A Fusion Approach Based on HOG and Adaboost Algorithm for Face Detection under Low-

The international arab journal of information technology

article

Farhad Navabifar¹  Mehran Emadi¹ 

[1] Department of Electrical Engineering, Mobarakeh branch, Islamic Azad University

关键词: Face detection;    cascade adaboost;    histogram of oriented gradients;    low-resolution image;   

DOI  :  10.34028/iajit/19/5/4

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

Detecting human faces in low-resolution images is more difficult than high quality images because people appearsmaller and facial features are not as clear as high resolution face images. Furthermore, the regions of interest are oftenimpoverished or blurred due to the large distance between the camera and the objects which can decrease detection rate andincrease false alarms. As a result, the performance of face detection (detection rate and the number of false positives) in low- resolution images can affect directly subsequent applications such as face recognition or face tracking. In this paper, a novelmethod, based on cascade Adaboost and Histogram of Oriented Gradients (HOG), is proposed to improve face detectionperformance in low resolution images, while most of researches have been done and tested on high quality images. The focusof this work is to improve the performance of face detection by increasing the detection rate and at the same time decreasingthe number of false alarms. The concept behind the proposed combination is based on the a-priori rejection of false positivesfor a more accurate detection. In other words in order to increase human face detection performance, the first stage (cascadeAdaboost) removes the majority of the false alarms while keeping the detection rate high, however many false alarms still existin the final output. To remove existing false alarms, a stage (HOG+SVM) is added to the first stage to act as a verificationmodule for more accurate detection. The method has been extensively tested on the Carnegie Melon University (CMU)database and the low-resolution images database. The results show better performance compared with existing techniques.

【 授权许可】

Unknown