believe you can sample the surface into blocks, then find the Principal Component Analysis (PCA) for each undeformed block and the PCA for a test block.
Then a supervised leaning technique such as back propagation neural network (BPNN) or Support Vector Machines (SVM) can be trained using the extracted PCAs features. An information fusion technique at the decision level can be used to decide if the whole surface is deformed or not.
Another approach is to match the Histogram of gradients(HOG) or SIFT features of an undeformed surface (template) with the test surface.
Hope texture analysis with different techniques(wavelets, PCA, etc ) along with different classifiers will be helpful. Feature extraction like color and pattern will be also useful.