The Teeth Image Recognition Using HDM and the Turn Point

This paper presents the image recognition results using the proposed HDM (Hybrid Differential Method) and its turn point. Derivative of HDM results are taken to analyse the point-symmetric feature of the match point. The results are discussed to determine creteria if the pattern match is found or not. The method is applied to search a specific image from a bigger target picture. The results show that HDM has multiple advantages over traditional method when applied to image searching, like considerably less time consumed, better recognition rate when the background or grayscale value changed. The HDM + turn point approach is proved to be useful in occlusal view of a teeth image. An image of a molar was used as an example in the paper, images are deformed to a certain grades to test the adaptability in proposed scenarios. All calculations are done using Matlab toolbox.