Md. Abul Hasnat

Learn More
Research on automatic speech recognition has been approach progressively since 1930 and the major advances are since 1980 with the introduction of the statistical modeling of speech with the key technology Hidden Markov Model (HMM) and the stochastic language model (B. H. Juang, 2005). However, the existing reported research works on Bangla speech(More)
Recent advances in depth imaging sensors provide easy access to the synchronized depth with color, called RGB-D image. In this paper, we propose an unsupervised method for indoor RGB-D image segmentation and analysis. We consider a statistical image generation model based on the color and geometry of the scene. Our method consists of a joint(More)
Recent advances in imaging sensors, such as Kinect, provide access to the synchronized depth with color, called RGB-D image. Numerous researches [2, 4] have shown that the use of depth as an additional feature improves accuracy of scene segmentation. However, it remains an important issue what is the best way to fuse color and geometry in an unsupervised(More)
BanglaOCR is currently the only open source optical character recognition (OCR) software for the Bangla (Bengali) script developed by the Center for Research on Bangla Language Processing (CRBLP). Tesseract, maintained by Google, is considered to be one of the most accurate free open source OCR engines currently available. In this paper, we present a new(More)
Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on(More)
In this paper, we propose an unsupervised clustering method for axially symmetric directional unit vectors. Our method exploits the Watson distribution and Bregman Divergence within a Model Based Clustering framework. The main objectives of our method are: (a) provide efficient solution to estimate the parameters of a Watson Mixture Model (WMM), (b)(More)
A number of pattern recognition tasks, e.g., face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the von Mises-Fisher (vMF) mixture model as the theoretical foundation for an effective deep-learning of such directional(More)