Paper Details

There are approximately 315 million people with visual imparity worldwide. The number of thesepeople is also increasing as this generation ages. Recent development in computer vision, digital cameras, andportable computers make it possible to assist these people by developing camera-based products that incorporatecomputer vision technology. We propose a camera-based object recognition application to help visually impairedpeople to recognize labeled and unlabelled hand held objects in their daily lives. To differentiate the object fromcomplex backgrounds or other surrounding objects in the camera view, we first propose a motion based method todefine a region of interest (ROI) in the image by asking the user to hold the object which is efficient and effective.Reference objects and test images are accompanied by local features (regions, interest points, etc.). If the test imageget match with reference image then the output signal created in the form of audio. Output audio is generated andsent towards head-phone through which the blind user could hear the information about the product which is heldon hand. In this proposed system we use speeded up robust features (SURF) for tasks such as object recognition,classification or 3D reconstruction, image registration.

Ankit Dongre, Dhruv Purandare, Jimil Gandhi, Suchit Adak, “Real Time Detection and Recognition of Hand Held Objects to Assist Blind People”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 16, pp. -, January 2017.