专利名称：System and method for face detection using
candidate image region selection
发明人：Renato Kresch申请号：US09229052申请日：19990111公开号：US06463163B1公开日：20021008
专利附图：
摘要：A face detection system and a method of pre-filtering an input image for facedetection utilize a candidate selector that selects candidate regions of the input imagethat potentially contains a picture of a human face. The candidate selector operates in
conjunction with an associated face detector that verifies whether the candidate regionscontain a human face. In the preferred embodiment, the candidate selector includes alinear matched filter and a non-linear filter that operate in series to select the candidateregions from the input image. Initially, the linear matched filter performs a linearcorrelation on the input image using a filtering kernel to derive a correlation image. Thelinear matched filter selects regions of the input image that have a local maximum in thecorrelation image and have correlation values greater than a threshold correlation value.Preferably, the linear correlation is performed in the discrete cosine transform (DCT)domain. The non-linear filter then examines contrast values from various sub-regions ofthe image regions that were selected by the linear matched filter to screen for suitablecandidate regions. The filtering kernel used by the linear matched filter is calculatedduring a training period, or a non-face detecting period, by a filtering-kernel generator.The filtering kernel is preferably computed utilizing a database of training face imagesthat have been averaged and then masked to remove DC, illumination and noisecomponents.
申请人：HEWLETT-PACKARD COMPANY
更多信息请下载全文后查看
因篇幅问题不能全部显示，请点此查看更多更全内容