Answers are grounded in this paper and cite their sources.
This paper aims to create visibility for visually impaired people or atleast to create ability for them to get the details of content which could be visible to the normal pair of eyes.System enables visually impaired users to leverage the camera of a mobile device to accurately recognize currency bills even if the images are partially or highly distorted.Once the face value of the currency bill is recognized, the mobile phone announces the denomination value of the bill.A captured sub image is matched across the definite set of bills in the knowledge base.The proposed method was experimented with manually created database containing 56 denominations of both newer and older bills for the knowledgebase or training.Moreover 560 randomly chosen partial images are acquired from all the denominations, which also include newer as well as older bills.The overall accuracy rate achieves 87% when all the bills are taken into consideration.100% accuracy rate was achieved when using only newer bills for comparison.
No takes yet. Share an insight, caveat, or question.
Amarnath et al. (2019) studied this question.
Synapse has enriched 4 related papers. Consider them for comparative context: