Deep Feature-Based Three-Stage Detection of Banknotes and Coins for Assisting Visually Impaired People

Park, Chanhum; Cho, Se Woon; Baek, Na Rae; Choi, Jiho; Park, Kang Ryoung

doi:10.1109/access.2020.3029526

Cited by 25 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For fine-grained currency recognition, a CONGAS-based feature is used. Park et al [23] performed recognition of Korean won (KRW) banknotes and coins using a Faster-RCNN and VGG16 backend. Anwar et al [26] focuses on the recognition of gold and silver coinage of the historical roman era.…”

Section: ) DL Modelsmentioning

confidence: 99%

IPCRF: An End-to-End Indian Paper Currency Recognition Framework for Blind and Visually Impaired People

et al. 2022

View full text Add to dashboard Cite

Currency recognition has always been a troublesome task for blind and visually impaired people (BVIP). The problem is more severe in developing countries such as India, where there is still a lack of robust currency recognition systems. BVIP primarily relies on size variations and patterns such as intaglio printings for recognizing the underlying currency denominations. Most of the current Indian legal tenders resemble in size, thus making the identification process more strenuous. Also, the engraved patterns are not as distinctive as BVIP standards, and they fade over time. For an automated paper currency recognition system, issues such as folded or partial views, uneven illumination, and background clutter make it non-trivial and challenging. This paper ventures to present an end-to-end and robust framework for assisting BVIP in recognizing the Indian paper currency denomination. This paper presents a lightweight network, IPCRNet, useful in a resource-constrained environment such as low/medium level smartphones. The proposed network is based on Dense connection, Multi-Dilation, and Depth-wise separable convolution layers. Additionally, we congregated one of the most diversified Indian paper currency image dataset with more than 50,000 images belonging to almost all denominations in circulation. A customized and publically available android application, "Roshni-Currency recognizer", has also been introduced. The experimental results on multiple datasets demonstrate the superiority of the proposed model. IPCRNet improves the classification accuracy by more than 2% on the proposed dataset compared to the state-of-the-art networks.

show abstract

Section: ) DL Modelsmentioning

confidence: 99%

IPCRF: An End-to-End Indian Paper Currency Recognition Framework for Blind and Visually Impaired People

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We highlight these overlaps throughout to provide a useful and farreaching review of this domain and its context to other areas. 4. We highlight and clarify the range of used terminologies in the domain.…”

Section: Introductionmentioning

confidence: 99%

“…For those who suffer from vision impairment, both independence and confidence in undertaking daily activities of living are impacted. Assistive systems exist to help BVIP in various activities of daily living, such as recognizing people [ 2 ], distinguishing banknotes [ 3 , 4 ], choosing clothes [ 5 ], and navigation support, both indoors and outdoors [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

A Systematic Review of Urban Navigation Systems for Visually Impaired People

El-taher

Taha

Courtney

et al. 2021

Sensors

View full text Add to dashboard Cite

Blind and Visually impaired people (BVIP) face a range of practical difficulties when undertaking outdoor journeys as pedestrians. Over the past decade, a variety of assistive devices have been researched and developed to help BVIP navigate more safely and independently. In addition, research in overlapping domains are addressing the problem of automatic environment interpretation using computer vision and machine learning, particularly deep learning, approaches. Our aim in this article is to present a comprehensive review of research directly in, or relevant to, assistive outdoor navigation for BVIP. We breakdown the navigation area into a series of navigation phases and tasks. We then use this structure for our systematic review of research, analysing articles, methods, datasets and current limitations by task. We also provide an overview of commercial and non-commercial navigation applications targeted at BVIP. Our review contributes to the body of knowledge by providing a comprehensive, structured analysis of work in the domain, including the state of the art, and guidance on future directions. It will support both researchers and other stakeholders in the domain to establish an informed view of research progress.

show abstract

“…Considering the current importance of the CNNs in the field of computer vision, there are some proposals in the area of banknote recognition and counterfeit detection. For example, transfer learning (TL) with Histograms of Oriented Gradients for Euro banknotes [12], a YOLO net for Mexican banknotes [13] or custom CNN architectures for dollar, Jordanian dinar and Won Koreano banknotes [14,15] have been proposed. However, one of the main disadvantages of proposals using CNNs that focus on fake banknote recognition is that there is no clarity about which design strategy is more appropriate, either custom or by transfer learning.…”

Section: Introductionmentioning

confidence: 99%

Fake Banknote Recognition Using Deep Learning

2021

View full text Add to dashboard Cite

Recently, some state-of-the-art works have used deep learning-based architectures, specifically convolutional neural networks (CNNs), for banknote recognition and counterfeit detection with promising results. However, it is not clear which design strategy is more appropriate (custom or by transfer learning) in terms of classifier performance and inference times for massive data applications. This paper presents a comparison of the two design strategies in various types of architecture. For the transfer learning (TL) strategy, the most appropriate freezing points in CNN architectures (sequential, residual and Inception) are identified. In addition, a custom model based on an AlexNet-type sequential CNN is proposed. Both the TL and the custom models were trained and compared using a Colombian banknote dataset. According to the results, ResNet18 achieved the best accuracy, with 100%. On the other hand, the network with the shortest inference times was the proposed custom network, since its performance is up to 6.48-times faster in CPU and 16.29-times faster in GPU than the inference time with the models by transfer learning.

show abstract

Deep Feature-Based Three-Stage Detection of Banknotes and Coins for Assisting Visually Impaired People

Cited by 25 publications

References 27 publications

IPCRF: An End-to-End Indian Paper Currency Recognition Framework for Blind and Visually Impaired People

IPCRF: An End-to-End Indian Paper Currency Recognition Framework for Blind and Visually Impaired People

A Systematic Review of Urban Navigation Systems for Visually Impaired People

Fake Banknote Recognition Using Deep Learning

Contact Info

Product

Resources

About