Improved PCA & LDA-Based PersonalIdentification Method

Since PCA-Based Teeth-Image Personal Identification Method [3] and LDA-Based Teeth-Image Persona Identification Method [2] are not robust against reflection and orientation, registered persons in the database is rejected around 10%. This paper proposes a method to improve the PCA & LDA based teeth-image personal identification method. In this method, the teeth image failed from the matching in the PCA & LDA based system is reconsidered by feeding back the image to eliminate the reflection and the rotation problems. The enhanced teeth image is fed back to PCA & LDA process in order to rescue misclassified teeth-image. In the experiments, 500 teeth images are tested with 200-teeth database. The results revealed that of the 10% errors caused by the two problems, 5% are correctly identified because of the proposed method.