期刊名称：International Journal of Environment and Geoinformatics
电子版ISSN：2148-9173
出版年度：2017
卷号：4
期号：2
页码：116-127
DOI：10.30897/ijegeo.312635
语种：English
出版社：IJEGEO
摘要：The human faceincludes different colors and forms due to its complexity. Therefore, facialimage processing comprises even more problems than image processing of otherobjects. Interest point detection is one of the important problems in computervision, which is the key aspect of solving problems such as facial expressionanalysis, age analysis, sex defining, facial recognition, and three-dimensionalface modelling in augmented reality. To accomplish these tasks, facial interestpoints need automatic definition. A hybrid algorithm was developed to detectautomatically interest regions and points in multiple images in the resentedstudy. The study used processed facial images from an authorized image databasewith a resolution of 1600 x 1200, taken in standardized illumination conditionsby using an InSpeck Mega Capturor II optical 3D structured light digitizer and1000-W halogen lamp. The presented study integrated skin color analysis withthe Haar classification method, processing 11 male and 25 female facial imageswith the developed algorithm. The average accuracy of facial interest pointdetection was 0.68 mm after testing all images.
关键词：Close-range photogrammetry; face recognition and facial interest points; image matching and processing
