Development of Real-Time Face Detection Architecture for Household Robot Applications

Autor:	Dongil Han, Jaekwang Song, Seong Joon Yoo, Hyeonjoon Moon, Hyunjong Cho
Rok vydání:	2009
Předmět:	Hardware architecture business.industry Computer science Detector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Overlay Frame rate Face (geometry) Robot Computer vision Artificial intelligence Field-programmable gate array Face detection business
Zdroj:	Universal Access in Human-Computer Interaction. Intelligent and Ubiquitous Interaction Environments ISBN: 9783642027093 HCI (6)
DOI:	10.1007/978-3-642-02710-9_7
Popis:	This paper describes the structure of real-time face detection hardware architecture for household robot applications. The proposed architecture is robust against illumination changes and operates at no less than 60 frames per second. It uses Modified Census Transform to obtain face characteristics robust against illumination changes. And the AdaBoost algorithm is adopted to learn and generate the characteristics of the face data, and finally detected the face using this data. This paper describes the hardware structure composed of Memory Interface, Image Scaler, MCT Generator, Candidate Detector, Confidence Mapper, Position Resizer, Data Grouper, and Overlay Processor, and then verified it using Virtex5 LX330 FPGA of Xilinx. Verification using the images from a camera showed that maximum 16 faces can be detected at the speed of maximum 30.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a2d3796026a391b15ca25e88f751f610 https://doi.org/10.1007/978-3-642-02710-9_7 Zobrazit plný text záznamu