Visually Impaired People Face A Number Of Challenges When Interacting With The Environments Because So Much Information Is Encoded Visually In Daily Life. One Specific Difficulty That A Blind Person Would Encounter Is To Know The Value Of The Currency Or Bill He Or She Is Holding. In This Paper, We Propose A Novel Component-based Banknote Recognition System By Using SURF Features To Achieve High Recognition Accuracy And To Handle Various Challenging Conditions In Real-world Environments. Patches With Descriptive Features For Each Banknote Category Are Selected As Reference Regions To Match With Query Images. The Proposed Algorithm Has Been Evaluated By Dataset To A Variety Of Conditions Including Occlusion, Rotation, Scaling, Cluttered Background, Illumination Change, Viewpoint Variation, And Worn Or Wrinkled Bills, And Further By Blind Subjects.
