Artificial intelligence inspired fog-cloud-based visual-assistance framework for blind and visually-impaired people

Interpreting their surroundings has always been challenging for Blind and Visually Impaired People (BVIP). People with visual impairment have difficulty evaluating how their surroundings are perceived. An intriguing approach for helping persons with visual impairments interpret their environment is the description of images. These BVIPs to some extent, are unable to relate to any items they encounter, including nearby automobiles as well as persons. However, a proper descriptive elucidation will help them better perceive their surroundings. This paper presents an artificial intelligence-inspired fog-cloud-based framework for generating expository interpretations from images captured by BVIP. This framework will aid them to comprehend their surroundings and function more comfortably. For the benefit of those with Achromatopsia, the proposed system additionally employs an edge-sharpening method. For the generation of image captions, we used a text-to-speech module and an image captioning algorithm. Additionally, to make it easier for patients with achromatopsia to comprehend, we employ an edge detection technique to identify the edges of an image and enhance the edges. The effectiveness as well as the performance of the proposed framework is compared with other state-of-the-art methods. The findings show that the suggested framework performs better than all other techniques taken into consideration and achieves a greater accuracy of 96.84%. This framework will assist blind persons in receiving a spoken exploratory description of their surroundings, as well as Achromatopsia sufferers in receiving edge-sharpened images that can be readily comprehended. BVIP can carry out their daily tasks with ease with the help of this framework.