Face Alignment Using Active Shape Model And Support Vector Machine

The Active Shape Model (ASM) is one of the most popular local texture modelsfor face alignment. It applies in many fields such as locating facial features in theimage, face synthesis, etc. However, the experimental results show that theaccuracy of the classical ASM for some applications is not high. This papersuggests some improvements on the classical ASM to increase the performanceof the model in the application: face alignment. Four of our major improvementsinclude: i) building a model combining Sobel filter and the 2-D profile in searchingface in image; ii) applying Canny algorithm for the enhancement edge on image;iii) Support Vector Machine (SVM) is used to classify landmarks on face, in orderto determine exactly location of these landmarks support for ASM; iv)automatically adjust 2-D profile in the multi-level model based on the size of theinput image. The experimental results on Caltech face database and TechnicalUniversity of Denmark database (imm_face) show that our proposedimprovement leads to far better performance.