Dataset of Spoilt Banknotes of India (Rupees)

Published: 16 December 2022| Version 1 | DOI: 10.17632/jh6979fg2t.1
Vidula Meshram,
Kailas PATIL,
Vishal Meshram


Accurate Currency recognition and classification is one of the challenging tasks for visually impaired people. As the damaged banknotes are not accepted by vendors while doing financial transactions, thus it is necessary to classify between spoilt and unspoilt banknotes. With this objective we have created the Spoilt Indian (Rupees) bank-notes dataset. This dataset consists of total 2240 (1120 old banknotes and 1120 new banknotes) high quality images. Mobile phones rear camera was used to take the images of spoilt Indian banknotes. The bank-note dataset consists of 8 classes namely Spoilt10 New, Spoilt10 Old, Spoilt20 New, Spoilt20 Old, Spoilt50 New, Spoilt50 Old, Spoilt100 New, and Spoilt100 Old. The banknote images which were soiled, mutated, holed, torn were considered for dataset creation. The images were taken in dark and illuminated backgrounds as well in the cluttered background.



Computer Vision, Machine Learning, Image Classification, Convolutional Neural Network, Deep Learning