초록

용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

In this paper, we present an implementation of automatic physiognomic analysis based on the analysis of features of facial components such as eye size, mouth size, and so on. The facial region is detected from an input image to analyze the various features of facial components. The Active Appearance...

In this paper, we present an implementation of automatic physiognomic analysis based on the analysis of features of facial components such as eye size, mouth size, and so on. The facial region is detected from an input image to analyze the various features of facial components. The Active Appearance Model (AAM) is used to extract facial feature points. From these facial feature points, 22 measurements are computed to distinguish each facial component into defined classes and the gender of a subject. The Support Vector Machine (SVM) is applied for gender and facial feature classification. After classifying facial components with each classification criterion and the gender of a subject, physiognomic information is generated by combining the classified results of each classification criterion and the gender of the subject. The experimental results demonstrate that the proposed method is an effective solution for solving the problem of facial feature analysis and generating physiognomic information of the subject.

주제어