Learn More
A multi-exposure and multi-focus image fusion algorithm is proposed. The algorithm is developed for color images and is based on blending the gradients of the luminance components of the input images using the maximum gradient magnitude at each pixel location and then obtaining the fused luminance using a Haar wavelet-based image reconstruction technique.(More)
Keywords: Feature selection Feature weighting Evolutionary multi-objective optimization MOEA/D Inter-and intra-class distances a b s t r a c t Selection of feature subset is a preprocessing step in computational learning, and it serves several purposes like reducing the dimensionality of a dataset, decreasing the computational time required for(More)
Recent efforts in computer vision consider joint scene and object classification by exploiting mutual relationships (often termed as context) between them to achieve higher accuracy. On the other hand, there is also a lot of interest in online adaptation of recognition models as new data becomes available. In this paper, we address the problem of how models(More)
The huge amount of time required to construct a set of labeled images to train a classifier has led researchers to develop algorithms which can identify the most informative training images, such that labelling those will be sufficient to achieve a considerable classification accuracy. In this paper we focus on choosing a subset of the most informative and(More)
RGB-D camera not only provides color images, but also provide depth of each pixel in the image, thus serving as a rich source of information for several robotics and computer vision tasks. This project develops a system to estimate the 6-DoF ego-motion of a camera using only RGBD images as input. A frame by frame approach is employed to detect the motion of(More)
• Active Learning of Recognition Models by Exploiting Contextual Relationships in Data: We are developing algorithms to learn recognition models using less data without compromising performance by exploiting contextual relationships occurring in various computer vision and pattern recognition tasks. Advisor: Prof. Panajotis Agathoklis • Fusion of(More)