Augmenting the SIFT Descriptor Set to Create a Navigation Assistant for the Visually Impaired
Vineet Kosaraju1, Rishabh Jain2
1Vineet Kosaraju, The Harker School, San Jose, California, USA.
2Rishabh Jain, The Harker School, San Jose, California, USA.
Manuscript received on March 02, 2014. | Revised Manuscript received on March 03, 2014. | Manuscript published on March 05, 2014. | PP: 95-100 | Volume-4 Issue-1, March 2014. | Retrieval Number: A2088034114/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The issue of mobility is considered among the foremost of concerns for visually impaired individuals. This work develops a Navigation Assistant that aids the visually impaired with mobility in a known environment such as a household, by combining the principles behind Scale-Invariant Feature Transform (SIFT) and Content-Based Image Retrieval (CBIR). Furthermore, this work proposes and tests several techniques such as Color Segmentation, Difference of Images, and Contrast Manipulation to improve the Navigation Assistant. Using a video stream that was obtained from a small camera that the user carries, key objects in the household were identified using the software developed. The Navigation Assistant created using the enhancements was markedly improved in both accuracy and speed from the control Assistant, and is therefore applicable to real-life usage by visually impaired individuals.
Keywords: CBIR, SIFT, Color Segmentation, Difference of Images.