• deava

Object recognition by the blind people often requires a manual intervention more which is more difficult to perform. In this proposed design, automated prediction of objects has been implemented to enhance the visually impaired people communication. In order to solve the common aiming problem for blind users, a motion-based method to detect the object of interest is projected, while the blind user simply shakes the object for a couple of seconds. This method can effectively distinguish the object of interest from background or other objects in the camera view. Localized text regions are transformed into audio output for blind users. The audio output component is to inform the blind user of recognized text codes. In order to solve the common problem for blind users, we proposed a motion based technique to detect the object of interest, while the blind user simply shakes the object for few seconds. This method can effectively distinguish the object of interest from background or other objects in the camera vision. To extract text regions from complex backgrounds, we have proposed a “Haar Cascade Classifier Algorithm” text localization algorithm the corresponding feature maps estimate the global structural feature of text at every pixel Key words: Blindness, assistive devices, text reading, hand-held objects, text region localization, stroke orientation, distribution of edge pixels, OCR.

Key words: Blindness, assistive devices, text reading, hand-held objects, text region localization, stroke orientation, distribution of edge pixels, OCR.

"MOTION BASED OBJECT DETECTION METHOD FOR VISUALLY IMPARIED PEOPLE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.112-118, December-2018, Available :http://www.jetir.org/papers/JETIR1812816.pdf

"MOTION BASED OBJECT DETECTION METHOD FOR VISUALLY IMPARIED PEOPLE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp112-118, December-2018, Available at : http://www.jetir.org/papers/JETIR1812816.pdf