Braille has empowered visually challenged community to read and write. But at the same time, it has created a gap due to widespread inability of non-Braille users to understand Braille scripts. This gap has fuelled researchers to propose Optical Braille Recognition techniques to convert Braille documents to natural language. The main motivation of this work is to cement the communication gap at academic institutions by translating personal documents of blind students. This has been accomplished by proposing an economical and effective technique which digitizes Braille documents using a smartphone camera. For any given Braille image, a dot detection mechanism based on Hough transform is proposed which is invariant to skewness, noise and other deterrents. The detected dots are then clustered into Braille cells using distance-based clustering algorithm. In succession, the standard physical parameters of each Braille cells are estimated for feature extraction and classification as natural language characters. The comprehensive evaluation of this technique on the proposed dataset of 54 Braille scripts has yielded into accuracy of 98.71%.
Weather conditions often disrupt the proper functioning of transportation systems. Present systems either deploy an array of sensors or use an in-vehicle camera to predict weather conditions. These solutions have resulted in incremental cost and limited scope. To ensure smooth operation of all transportation services in all-weather conditions, a reliable detection system is necessary to classify weather in wild. The challenges involved in solving this problem is that weather conditions are diverse in nature and there is an absence of discriminate features among various weather conditions. The existing works to solve this problem have been scene specific and have targeted classification of two categories of weather. In this paper, we have created a new open source dataset consisting of images depicting three classes of weather i.e rain, snow and fog called RFS Dataset. A novel algorithm has also been proposed which has used super pixel delimiting masks as a form of data augmentation, leading to reasonable results with respect to ten Convolutional Neural Network architectures.