Proceedings of
2nd International Conference on Advances in Computing, Electronics and Electrical Technology CEET 2014
"CAPTURING FEATURES FOR HEIGHT COMPUTATION DERIVED WITH GAUSSIAN MIXTURE MODEL"
Abstract: “Height is a biometric trait which is considered as one of the important parameters for the identification of a person and nutritional status. This study generally aimed to obtain the height of a person through experimental approach utilizing computer vision. The web cam captures group of students into a single image. Canny edge detection is applied for image segmentation and Gaussian Mixture Model (GMM) for background subtraction. Segmented images were evaluated to identify the ideal number of students from a controlled environment lessening computer vision constraints. Data collected from the experiment were subjected to one-way ANOVA and T-Test to analyze the difference between prototype derived height from a captured image and actual height of the student. The prototype was developed using OpenCV library integrated to C# available in Microsoft Studio 2010”
Keywords: background subtraction, Gaussian Mixture Model, Canny Edge Detection, height derivation