Comparison between HDM and PCA in teeth image recognition

摘要

This paper presents the image recognition comparison between the proposed HDM (Hybrid Differential Method) and the commonly accepted PCA method. Both methods are applied to search a specific image from a bigger target picture. The results show that HDM has multiple advantages over PCA 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 proposed and will be used in the dental decision making software to do preliminary dental advising for potential patients. An image of a molar was used as an example in the paper, images are intentionally modified to test adaptability in proposed scenarios. All calculations are finished using Matlab toolbox.