Robust Head Pose Estimation Using Contourlet Transform
محل انتشار: بیست و یکمین کنفرانس مهندسی برق ایران
سال انتشار: 1392
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,079
فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE21_452
تاریخ نمایه سازی: 27 مرداد 1392
چکیده مقاله:
Head pose estimation is an important pre-processing step in many pattern recognition and computer vision systems such as face recognition. Since the performance of facerecognition systems is greatly affected by the pose of the face, how to estimate the accurate pose of the face is still achallenging problem. In this paper, we present a novel method for head pose estimation. To enhance the efficiency of the estimation, we first use contourlet transform for featureextraction which is a multi-resolution, multi-directional transform. In order to reduce the feature space dimension andobtain appropriate features, principal component analysis (PCA) and linear discriminant analysis (LDA) are used to remove inefficient features. Then, K-nearest neighbor (KNN)and minimum distance classifiers are applied separately to classify the pose of head. We use the public available FERETdatabase to evaluate the performance of the proposed method. Simulation results indicate the efficiency of the proposed method in comparison with previous methods
کلیدواژه ها:
نویسندگان
Mohammad Tofighi
Department of Electrical Engineering, Urmia University, Urmia, Iran