Overview / Usage

Vision being an important sensory input for any system, being able to process images effectively is of high importance in current days. Captioning images means processing the images to understand what is happening in the image. Being able to automatically generate captions for images would enable us to process huge amount of data available in current generation for striving towards a better society. It would potentially reduce human intervention in many redundant tasks in the fields like security, search operations, etc., and could help in enhancing the experience of self-driving cars, enabling to understand the scene better in front of the vehicle.
For the execution of this project, I forsee to use the Intel optimized Deep Learning Frameworks like Caffe, TensowFlow and optimize code for Intel Architecture.