Face image analysis method for sasang constituition diagnosis

摘要

The present invention relates to a facial image analysis method for objectively discriminating the constitution of sasang in place of subjective judgment. In the syllable structure discrimination model learning process, feature points of facial images using ASM (Active Shape Models) are extracted and normalized for sampled images to obtain feature values of the defined facial images for sagittal discrimination, and then the SVM (Support Vector Machine) Boundary is derived. In the recognition process, ASM features are extracted from the new facial images, facial features are normalized, feature values of the facial images are obtained, and the final sasang constitution result is derived using the SVM classifier generated during the learning process. The performance of the proposed method is confirmed to be 92%.;