The Teeth Occlusal View Image Recognition Using Extended HDM
Xitao Zheng, Yongwei Zhang, Kun Yang, Haitao Xiao · 2012
This paper presents the image recognition results using the proposed HDM (Hybrid Differential Method) and its derivative analysis extension. The derivative distribution of HDM data is processed to get the point symmetric feature and then to find the match point. To deal with the searching of an image features from other images, the feature selection and easy acquisition should be the key to make the method practicable. Using HDM derivative extension, feature extraction and processing are simultaneous so the target image can be any of that size. 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. The HDM approach is proved to be useful in searching 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.