Dataset of Indian and Thai banknotes with annotations.

Researchers

Journal

Modalities

Models

Abstract

Multinational banknote detection in real time environment is the open research problem for the research community. Several studies have been conducted for providing solution for fast and accurate recognition of banknotes, detection of counterfeit banknotes, and identification of damaged banknotes. The State-of art techniques like machine learning (ML) and deep learning (DL) are dominating the traditional methods of digital image processing technique used for banknote classification. The success of the ML or DL projects heavily depends on size and comprehensiveness of dataset used. The available datasets have the following limitations:  1. The size of existing Indian dataset is insufficient to train ML or DL projects [1], [2].  2. The existing dataset fail to cover all denomination classes [1].  3. The existing dataset does not consists of latest denomination [3].  4. As per the literature survey there is no public open access dataset is available for Thai banknotes. To overcome all these limitations we have created a total 3000 image dataset of Indian and Thai banknotes which include 2000 images of Indian banknotes and 1000 images of Thai banknotes. Indian banknotes consist of old and new banknotes of 10, 20, 50, 100, 200, 500 and 2000 rupees and Thai banknotes consist of 20, 50, 100, 500 and 1000 Baht.© 2022 The Author(s). Published by Elsevier Inc.