Deconstructing image semantics in natural language representation

Image - in today's digital world represented by numerical numbers. These numbers collectively present abstract concepts that is only understood by human perception. In this paper, we propose a novel framework that is more close to human perception of reality to translate the conventional representation of an image. Also, we focus on automating the image representation in terms of a natural language description both understandable by human and machine. The proposed framework can be extended to use a wide variety of real world applications in future.