Reena Behera | KPIT - Academia.edu (original) (raw)
Related Authors
Graduate Center of the City University of New York
Uploads
Papers by Reena Behera
2015 International Conference on Communications and Signal Processing (ICCSP), 2015
Face detection has become a fundamental task in computer vision and pattern recognition applicati... more 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.
SAE International Journal of Passenger Cars - Electronic and Electrical Systems, 2015
SAE Technical Paper Series, 2015
2012 World Congress on Information and Communication Technologies, 2012
Procedia Computer Science, 2015
In video analytics based systems, an efficient method for segmenting foreground objects from vide... more In video analytics based systems, an efficient method for segmenting foreground objects from video frames is the need of the hour. Currently, foreground segmentation is performed by modelling background of the scene with statistical estimates and comparing them with the current scene. Such methods are not applicable for modelling the background of a moving scene, since the background changes between the scenes. The scope of this paper includes solving the problem of background modelling for applications involving moving camera. The proposed method is a non-panoramic background modelling technique that models each pixel with a single Spatio-Temporal Gaussian. Experimentation on various videos promises that the proposed method can detect foreground objects from the frames of moving camera with negligible false alarms.
2015 International Conference on Communications and Signal Processing (ICCSP), 2015
Face detection has become a fundamental task in computer vision and pattern recognition applicati... more 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.
SAE International Journal of Passenger Cars - Electronic and Electrical Systems, 2015
SAE Technical Paper Series, 2015
2012 World Congress on Information and Communication Technologies, 2012
Procedia Computer Science, 2015
In video analytics based systems, an efficient method for segmenting foreground objects from vide... more In video analytics based systems, an efficient method for segmenting foreground objects from video frames is the need of the hour. Currently, foreground segmentation is performed by modelling background of the scene with statistical estimates and comparing them with the current scene. Such methods are not applicable for modelling the background of a moving scene, since the background changes between the scenes. The scope of this paper includes solving the problem of background modelling for applications involving moving camera. The proposed method is a non-panoramic background modelling technique that models each pixel with a single Spatio-Temporal Gaussian. Experimentation on various videos promises that the proposed method can detect foreground objects from the frames of moving camera with negligible false alarms.