A Proficient Model to Classify Bangladeshi Bank Notes for Automatic Vending Machine Using a Tıny Dataset with One-Shot Learning &amp; Siamese Networks

Hossain, Md. Ekram; Islam, Arni; Islam, Md. Sanzidul

doi:10.1109/icccnt49239.2020.9225405

Cited by 4 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• In this study, very similar objects are classified using OSL, Siamese network and DL. From studies using OSL, Siamese network and DL [Agarwal et al 2020] classified 5 objects, [Hossain et al 2020] classified 5 objects and [Sabri and Setumin 2021] classified 4 objects, 18 objects were classified in our study.…”

Section: Introductionmentioning

confidence: 70%

“…The OSL and Siamese networks were used to detect Bangladeshi banknotes with a small dataset [Hossain et al 2020]. Twenty images were used to recognize five different banknotes.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The regularized cross entropy was used as a loss function in the study. The model in [Hossain et al 2020] was run with 50 epochs. In another study, the similarity between two anomaly sequences is measured using 3D CNN Siamese network for anomaly detection, and OSL is used to solve the problem of lack of data.…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Fastener Classification Using One-Shot Learning with Siamese Convolution Networks

Tastimur¹,

Akın²

2022

jucs

View full text Add to dashboard Cite

Deep Learning has been widely used in image-based applications such as object classification, object detection, and object recognition in recent years. Classifying highly similar objects is a very difficult problem. It is difficult to classify datasets in this situation where object similarity between classes and differences between classes are high. In this study, Siamese Convolution Neural Network, which is a similarity measurement-based network, has been practiced to classify 6 types of screws, 5 types of nuts, and 7 types of bolts that are very similar to each other. In addition, this neural network formed with the One-Shot Learning technique is trained. Thanks to the OSL technique, there is no need to use large data sets. Also, there is no need to use large amounts of data from each class. Adding a new class to be classified is also made easier by the use of the OSL technique. The performance results of the proposed method are manifested in detail in the article.

show abstract

Section: Introductionmentioning

confidence: 70%

“…The OSL and Siamese networks were used to detect Bangladeshi banknotes with a small dataset [Hossain et al 2020]. Twenty images were used to recognize five different banknotes.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Fastener Classification Using One-Shot Learning with Siamese Convolution Networks

Tastimur¹,

Akın²

2022

jucs

View full text Add to dashboard Cite

show abstract

Ensembling Shallow Siamese Neural Network Architectures for Printed Documents Verification in Data-Scarcity Scenarios

Ferreira¹,

Purnekar

Barni

2021

IEEE Access

View full text Add to dashboard Cite

The popularity of printing devices has multiplied the diffusion of printed documents, raising concerns regarding the security and integrity of their content. The same device that prints reliable contracts, newspapers, and others, can also be used for malicious purposes, such as printing fake money, forging fake contracts, and produce illegal packaging, thus calling for the development of image forensics techniques to pinpoint criminal printed materials and trace back to their origin. In this work, we address the source linking problem of printed color documents by treating it as a verification problem. Specifically, we aim at deciding if two documents have been printed by the same printer or not. To achieve this goal, and to cope with the data scarcity deriving from the difficulty of gathering massive amounts of printed and scanned documents, we propose to use an ensemble of Siamese Neural Networks, with unique architectures expressly designed to work with a small training dataset. As a further unique feature, the proposed approach is suited to work in an open set scenario, where the printers used to produce the documents analyzed at the test time are not included in the training set. Results obtained under both open and closed set conditions, with a thorough comparison with available baseline methods, highlight the validity of the proposed solution and its capability to work in real-world settings.

show abstract

Deep Feature Fusion Classification Model for Identifying Machine Parts

Batool,

Dai,

et al. 2023

JACIII

View full text Add to dashboard Cite

In the digital world, automatic component classification is becoming increasingly essential for industrial and logistics applications. The ability to automatically classify various machine parts, such as bolts, nuts, locating pins, bearings, plugs, springs, and washers; using computer vision is challenging for image-based object recognition and classification. Despite varying shapes and classes, components are difficult to distinguish when they appear identical in several ways–particularly in images. This paper proposes identifying machine parts by a deep feature fusion classification model (DFFCM)-variance based designed through the convolutional neural network (CNN), by extracting features and forwarding them to an AdaBoost classifier. DFFCM-v extracts multilayered features from input images, including precise information from image edges, and processes them based on variance. The resulting deep vectors with higher variance are fused using weighted feature fusion to differentiate similar images and used as input to the ensemble AdaBoost classifier for classification. The proposed DFFCM-variance approach achieves the highest accuracy of 99.52% with 341,799 trainable parameters compared with the existing CNN and one-shot learning models, demonstrating its effectiveness in distinguishing similar images of machine components and accurately classifying them.

show abstract

A Proficient Model to Classify Bangladeshi Bank Notes for Automatic Vending Machine Using a Tıny Dataset with One-Shot Learning & Siamese Networks

Cited by 4 publications

References 5 publications

Fastener Classification Using One-Shot Learning with Siamese Convolution Networks

Fastener Classification Using One-Shot Learning with Siamese Convolution Networks

Ensembling Shallow Siamese Neural Network Architectures for Printed Documents Verification in Data-Scarcity Scenarios

Deep Feature Fusion Classification Model for Identifying Machine Parts

Contact Info

Product

Resources

About