Real-Time Bangladeshi Currency Recognition Using Faster R-CNN Approach for Visually Impaired People

Islam, Md. Tobibul; Ahmad, Mohiuddin; Bappy, Akash Shingha

doi:10.1007/978-981-16-1089-9_13

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance on unseen currency data is comparable to models trained exclusively on a single currency, such as [10][11][12]18].…”

Section: Leave-currency-out Cross Validationmentioning

confidence: 95%

“…Machine learning (ML) is often applied for this task. Several ML models have been develop for particular currencies [21], including Indian Rupee [12,19,27,28], US dollar [7,9,18], Canadian dollar [18], Euro [20], Bangladesh Taka [11], Thailand Baht [25], Egyptian Pound [23], Pakistan Rupee [10], among others [21]. The techniques employed in previous works include both classical computer vision and machine learning approaches, such as LDA [19], feature transformations and template-matching [7,20,23], support vector machines [27], and modern deep learning approaches [10,11,25,28].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BankNote-Net: Open dataset for assistive universal currency recognition

Oviedo¹,

Vinnakota²,

Seleznev³

et al. 2022

Preprint

View full text Add to dashboard Cite

Millions of people around the world have low or no vision. Assistive software applications have been developed for a variety of day-to-day tasks, including optical character recognition, scene identification, person recognition, and currency recognition. This last task, the recognition of banknotes from different denominations, has been addressed by the use of computer vision models for image recognition. However, the datasets and models available for this task are limited, both in terms of dataset size and in variety of currencies covered. In this work, we collect a total of 24,826 images of banknotes in variety of assistive settings, spanning 17 currencies and 112 denominations. Using supervised contrastive learning, we develop a machine learning model for universal currency recognition. This model learns compliant embeddings of banknote images in a variety of contexts, which can be shared publicly (as a highly-compressed vector representation), and can be used to train and test specialized downstream models for any currency, including those not covered by our dataset or for which only a few real images per denomination are available (few-shot learning). We deploy a variation of this model for public use in the last version of the Seeing AI app developed by Microsoft. We share our encoder model and the embeddings as an open dataset in our BankNote-Net repository. CCS Concepts: • Human-centered computing → Accessibility technologies.

show abstract

“…The performance on unseen currency data is comparable to models trained exclusively on a single currency, such as [10][11][12]18].…”

Section: Leave-currency-out Cross Validationmentioning

confidence: 95%