Thai Banknote Recognition Using Neural Network and Continues Learning by DSP Unit

Takeda, Fumiaki; Sakoobunthu, Lalita; Satou, Hironobu

doi:10.1007/978-3-540-45224-9_158

Cited by 22 publications

(24 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset presented in our experiment is more challenging than that from other banknote recognition papers. For example, the dataset in [20] was collected by using a scanner to scan the bills which were taken under restricted or standard conditions. Thus, our dataset generalizing the conditions of taking banknote images is more challenging and more approximates to the real world application environment.…”

Section: Experiments and Analysismentioning

confidence: 99%

Robust and effective component-based banknote recognition by SURF features

Hasanuzzaman

Yang

Tian

2011

2011 20th Annual Wireless and Optical Communications Conference (WOCC)

View full text Add to dashboard Cite

Camera-based computer vision technology is able to assist visually impaired people to automatically recognize banknotes. A good banknote recognition algorithm for blind or visually impaired people should have the following features: 1) 100% accuracy, and 2) robustness to various conditions in different environments and occlusions. Most existing algorithms of banknote recognition are limited to work for restricted conditions. In this paper we propose a component-based framework for banknote recognition by using Speeded Up Robust Features (SURF). The component-based framework is effective in collecting more class-specific information and robust in dealing with partial occlusion and viewpoint changes. Furthermore, the evaluation of SURF demonstrates its effectiveness in handling background noise, image rotation, scale, and illumination changes. To authenticate the robustness and generalizability of the proposed approach, we have collected a large dataset of banknotes from a variety of conditions including occlusion, cluttered background, rotation, and changes of illumination, scaling, and viewpoints. The proposed algorithm achieves 100% recognition rate on our challenging dataset.

show abstract

Section: Experiments and Analysismentioning

confidence: 99%

Robust and effective component-based banknote recognition by SURF features

Hasanuzzaman

Yang

Tian

2011

2011 20th Annual Wireless and Optical Communications Conference (WOCC)

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that, in general, neural network systems achieved recognition rate no larger than 95% (see e.g. [57,70] ) with more complex and time consuming procedures.…”

Section: Experimental Assessmentmentioning

confidence: 99%

“…This suggests us that the PCR task can be efficiently modeled as an image retrieval problem, skipping the object detection phase which we adopted in the previous sections and which is also used in the literature to address PCR. With this respect, it is worth citing methods available in the literature making use of neural networks (see, for instance, [55][56][57] ), HMM [58] , PCA [59] , or vector quantization [60] .…”

Section: Recognizing Hand Held Objectsmentioning

confidence: 99%

An integrated artificial vision framework for assisting visually impaired users

Chessa

Odone

Solari

et al. 2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…The research in [7] implements a system for classifying Thai banknotes using neural networks. Firstly, images of notes are collected by a scanner which is saved as bitmap data.…”

Section: Literature Surveymentioning

confidence: 99%

Analysis of Banknote Authentication System using Machine Learning Techniques

Shahani¹,

Jagiasi²,

Priya³

2018

IJCA

View full text Add to dashboard Cite

Banknotes are one of the most important assets of a country. Some miscreants introduce fake notes which bear a resemblance to original note to create discrepancies of the money in the financial market. It is difficult for humans to tell true and fake banknotes apart especially because they have a lot of similar features. Fake notes are created with precision, hence there is need for an efficient algorithm which accurately predicts whether a banknote is genuine or not. This paper proposes machine learning techniques to evaluate authentication of banknotes. Supervised learning algorithms such as Back propagation Neural Network (BPN) and Support Vector Machine (SVM) are used for differentiating genuine banknotes from fake ones. The study also shows the comparison of these algorithms in classification of banknotes.

show abstract

Thai Banknote Recognition Using Neural Network and Continues Learning by DSP Unit

Cited by 22 publications

References 3 publications

Robust and effective component-based banknote recognition by SURF features

Robust and effective component-based banknote recognition by SURF features

An integrated artificial vision framework for assisting visually impaired users

Analysis of Banknote Authentication System using Machine Learning Techniques

Contact Info

Product

Resources

About