Being a densely populated country with limited natural resources, Bangladesh is deadly suffering from the energy crisis since the past few decades. The geographical location of the country has even made it more vulnerable to the natural disasters. As a result, the country is experiencing the impact of current weather change and the economy is struggling to improve against the periodic occurrence of natural calamities such as cyclones, floods and drought. In spite of being in the row of least carbon producers, Bangladesh is one of the worst sufferers. Due to the limitation in fossil fuel reserve, the only way to minimize the supply-demand gaps in the energy sector is switching towards the alternative renewable energy sources. The initiatives in sourcing out alternative energy resources with low carbon emission from both the government and the private investors are still on the infancy stages. Local investors have started the initiations to switch towards renewable energy systems. There have been some remarkable achievements as the rural people have started using these green energy systems. Government has already taken necessary steps to energize the local economy through inspiring them by low interest loan schemes, and introducing the energy usage in the government owned offices. The renewable energy system is showing a lot of promise in Bangladesh, with the proper technical support and large-scale production Bangladesh will be one of the world leaders in adaptation of renewable energy system.
This paper evaluates and compares the performance of K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Sparse Representation Classifier (SRC) for recognition of isolated Arabic handwritten characters. The proposed framework converts the gray-scale character image to a binary image through Otsu thresholding, and size-normalizes the binary image for feature extraction. Next, we exploit image down-sampling and the histogram of image gradients as features for image classification and apply fusion (combination) of these features to improve the recognition accuracy. The performance of the proposed system is evaluated on Isolated Farsi/Arabic Handwritten Character Database (IFHCDB) – a large dataset containing gray scale character images. Experimental results reveal that the histogram of gradient consistently outperforms down-sampling based features, and the fusion of these two feature sets achieves the best performance. Likewise, SRC and SVM both outperform KNN, with the latter performing the best among the three. Finally, we achieved a commanding accuracy of 93.71% in character recognition with fusion of features classified by SVM, where 92.06% and 91.10% is achieved by SRC and KNN respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.