检索结果-内蒙古大学图书馆

Two stream CNN for muzzle print recognition using gabor filters

Multimedia Tools and Applications 2025年 1-17页

作者： Russel, Newlin Shebiah Selvaraj, Arivazhagan Centre for Image Processing and Pattern Recognition Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Tamilnadu Sivakasi India

Muzzle print recognition, an essential aspect of biometric identification for animals, has gained significant attention in recent years. This study introduces a novel method for enhancing the precision and robustness of muzzle print identification through the utilization of a Two-Stream Convolutional Neural Network (CNN) integrated with Gabor Filters. The proposed Two-Stream CNN architecture comprises of two distinct streams, the Spatial Stream, which processes raw muzzle images, and the Texture Stream, dedicated for extracting texture features through Gabor Filters. By integrating feature maps from both streams, the model effectively utilizes the synergistic advantages of spatial and texture information, thereby augmenting the discriminative capabilities of the recognition system. The Gabor Filters applied in the Texture Stream enable the extraction of intricate texture details, making the model highly sensitive to variations in muzzle patterns. By conducting training and fine-tuning procedures on animal muzzle prints in the Beef Cattle Muzzle/Nose print database for individual identification, a recognition accuracy of 98.99% was achieved. Additional performance metrics include a recall of 98.36%, precision of 98.39%, specificity of 100% and F1-Score of 98.18%. The ability of the proposed model to accurately differentiate intricate variations in muzzle prints presents significant prospects for diverse fields of application, such as wildlife preservation, animal monitoring, and security measures. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Robust penta-modal biometric identification through deep learning and weighted score fusion

引用

Iran Journal of Computer Science 2025年 1-17页

作者： Selvaraj, Arivazhagan Russel, Newlin Shebiah Seenivasan, Mridula Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Tamil Nadu Sivakasi India

Recent advancements in biometric security systems, which are designed to reliably verify an individual’s identity, have garnered significant attention in the fields of security and access control. However, traditional unimodal biometric systems encounter several challenges, including intra-class variability, vulnerability to spoofing, and noise interference, which can undermine their effectiveness. To overcome these limitations, this study introduces a novel penta-modal biometric recognition system that integrates five distinct biometric traits: iris, fingerprint, palm print, ear, and face. The proposed system employs a weighted similarity approach, utilizing Local Binary pattern (LBP) feature maps that are extracted from query images using a Convolutional Neural Network (CNN). These extracted features are then compared against enrolled templates stored in a database. The operation of the system follows a structured five-step process: (1) pre-processing of biometric data, (2) extraction and classification of LBP feature maps via CNN, (3) score computation for each biometric modality, (4) weighted score-level fusion, and (5) final authentication. The performance of the penta-modal biometric system was rigorously evaluated using various public benchmark datasets, including CASIA-FingerprintV5, CASIA-FaceV5, CASIA-PalmprintV1, CASIA-Iris-V3, the AMI ear dataset, and the MEPCO multimodal dataset, as well as synthetically generated multimodal databases. The system achieved an impressive accuracy rate of 99.85% on the virtual databases, demonstrating significantly enhanced security and reliability compared to traditional unimodal systems. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： CASIA database Convolutional neural network (CNN) Local binary pattern (LBP) Penta-modal Penta-modal Score-level fusion

来源：评论

学校读者我要写书评

暂无评论

Wavelet scattering transform and deep features for automated classification and grading of dates fruit

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第6期15卷 2909-2923页

Date fruit, a vital agricultural product in the Middle East area, is harvested annually in millions of metric tons and is renowned for its abundant nutrients. With computer vision and machine learning techniques, automatic date fruit classification enables farmers and supermarkets to differentiate between various varieties and qualities of date fruits within their inventory. Date fruits have unique physical characteristics, such as shape, size, color, texture, and skin type that are important in determining their variety and quality. These characteristics can vary significantly depending on the cultivar, growing conditions, and ripening stage of the date fruits. This paper presents a novel date fruit type classification and grading system achieved through the feature-level fusion of deep learning features and wavelet scattering features. Wavelet scattering features are extracted at varying levels of decomposition;enabling reliable extraction of information from diverse channels. To extract deep features this study utilizes pre-trained architectures, including Alexnet, Googlenet, Resnet, and MobileNetV2. The proposed methodology has been experimentally evaluated with the Date Fruit in Controlled Environment dataset, which has nine classes, and has yielded an accuracy of 95.9% for date species classification. Various date fruit species from the TU-DG dataset were graded, and for Ajwa species, the accuracy is 97.8%, for Mabroom, 92.6% accuracy, and for Sukkary, 99.5% accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Curated Dataset for Spinach Species Identification 1

引用

7th International Conference on Computer Vision and image processing, CVIP 2022

作者： Priyadharshini, R. Ahila Arivazhagan, S. Arun, M. Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Sivakasi India

ISBN: (数字)9783031314179

ISBN: (纸本)9783031314162

India has a large population of spinach eaters. Despite this fact most people and young generation have difficulty in distinguishing the spinach species because of the structure similarity of many plant species. So, automated spinach recognition will support the people community to a greater extent. In this study, we present spinach dataset, a freely accessible annotated collection of images of spinach leaves in Indian scenario. We propose three different custom designed convolutional neural networks (CNN) and compare the performance of the same. Also we apply the transfer learning approach using MobileNetV2 pretrained model for this spinach species recognition. Using transfer learning approach we got an accuracy of 92.96%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Development of a Robust Dataset for Printed Tamil Character recognition 3rd

Development of a Robust Dataset for Printed Tamil Character ...

引用

3rd International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2023

作者： Arun, M. Arivazhagan, S. Priyadharshini, R. Ahila Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Tamil Nadu Sivakasi India

ISBN: (纸本)9789819939312

Despite the fact that many character datasets for several languages are publicly available, there are only a very few standardized datasets for Tamil characters. This article presents a subset of the Mepco Tamil Character database, a Tamil font isolated character dataset representing the printed characters. This dataset includes 124 glyphs representing the 247 characters of Tamil language. This dataset is tested for its robustness using multiple experimentations using SVM classifier and is compared against UJTDchar, another dataset available for Tamil language. Also we have verified the robustness of DIGI-Net, CNN architecture for this Tamil character recognition problem using the UJTDchar dataset and the Mepco Tamil Character dataset. We report an accuracy of 90.59% and 97.66% while using SVM and DIGI-Net CNN on our newly created dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A Large Volume Natural Tamil Character Dataset 6th

A Large Volume Natural Tamil Character Dataset

引用

6th International Conference on Computer Vision and image processing, CVIP 2021

作者： Arun, M. Arivazhagan, S. Ahila Priyadharshini, R. Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Tamil Nadu Sivakasi India

ISBN: (纸本)9783031113451

This paper focuses on recognizing the individual Tamil characters in images of natural scenes. Even though natural character dataset are available publicly for different languages, no specific standardized dataset is available for natural Tamil characters. In this work, we present a publicly available Tamil character dataset "Mepco-TamNatChar" for natural Tamil character recognition. This research work presents the preliminary results on natural Tamil character recognition using spatial and machine learnt features. We report an accuracy of 87.50 ± 1.42% for a train test ratio of 50:50 using machine learnt features. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Ayurvedic Medicinal Plants Identification: A Comparative Study on Feature Extraction Methods 5th

Ayurvedic Medicinal Plants Identification: A Comparative Stu...

引用

5th International Conference on Computer Vision and image processing, CVIP 2020

作者： Ahila Priyadharshini, R. Arivazhagan, S. Arun, M. Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Sivakasi Tamil Nadu India

ISBN: (纸本)9789811610912

Proper identification of medicinal plants is essential for agronomists, ayurvedic medicinal practitioners and for ayurvedic medicines industry. Even though many plant leaf databases are available publicly, no specific standardized database is available for Indian Ayurvedic Plant species. In this paper, we introduce a publicly available annotated database of Indian medicinal plant leaf images named as MepcoTropicLeaf. The research work also presents the preliminary results on recognizing the plant species based on the spatial, spectral and machine learnt features on the selected set of 50 species from the database. To attain the machine learnt features, we propose a six level convolutional neural network (CNN) and report an accuracy of 87.25% using machine learnt features. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Dyadic Interaction recognition Using Dynamic Representation and Convolutional Neural Network 1

引用

6th International Conference on Computer Vision and image processing, CVIP 2021

作者： Shebiah, R. Newlin Arivazhagan, S. Centre for Image Processing and Pattern Recognition Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Tamilnadu Sivakasi626005 India

ISBN: (数字)9783031113468

ISBN: (纸本)9783031113451

Human interaction recognition can be used in video surveillance to recognise human behaviour. The goal of this research is to classify human interaction by converting video snippets into dynamic images and deep CNN architecture for classification. The human interaction input video is snipped into a certain number of smaller segments. For each segment, dynamic image is constructed that efficiently encodes a video segment into an image with an action silhouette, which plays an important role in interaction recognition. The discriminative features are learned and classified from dynamic image using Convolutional Neural Network. The efficacy of the proposed architecture for interaction recognition is demonstrated by the obtained results on the SBU Kinect Interaction dataset, IXMAS, and TV Human Interaction datasets. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Livestock Management: A Multiscale Approach to Cow recognition System

Revolutionizing Livestock Management: A Multiscale Approach ...

引用

International Conference on Computer Vision and Internet of Things 2023, ICCVIoT 2023

ISBN: (纸本)9781839539848

The implementation of a cow recognition system has significantly transformed the field of livestock management through the automation of identification and monitoring procedures. By employing sophisticated computer vision, this system is capable of distinguishing individual cows, facilitating accurate health monitoring, reproductive management, as well as customized diet. This study presents a multiscale framework inspired by Googlenet architecture that effectively captures intricate information at many levels of abstraction within an image. The complexity of cow identification, influenced by factors like posture, size, and unique characteristics, necessitates a multiscale technique. The proposed Methodology was tested using a dataset consisting of 13 classes of Holstein cow images, resulting in an accuracy rate of 97.97%. In order to assess the credibility of the model, the dataset and experimental settings were maintained at a constant level and subsequently compared to the outcomes obtained by VGG16, AlexNet, GoogLeNet, MobileNet, ResNet, SqueezeNet, and EfficientNet. © The Institution of Engineering & Technology 2023.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based image Analysis for Classification of Foot and Mouth Disease in Cattle 5

Deep Learning Based Image Analysis for Classification of Foo...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Shebiah, R. Newlin Arivazhagan, S. Mepco Schlenk Engineering College Centre for Image Processing and Pattern Recognition Department of Electronics and Communication Engineering Tamilnadu Sivakasi626005 India

ISBN: (纸本)9798350321425

Foot and mouth disease (FMD) poses a substantial threat to the global cattle industry, as it is a highly contagious viral infection. Timely detection and precise classification of FMD in cattle are essential for effective disease management and control. The proposed method harnesses the power of convolutional neural networks (CNNs) to automatically extract distinguishing features from cattle images and classify whether the cattle is diseased or not. Furthermore, a pre-trained architecture such as MobileNetV2 is employed and fine-tuned for FMD classification. Experiments were performed to assess the effectiveness of the proposed approach, taking into account metrics such as accuracy, precision, recall, and F1-score. The experimental results demonstrate the efficacy of proposed deep learning-based classification approach, achieving impressive accuracy rates in differentiating between healthy and FMD-infected cattle. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：