Face detection using data mining approach

Face detection has become a fundamental task in computer vision and pattern recognition applications. This paper describes a system for face detection using data mining approach. The proposed face detection method is a two phase process comprising of training and detection phase. In the training phase, training image is transformed into an edge and non-edge image. Maximal Frequent Itemset Algorithm (MAFIA) is used to mine positive and negative feature patterns from edge and non-edge images respectively. Based on the feature patterns mined, a face detector is constructed to prune non-face candidates. In the detection phase, sliding window approach is applied to the test image in different scales. Experimental results on FEI face database show good performance even across different orientations, pose and expression variations to a certain extent.