Deep Learning Approach Combining Lightweight CNN Architecture with Transfer Learning: An Automatic Approach for the Detection and Recognition of Bangladeshi Banknotes

@article{Linkon2020DeepLA,
  title={Deep Learning Approach Combining Lightweight CNN Architecture with Transfer Learning: An Automatic Approach for the Detection and Recognition of Bangladeshi Banknotes},
  author={Ali Hasan Md. Linkon and Md. Mahir Labib and Faisal Haque Bappy and Soumik Sarker and Marium-E. Jannat and Md. Saiful Islam},
  journal={2020 11th International Conference on Electrical and Computer Engineering (ICECE)},
  year={2020},
  pages={214-217}
}
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… 

Figures and Tables from this paper

Efficacy of the Image Augmentation Method using CNN Transfer Learning in Identification of Timber Defect

The experimental findings suggest that the proposed methods improved CNN algorithms classification performance in identification of timber defect while tackling the imbalanced and limited dataset challenges.

Bangladeshi Paper Currency Recognition Using Lightweight CNN Architectures

This paper aims to identify different banknotes of Bangladesh using the avant-garde convolutional neural network (CNN) models with transfer learning by utilizing the dataset at hand and updating and augmenting the dataset.

References

SHOWING 1-10 OF 13 REFERENCES

Learning Transferable Architectures for Scalable Image Recognition

This paper proposes to search for an architectural building block on a small dataset and then transfer the block to a larger dataset and introduces a new regularization technique called ScheduledDropPath that significantly improves generalization in the NASNet models.

Indian Banknote Recognition using Convolutional Neural Network

  • Shubham MittalShiva Mittal
  • Computer Science
    2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU)
  • 2018
Experimental results prove the retrained lightweight model achieves an accuracy of 96.6 % on a held out testing subset, and proves it to be employable for development of dedicated portable systems for identification of banknote denominations.

Vision Based System for Banknote Recognition Using Different Machine Learning and Deep Learning Approach

It can be concluded that AlexNet can only perform great in testing new data if only the data had previously been trained with similar orientation, and Orientation does give effect to the performance of AlexNet model.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Developing a bangla currency recognizer for visually impaired people

A camera-based automatic currency recognizer for Bangladeshi bank notes that assists visually impaired people in Bangladesh is developed and validated and shows that the proposed system is robust and highly effective with heterogeneous environment.

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

Bangladeshi banknote recognition by neural network with axis symmetrical masks

  • N. JahangirA. Chowdhury
  • Computer Science
    2007 10th international conference on computer and information technology
  • 2007
Experimental results show that this Neural Network based recognition scheme for Bangladeshi banknotes can recognize currently available 8 notes successfully with an average accuracy of 98.57%.

Mobile-Based Indian Currency Detection Model for the Visually Impaired

The proposed model is using image processing for feature extraction and a basic CNN (convolutional neural network) for identification of currency with the given feature inputs and is being made into a mobile-based application so as to enable a visually impaired person to check for any possible frauds as fast as possible.

Recognizing Bangladeshi Currency for Visually Impaired

A system able to analyze an input frame and generate the value of the paper-based currency in order to aid the visually impaired in their day-to-day life is developed.

Bangla Money. [online] Kaggle.com

  • Available at: https://www.kaggle.com/nsojib/bangla-money [Accessed
  • 2020