检索结果-内蒙古大学图书馆

An intelligent flower classification framework: optimal hybrid flower pattern extractor with adaptive dynamic ensemble transfer learning-based convolutional neural network

引用

IMAGING SCIENCE JOURNAL 2024年第1期72卷 52-75页

作者： Anand, M. Suresh Swaroopa, Korla Nainwal, Manoj Therasa, M. SRM Inst Sci & Technol SRMIST Sch Comp Dept Comp Technol Chennai India Aditya Engn Coll CSE Dept Surampalem India Om Sterling Global Univ Dept Comp Sci & Engn Hisar India Panimalar Engn Coll Comp Sci & Engn Chennai India

The rapid development in computer technology plays an essential role in the research works for performing fast and accurate identification of flower species through the processing of flower images with the support of mobile devices that seeks more attention in the research areas. It is highly significant for maintaining the sensitivity of ecological balance, and therefore, the image-processing approaches have provided improved outcomes in recent days. To rectify these existing problems and improve the accuracy attains the flower classification, the CNN variants of ensemble techniques can be used for the dynamic ensemble selection of the CNN networks. This paper develops an enhanced ensemble deep learning-based flower classification model to get efficient classification results with optimal models. The pre-processing is done through the Contrast Limited Adaptive Histogram Equalization (CLAHE) and filtering techniques. The pre-processed images are considered for the optimal pattern extraction phase, where optimal hybrid patterns are extracted from the local binary pattern (LBP) and local Vector pattern (LVP). Here, the optimal hybrid pattern extraction phase contains the optimization in it using the enhanced heuristic algorithm named Improved Rat Swarm Optimizer (IRSO). The flower classification is performed with an Adaptive Dynamic Ensemble Transfer learning-based Convolutional Neural Network (ADET-CNN). Here, the optimal models are selected with the support of the same RSO algorithm. The experimental results show a better efficacy of the developed flower classification framework.

关键词： Flower classification optimal hybrid flower pattern extractor contrast limited adaptive histogram equalization local binary pattern local vector pattern ‌ adaptive dynamic ensemble transfer learning-based convolutional neural network improved rat swarm optimizer ensemble deep learning model

来源：评论

学校读者我要写书评

暂无评论

Content-Based Image Retrieval (CBIR): Using Combined Color and Texture Features (TriCLR and HistLBP)

引用

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS 2025年第3期25卷

作者： Bosco, P. John Janakiraman, S. Pondicherry Univ Sch Engn & Technol Dept Comp Sci Pondicherry 605014 India Pondicherry Univ Dept Banking Technol Sch Management Pondicherry 605014 India

Content-Based Image Retrieval (CBIR) is a broad research field in the current digital world. This paper focuses on content-based image retrieval based on visual properties, consisting of high-level semantic information. The variation between low-level and high-level features is identified as a semantic gap. The semantic gap is the biggest problem in CBIR. The visual characteristics are extracted from low-level features such as color, texture and shape. The low-level feature increases CBIRs performance level. The paper mainly focuses on an image retrieval system called combined color (TriCLR) (RGB, YCbCr, and L*a*b*) with the histogram of texture features in LBP (HistLBP), which, is known as a hybrid of three colors (TriCLR) with Histogram of LBP (TriCLR and HistLBP). The study also discusses the hybrid method in light of low-level features. Finally, the hybrid approach uses the (TriCLR and HistLBP) algorithm, which provides a new solution to the CBIR system that is better than the existing methods.

关键词： Color features RGB texture features CBIR multiple features local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Identification of Tamil Sign Language using Hamiltonian deep neural network

引用

International Journal of Systems, Control and Communications 2025年第1期16卷 62-78页

作者： Lingeswari, Ponnusamy Pavunraj, Daniel Kanagavalli, Mariappan Manikandan, Karuppasamy Department of Electronics and Communication Engineering P.S.R. Engineering College Tamil Nadu Sivakasi India Department of Artificial Intelligence and Data Science Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai India Department of Electronics and Communication Engineering P.S.R.R. College of Engineering Tamil Nadu Sivakasi India Department of Computer Science and Engineering P.S.R. Engineering College Tamil Nadu Sivakasi India

Sign language consisting of various hand patterns, serves as a vital communication medium for conveying messages, sharing knowledge, and expressing ideas among the deaf community. This research addresses the challenge of recognising Tamil Sign Language (TSL) by proposing a novel identification method using a Hamiltonian deep neural network (HDNN). The primary objective is to maximise the accuracy and reliability of TSL recognition, especially for real-time applications. The dataset comprises real-time images of 12 vowels, 1 Aayutha Ezhuthu, and 18 consonants, collected from 110 different signers. To address noise in the images, an iterative guided filtering (IGF) method is employed for preprocessing. Subsequently, feature extraction is performed using residual exemplars local binary pattern (RELBP). HDNN is then applied to classify the signs. The performance of the proposed approach achieves 23.32%, 25.07%, 21%, 27.53%, and 30% higher accuracy and 14.09%, 19.63%, 28%, 18.45%, and 10.54% lower error rates compared to existing methods. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Age-Invariant Cross-Age Face Verification using Transfer Learning

引用

INTELIGENCIA ARTIFICIAL-IBEROAMERICAN JOURNAL OF ARTIFICIAL INTELLIGENCE 2024年第74期27卷 37-47页

作者： Russel, Newlin Shebiah Selvaraj, Arivazhagan Devi, Dhanya S. Dhivyarupini, M. Ctr Image Proc & Pattern Recognit Sivakasi India Dept Elect & Commun Engn Sivakasi India Mepco Schlenk Engn Coll Sivakasi India

The integration of face verification technology has become indispensable in numerous safety and security software systems. Despite its promising results, the field of face verification encounters significant challenges due to age-related disparities. Human facial characteristics undergo substantial transformations over time, leading to diverse variations including changes in facial texture, morphology, facial hair, and eyeglass adoption. This study presents a pioneering methodology for cross -age face verification, utilizing advanced deep learning techniques to extract resilient and distinctive facial features that are less susceptible to age-related fluctuations. The feature extraction process combines handcrafted features like local binary pattern/Histogram of Oriented Gradients with deep features from MobileNetV2 and VGG-16 networks. As the texture of the facial skin defines the age related characteristic the well-known texture feature extractors like LBP and HoG is preferred. These features are concatenated to achieve fusion, and subsequent layers fine -tune them. Experimental validation utilizing the CrossAge Celebrity Dataset demonstrates remarkable efficacy, achieving an accuracy of 98.32%.

关键词： Cross-age face verification local binary pattern Histogram of Oriented Gradients Transfer Learning MobileNetV2 VGG-16

来源：评论

学校读者我要写书评

暂无评论

Multiscale Discriminative binary pattern (MDBP): Novel Descriptor for Face Recognition in Pose and Illumination Variations

引用

IETE JOURNAL OF RESEARCH 2025年

作者： Karanwal, Shekhar GLA Univ Dept Comp Engn & Applicat Mathura Uttar Pradesh India

local binary pattern (LBP) encodes the binary pattern by neighborhood comparison with a center pixel. In addition, various LBP variants follow the uniform coordination between neighbors and center pixel. The two major issues noticed in these descriptors are: (1) Limited spatial size (2) Noisy thresholding function. The proposed work eliminates both these issues and introduces a novel LBP variant for Face Recognition called Multiscale Discriminative binary pattern (MDBP). In MDBP, the center pixel is replaced by a novel thresholding function value, which is formed utilizing the two local statistics, mean and median, in conjunction with the introduced parameter t (the threshold). The thresholding function is written as [(Mean + Median)/abs (1-t)]. The mean and median are computed from the 5 x 5 patch. By putting 3 different values of t (i.e. 2.95, 3, and 3.05), 3 values are produced for comparison. Then 8 neighborhoods at 2 different scales (Specified as P = 8, R = 1, and P = 8, R = 2) are compared with 3 different values. Eventually, the multiscale features extracted utilizing the same compared values are combined to produce the size of 3 novel descriptors, MDBP1, MDBP2, and MDBP3. For all three proposed descriptors, the regional histograms are extracted and fused. PCA and FLDA are used for compression, and SVMs and NN are used for the classification of results. Tests are done on ORL, GT, Yale, and EYB datasets. The results prove the efficacy of MDBP against the compared ones.

关键词： Classification Feature compression Global feature local binary pattern local feature Multiscale discriminative binary pattern

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition based on Face and Speech using Deep Convolution Neural Network and Long Short Term Memory

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2025年 1-28页

作者： Taware, Shwetkranti Thakare, Anuradha D. Pimpri Chinchwad Coll Engn Dept Comp Engn Pune India

Multimodal emotion recognition (MER) is crucial for analyzing a person's mental behavior and health to enhance the performance of human-computer-interaction systems. Various deep learning-based MER systems have been presented in the last decade. However, the outcomes of the MER schemes are limited due to poor feature representation, lower correlation in short and long-term features, security issues, lower generalization capability, lower reliability of emotional modality systems, and higher computational intricacy of deep learning models. This paper presents the MER based on facial images and speech data using parallel deep convolution neural network (PDCNN) and bidirectional long short-term memory (BiLSTM) to improve the system's reliability, security, and robustness. The PDCNN aims to offer superior generalization capability and feature depiction;however, BiLSTM offers better long-term dependency, temporal representation, and correlation between the multimodal data's short and long-term attributes. The novel hybrid Particle Swarm Optimization based on Multi-Attribute Utility Theory and Archimedes Optimization Algorithm (PMA) is used to select crucial features of the facial expressions and speech data to minimize the computational intricacy of the PDCNN-LSTM framework. It offers an overall improved accuracy of 99.22%, precision of 0.9967, recall of 0.9933, and F1-score of 0.9949 for MER on the BAUM dataset compared to traditional techniques.

关键词： Affective computing Multimodal emotion recognition Deep Convolution neural network local binary pattern Deep learning Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Texture Classification Using Directional Binarized Random Features

引用

IEEE ACCESS 2023年 11卷 55895-55910页

作者： Zhao, Xiaochao Xu, Fang Ma, Yi Liu, Zhen Deng, Min Khan, Umer Sadiq Xiong, Zenggang Hubei Engn Univ Sch Comp & Informat Sci Xiaogan 432000 Peoples R China Hubei Engn Univ Inst AI Ind Technol Res Xiaogan 432000 Peoples R China

Dynamic texture description has been studied extensively due to its wide applications in the field of computer vision. local binary pattern (LBP) and its various variants account for a large part of dynamic texture description methods because of its advantages, such as good discriminability and low computational complexity. However, many LBP-based methods directly extract feature from pixel intensities and only use a proportion of pixels in a local neighborhood. And their good classification performance is usually achieved at the cost of high feature dimensionality, which would limit their application scenarios. We argue that extracting features from the gradient domain will capture more discriminative features due to the additional directional information, and that making use of all the pixels in a local neighborhood would improve performance. In this paper, we propose a simply but effective dynamic texture descriptor that inherits the advantages of LBP while excluding its disadvantages. The proposed method consists of four stages of data processing: 1) gradients extraction;2) random feature extraction from gradients;3) binary hashing of directional random features;and 4) histogramming. Gaussian first-order derivatives are used as gradient filters such that stable gradients could be generated. Then random projection is applied to extract random features from each gradients. Both the above two stages are conducted via 3D filtering, and thus they are efficient. Thirdly, the random features from each gradient are binarized and encoded into integer codes, from which a histogram is built. Finally, the histograms from each gradient are concatenated into a feature vector. Because we use 8-bit codes, The feature dimensionality is very low. We evaluate the proposed method on three benchmark dynamic texture datasets with various test protocols. The results demonstrate its effectiveness and efficiency when comparing to many state-of-the-art methods.

关键词： INDEX TERMS Dynamic texture feature extraction gradient Gaussian derivative local binary pattern random feature

来源：评论

学校读者我要写书评

暂无评论

An improved method for classifying depth-based human actions using self-adaptive evolutionary technique

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 157-173页

作者： Pareek, Preksha Thakkar, Ankit Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India

Automatic Human Action Recognition (HAR) using RGB-D (Red, Green, Blue, and Depth) videos captivated a lot of attention in the pattern classification field due to low-cost depth cameras. Feature extraction in action recognition is an important aspect. As compared to Depth Motion Maps (DMM), Depth Motion Maps–local binary pattern (DMM–LBP) provides compact representation of features. After extracting features using DMM–LBP, Principal Component Analysis (PCA) is used for dimensionality reduction. For classification task, randomly generated input weights of Extreme Learning Machine (ELM) can lead to non-optimal results. Therefore, in this paper, we have used an improved learning algorithm named Self-adaptive Differential Evolution (SaDE) ELM for action classification. In the proposed approach, DMM–LBP is used for feature extraction and SaDE–ELM is used for action classification. To evaluate strength of the proposed approach, experiments are performed on four public datasets, namely, MSRAction3D, MSRDaily Activity3D, UTD–MHAD, and MSRGesture3D. The proposed approach gives better accuracy compared to existing approaches Kernel ELM (KELM), l2-Collaborative Representation Classifier (l2-CRC), and Probabilistic CRC (ProCRC) methods. We have also presented statistical significance of results in the paper. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Image classification of hyperspectral remote sensing using semi- supervised learning algorithm

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第6期20卷 11502-11527页

作者： Ye, Ansheng Zhou, Xiangbing Weng, Kai Gong, Yu Miao, Fang Zhao, Huimin Chengdu Univ Technol Key Lab Earth Explorat & Informat Tech Minist Educ Chengdu 610059 Peoples R China Chengdu Univ Sch Comp Sci Chengdu 610106 Peoples R China Sichuan Tourism Univ Sch Informat & Engn Chengdu 610100 Peoples R China Sichuan Prov Dept Culture & Tourism Publ & Informat Ctr Chengdu 611930 Peoples R China Civil Aviat Univ China Coll Elect Informat & Automat Tianjin 300300 Peoples R China

Hyperspectral images contain abundant spectral and spatial information of the surface of the earth, but there are more difficulties in processing, analyzing, and sample-labeling these hyperspectral images. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression model are introduced to propose a sample labeling method based on neighborhood information and priority classifier discrimination. A new hyperspectral remote sensing image classification method based on texture features and semi-supervised learning is implemented. The LBP is employed to extract features of spatial texture information from remote sensing images and enrich the feature information of samples. The multivariate logistic regression model is used to select the unlabeled samples with the largest amount of information, and the unlabeled samples with neighborhood information and priority classifier discrimination are selected to obtain the pseudo labeled samples after learning. By making full use of the advantages of sparse representation and mixed logistic regression model, a new classification method based on semi-supervised learning is proposed to effectively achieve accurate classification of hyperspectral images. The data of Indian Pines, Salinas scene and Pavia University are selected to verify the validity of the proposed method. The experiment results have demonstrated that the proposed classification method is able to gain a higher classification accuracy, a stronger timeliness, and the generalization ability.

关键词： hyperspectral remote sensing image local binary pattern sparse representation mixed logistic regression neighborhood information

来源：评论

学校读者我要写书评

暂无评论

Weighted Constraint Feature Selection of local Descriptor for Texture Image Classification

引用

IEEE ACCESS 2023年 11卷 91673-91695页

作者： Gemeay, Entessar Saeed Alenizi, Farhan A. Mohammed, Adil Hussein Shakoor, Mohammad Hossein Boostani, Reza Taif Univ Comp & Informat Technol Coll Dept Comp Engn Taif 21944 Saudi Arabia Tanta Univ Coll Engn Dept Elect & Commun Engn Tanta 31527 Egypt Prince Sattam bin Abdulaziz Univ Coll Engn Elect Engn Dept Al Kharj 11942 Saudi Arabia Cihan Univ Erbil Fac Engn Dept Commun & Comp Engn Erbil 44001 Kurdistan Reg Iraq Arak Univ Fac Engn Dept Comp Engn Arak *** Iran Shiraz Univ Sch Elect & Comp Engn Comp Engn Dept Shiraz *** Iran

There are several statistical descriptors for feature extraction from texture images. local binary pattern is one of the most popular descriptors for revealing the underlying structure of a texture. Recently several variants of local binary descriptors have been proposed. The completed local binary pattern is an efficient version that can provide discriminant features and consequently provide a high classification rate. It finely characterizes a texture by fusing three histograms of features. Fusing histograms is applied by jointing the histograms and it increases the feature number significantly;therefore, in this paper, a weighted constraint feature selection approach is proposed to select a very small number of features without any degradation in classification accuracy. It significantly enhances the classification rate by using a very low number of informative features. The proposed feature selection approach is a filter-based feature selection. It employed a weighted constraint score for each feature. After ranking the features, a threshold estimation method is proposed to select the most discriminant features. For a better comparison, a wide range of different datasets is used as a benchmark to assess the compared methods. Implementations on Outex, UIUC, CUReT, MeasTex, Brodatz, Virus, Coral Reef, and ORL face datasets indicate that the proposed method can provide high classification accuracy without any learning step just by selecting a few features of the descriptor.

关键词： local binary pattern weighted constraint feature selection texture image classification

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：