Indian Sign Language (ISL) is used by the deaf and hard-of-hearing community in India and it has its own vocabulary, grammar, gesture and syntax. The language evolved in the late nineteenth century and is recognized by deaf community teachers and researchers. This language is hard to be understood by normal people as it involves manual hand gesture movements and thus an interpreter is required to make communication possible between normal people and hard-of-hearing people. In recent years researchers and developers have made efforts to develop a system for the translation and recognition of Indian Sign Language using different computing technologies that have the potential to improve accessibility and communication for the deaf community in India. As we know that Hindi is the common language to be used by the people in India, we have captured the static gesture dataset of Hindi vowels from varied age groups i.e., from kids, adults and senior adults. Every sign language is unique in itself as per the region concerned. Unlike American Sign Language, Indian Sign Language makes use of both hands for signing which increases more complexity of interpretation because of the occlusion of fingers and hands. However considering all these challenges we have developed a state-of-art method in this paper using a deep learning technique i.e., You Only Look Once (YOLO) to interpret the static Indian Sign Language gestures of Hindi Vowels and have attained an accuracy of 94.60% with good precision and recall values.