Deep Learning Approach Combining Lightweight CNN Architecture with Transfer Learning: An Automatic Approach for the Detection and Recognition of Bangladeshi Banknotes
This technology provides an automatic banknote detection and recognition solution for people with visual difficulties and for banks to efficiently manage paper currencies, offering an incremental improvement in a specific domain.
This paper addresses the problem of automatic detection and recognition of Bangladeshi banknotes using lightweight Convolutional Neural Network (CNN) architectures combined with transfer learning. The authors achieved a maximum test accuracy of 98.88% on an 8000-image dataset using MobileNet, 100% on a 1970-image dataset using NASNetMobile, and 97.77% on a combined 9970-image dataset using MobileNet.
Automatic detection and recognition of banknotes can be a very useful technology for people with visual difficulties and also for the banks itself by providing efficient management for handling different paper currencies. Lightweight models can easily be integrated into any handy IoT based gadgets/devices. This article presents our experiments on several state-of-the-art deep learning methods based on Lightweight Convolutional Neural Network architectures combining with transfer learning. ResNet152v2, MobileNet, and NASNetMobile were used as the base models with two different datasets containing Bangladeshi banknote images. The Bangla Currency dataset has 8000 Bangladeshi banknote images where the Bangla Money dataset consists of 1970 images. The performances of the models were measured using both the datasets and the combination of the two datasets. In order to achieve maximum efficiency, we used various augmentations, hyperparameter tuning, and optimizations techniques. We have achieved maximum test accuracy of 98.88\% on 8000 images dataset using MobileNet, 100\% on the 1970 images dataset using NASNetMobile, and 97.77\% on the combined dataset (9970 images) using MobileNet.