检索结果-内蒙古大学图书馆

International Conference on Data Mining and Intelligent Computing (ICDMIC)

作者： Agrawal, Gauri Maurya, Sanjay Kumar GLA Univ Elect & Commun Mathura UP India GLA Univ Elect Engn Mathura UP India

ISBN: (纸本)9781479946747

In real world applications of face recognition system occlusion is always a big challenge. This paper presents an approach using hybrid combination of DT-CWT and LBP for feature extraction to deal with various occlusion. The DT-CWT focuses on global scale invariant feature however LBP emphasis on local structure of face image. The proposed approach are tested for synthetically created occlusion at eyes, mouth, upper face, lower face, which are general occlusion that is encountered in real world applications. The experimental result of recognition shows the robustness and effectiveness of proposed local complex binary pattern (LCBP) under different occlusion.

关键词： Face recognition local complex binary pattern (LCBP) local binary pattern complex filter face occlusion Dual tree complex wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Face Recognition Algorithms: Evaluating LBPH and FaceNet with Haar Cascade 14

Comparative Analysis of Face Recognition Algorithms: Evaluat...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Irfan, Ayaan Mohammed Deshmukh, Shantanu Atul Goel, Harsh Dharamdatt Vernekar, Gayatri Manoj Thomas, Sneha Suzanna Patil, Rajesh A. Veermata Jijabai Technological Institute Electronics and Telecommunications Mumbai India Veermata Jijabai Technological Institute Dept. of Electrical Engineering Mumbai India

ISBN: (纸本)9798350335095

Facial recognition is a widely utilized technology in numerous industries, such as security, retail, delivery, and criminal detection. However, it encounters significant challenges when dealing with low-resolution images and videos. To achieve accurate facial recognition, researchers have explored various techniques, including LBPH, Face++, and ReKognition. Despite advancements, there remains considerable room for improving recognition accuracy. LBPH, a feature-based method, demonstrates remarkable proficiency in recognizing faces from diverse viewpoints. In contrast, deep learning approaches like FaceNet and Haar Cascade have emerged as prominent techniques. Haar Cascade specifically focuses on face recognition. This study evaluates the performance of LBPH face recognition system in comparison with a combined approach employing FaceNet and Haar Cascade using real-time video data. © 2023 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Based Approach of Facial Images for the Detection of Autism Spectrum Disorder

A Hybrid Feature Based Approach of Facial Images for the Det...

引用

International Conference on Data Analytics and Insights, ICDAI 2023

作者： Khanna, Akshay Mishra, Mayank Pati, Umesh C. Department of Electronics and Communication Engineering National Institute of Technology Rourkela Rourkela769008 India

ISBN: (纸本)9789819938773

Autism spectrum disorder (ASD) is a neurological disorder that is commonly observed in children. It affects the ability of a child to maintain eye contact and communicate properly in social gatherings. Recently, the utilization of facial images has increased for the detection of various disorders. This work presents an approach for ASD detection from facial images with a hybrid combination of extracted histograms of oriented gradients (HOG) and local binary pattern (LBP) features. The dataset utilized in this work has been collected from Kaggle and contains 2940 facial images, equally divided between autistic and non-autistic children. The hybrid combination of the extracted features has been used for training four different machine learning algorithms, such as support vector machine (SVM), random forest (RF), K-nearest neighbors (KNN), and decision tree (DT), for the detection of ASD. The best classification performance has been achieved by SVM classifier with an accuracy of 77.96%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Skin texture recognition of leg images based on chaotic mapping reorganization features 3

Skin texture recognition of leg images based on chaotic mapp...

引用

3rd International Conference on Intelligent Computing and Human-Computer Interaction, ICHCI 2022

作者： Zhang, Tianshu Tang, Chaoying Huang, Qiaoyue Nanjing University of Aeronautics and Astronautics Automation College Nanjing China

ISBN: (纸本)9781510661301

In criminal and victim identification, when information such as fingerprint and facial images cannot be obtained, the development of other new bio-metric recognition has become an important task. It is found from investigations that the lower leg is often exposed in an evidence image. If we can use the information to identify the identity of the suspect, it will be a great break-through for criminal investigation. Unlike faces or fingerprints, the image of a lower leg does not have many discriminative features. Therefore, capturing more information from an image has become the key to the success of recognition. Despite the rapid development of deep learning in recent years and the wide application of convolutional neural networks in biometric recognition, they are very dependent on a large amount of training data. In this paper, we propose a recognition method based on the combination of chaotic mapping and local binary pattern (LBP), which captures the nonlinear features of the image. Experimental results show that the method proposed in this paper has a better recognition rate and an encouraging performance. © 2023 SPIE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Design Methodology for Single-Channel CNN-Based FER Systems 6

Design Methodology for Single-Channel CNN-Based FER Systems

引用

6th International Conference on Information and Computer Technologies, ICICT 2023

作者： Parra, Dorfell Camargo, Carlos Universidad Nacional Department of Electric and Electronic Engineering Bogota Colombia

ISBN: (纸本)9798350300956

Facial Expression Recognition (FER) systems classify emotions by using geometrical approaches or Machine Learning (ML) algorithms such as Convolutional Neural Networks (CNNs). Due to their complexity, these FER systems need to be implemented on high-performance hardware, which makes them unsuitable for embedded devices. To address this challenge, we propose a methodology for the design of low-complexity, CNN-based FER systems. Our methodology includes data preprocessing, local binary pattern (LBP) implementation, Data Augmentation (DA), and CNN design. Here, we also introduce the Model M6, a single-channel CNN that reaches an accuracy of 94% in less than 30 epochs. M6 has 306,182 parameters that correspond to 1.17 MB of memory. Therefore, our methodology and M6 model are feasible for implementation onto embedded systems capable of computing floating point operations. We validated our methodology and M6 model using 66 tests with 6 CNN models and 4 training parameters (batch size, learning rate, number of epochs, optimizer). This validation was performed using the Japanese Female Facial Expression (JAFFE) dataset and TensorFlow. In each test, the relationship between parameters, layers, overfitting, and underfitting was studied. Moreover, we present a step-by-step guideline on how to design the single-channel CNN and provide open-source code for readers interested in reproducing our work. © 2023 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Deep Retinal Image Analysis and Classification Using Deer Hunting Optimization-Based Tandem Pulse Coupled Neural Network

引用

Journal of The Institution of Engineers (India): Series B 2022年第6期103卷 1909-1916页

作者： Vinayaki, V. Desika Kalaiselvi, R. Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Kumaracoil India Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Gummidipoondi India

Retinal eye diseases lead to vision loss and visual deficiency. Various kinds of human eye diseases are arteriosclerosis, diabetic retinopathy, hypertension, and glaucoma. Diabetic retinopathy is the form of the injured retina which is occurred by diabetes. The improper treatment without proper observations leads to permanent blindness. Therefore, it is necessary to detect the disease at an earlier stage to protect their vision. The main aim of this research is to detect diabetic retinopathy early from the fundus images. The proposed approach detects diabetic retinopathy through four major stages, namely pre-processing, segmentation, feature extraction, and classification. The proposed classifier uses the deep neural network for classifying the diabetic retinopathy (DR) infected images and normal images. Here, the proposed approach utilizes features such as coherence, edge features, shape features, local binary pattern, and Gray Level Co-occurrence Matrix (GLCM) features from the segmented output. The performance measures like sensitivity, specificity, accuracy, precision, F1-measure and processing time are utilized for the estimation of the proposed classifier and compared to other approaches. From the performance evaluation, it is noted that the proposed diabetic retinopathy detection has obtained an accuracy of 99.42%, a sensitivity of 98.84%, and a specificity of 96.49% that outperforming other state-of-art methods. © 2022, The Institution of Engineers (India).

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

A texture-based approach for offline writer identification

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第8期34卷 5204-5222页

作者： Bahram, Tayeb Univ Dr Tahar Moulay Saida LGACA Lab BP 138 cite En-Nasr Saida Algeria

Offline handwriting has become a very important part in the field of behavioral biometrics. In this paper, we proposed an approach to identify writers from their handwritten documents. The foremost contribu-tion of this study is to suggest the use of co-occurrence features to improve the performance of writer identification. A contour texture-based feature is extracted from preprocessed regions of interest (com-ponents or sub-images) and their exterior contours are based primarily on Modified local binary pattern (MLBP) and Ink-trace Width and Shape Letters (IWSL) measurements. Considering the contour as a tex-ture, and using these textural descriptors, the joint probability distributions of MLBP and IWSL on differ-ent pixels are calculated in order to determine the similarities between different images of handwriting. Identification is carried out using the nearest neighbor rule and Chi-square distance. The proposed sys-tem has been evaluated on eight well-known handwriting databases (Arabic IFN/ENIT and KHATT, English IAM and CVL, Dutch Firemaker, Portuguese BFL, Chinese CERUG-CN, and English/Greek ICDAR2013). Experimental results show that the recommended scheme achieves the highest perfor-mance on KHATT, CVL, Firemaker, BFL, CERUG-CN, and ICDAR2013 databases, and that it demonstrates competitive performance on IFN/ENIT and IAM databases as compared to those reported by the state-of-the-art identification systems.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Writer identification Texture analysis Feature extraction local binary pattern Ink -trace Width and Shape Letters Forensic document examination

来源：评论

学校读者我要写书评

暂无评论

Learning center-epsilon local binary pattern for bovine IRIS recognition

引用

ICIC Express Letters 2013年第4期7卷 1209-1214页

作者： Song, Yang Sun, Shengnan Zhao, Lindu Institute of Systems Engineering Southeast University No. 2 Sipailou Nanjing 210096 China

The local binary pattern (LBP) descriptor has gained a lot of interest in recent years due to its simplicity and excellent performance in various applications. Nevertheless, the conventional LBP operator misses the information of the central pixel. In this paper, we propose a novel bovine iris recognition approach using center-epsilon local binary pattern (CΕ-LBP) descriptor. This novel local feature descriptor incorporates the information of the central pixel into the conventional LBP descriptor. Furthermore, the proposed descriptor can tolerate flat image areas, illumination changes and noise, while a variable Ε is introduced to the sign function. The experimental results on the bovine iris database verify the effectiveness of our proposed local feature descriptor. © 2013 ICIC International.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Student Attendance Recognition using the Haar Cascade Algorithm

Student Attendance Recognition using the Haar Cascade Algori...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Keerthi, Lagisetty Divya, Poleboina Sairam, U. Chaitanya Bharathi Institute of Technology Department of Information Technology Telangana India

ISBN: (纸本)9798350333602

Attendance systems are very important in schools, colleges, and many organizations. It tells about whether a student is regular to the school/college or not, an employee is regular to the work or not. The traditional method of attendance is to take manually by using roll calls and notes in the attendance register given by the organization. In some organizations, students need to sign in the register for attendance. But it is a difficult process, there may be a chance for the occurrence of proxy. It creates a lot of disturbances in class and a waste of time. Proxy leads to the irregularity of the students and decreases performance in academics. It may affect their goals and deviates into other activities. Alternating methods need to be implemented that should rectify the issues that exist with the traditional method, and save both time and manual work. © 2023 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Texture and CNN Based Doppler Signal Classification 8

Texture and CNN Based Doppler Signal Classification

引用

8th International Conference on Computer Science and Engineering, UBMK 2023

作者： Lone, Ab Waheed Aydin, Nizamettin Yildiz Technical University Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350340815

Background understanding and extraction from images becomes easy when different image descriptors capture the location and movement of different sub-elements in a given image. One main type of artificial neural network called Convolutional neural network (CNN) has attracted lot of interest in bio-medical sub-domain. Depending on the type and amount of data, its different architectures lead to its heterogeneous learning capability. Cerebral emboli detection is considered as one of the main problems in understanding the nature of normal and abnormal blood flow. Embolus detection using transcranial Doppler ultrasound is a useful method for the identification of active embolic sources in cerebrovascular diseases. Texture features represent the lower space of image data and encode the relationship of different pixel values. local Derivative pattern (LDP) calculates the n-th order derivative directions of each pixel in an image. In this paper, we make use of labelled Doppler signal dataset collected from patients with carotid stenosis and make use of combination of CNN layers and LDP operators for Doppler signal classification. We convert Doppler signals into image data and add LDP feature extraction as a layer in CNN. In a single mode CNN-LDP, network on our Doppler image data achieved validation accuracy of 90% with a loss of 21.91% (Batch size of 64, epochs 10). In multi-mode CNN-LDP, network achieved validation accuracy of 91% with a loss of 20.64% (Batch-size 64 epochs 8). © 2023 IEEE.

关键词： local binary pattern

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：