NATURAL DISASTER AID SYSTEM USING IMAGE PROCESSING

Abstract

Natural Disasters sometime come with terrible consequences where those affected are subjected to depreciation of even the basic needs, be it connectivity using roads, be it electricity or be it water. The list has no end. All this takes toll especially on the victims of the disaster with lack of above stated essentials makes the reaching of help difficult.Many times vehicles also get damaged due to damaged and unmotorable roads.The proposed work acts as a single control unit for all solutions, bringing all the recovery control system under one umbrella, facilitating quick response to the disaster and recovery system. The web application has two modules, one for the user end and other for the administrator end. It always strives to bring all the possible means for the same under single umbrella. Methodologies used include IBM Watson for image processing, TensorFlow for training model, and Anaconda for package management and deployment and HTML, CSS, JavaScript, JQuery and PHP for Web based GUI. With an everlasting desire to attain perfection, we are trying to expand our sphere. The goal set involves bringing of financial aid, in collaboration with the banks and also food supplies from local vendors for the victims, in near future, along with solving the above mentioned problems. As a subcategory or field of digital signal processing, digital image processing has many advantages over analog image processing. It allows a much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and distortion during processing. Since images are defined over two dimensions (perhaps more) digital image processing may be modeled in the form of multidimensional systems. The IBM Watson Visual Recognition service uses deep learning algorithms to analyze images for scenes, objects, and other content. The response includes keywords that provide information about the content. Keywords: Natural Disaster,Digital image processing,Noise and distortion,IBM Watson,Deep Learning,Vehicle damage