检索结果-内蒙古大学图书馆

A sparse representation-based local occlusion recognition method for athlete expressions

INTERNATIONAL JOURNAL OF BIOMETRICS 2024年第3-4期16卷 287-299页

作者： Huang, Shaowu St Paul Univ Grad Sch Tuguegarao 3500 Cagayan Philippines

A sparse representation-based local occlusion recognition method for athlete expressions is proposed to address the problems of large mean square error, low recall rate, and poor recognition performance. We calculate the gradient direction and size of image pixels, divide image blocks, count the histogram of the gradient direction of the image blocks, combine all small histograms into a feature vector, and obtain the facial feature extraction results. The lbp algorithm is used for local occlusion image segmentation, and a sparse representation model is established to extract expression features. By dividing the image into blocks and solving the sparse representation coefficients of each block, local occlusion expression recognition is achieved. Experimental results show that the maximum mean squared error of the proposed method for facial expression recognition is only 0.21, and the maximum recall rate is more than 80%, which shows that it can effectively recognise occluded parts.

关键词： sparse representation localised occlusion of facial expressions HOG lbp algorithm feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dual UNet low-light image enhancement network based on attention mechanism

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第16期82卷 24707-24742页

作者： Liu, Fangjin Hua, Zhen Li, Jinjiang Fan, Linwei Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai 264005 Peoples R China Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Peoples R China Shandong Univ Finance & Econ Sch Comp Sci & Technol Jinan Shandong Peoples R China

Low-light image enhancement has been an important research direction in the field of image processing. Recently, U-Net networks have shown better promise in low-light image enhancement. However, because of the semantic gap and the lack of connection between global contextual information in the U-shaped network, it leads to problems such as inaccurate color information in the enhanced images. To address the above problems, this paper proposes a Dual UNet low-light image enhancement network (DUAMNet) based on an attention mechanism. Firstly, the local texture features of the original image are extracted using the Local Binary Pattern(lbp) operator, and the illumination invariance of the lbp operator better maintains the texture information of the original image. Next, use the Brightness Enhancement Module(BEM). In the BEM module, the outer U-Net network captures feature information at different levels and luminance information of different regions, and the inner densely connected U-Net++ network enhances the correlation of feature information at different levels, mines more hidden feature information extracted by the encoder, and reduces the feature semantic gap between the encoder and decoder. The attention module Convolutional Block Attention Module(CBAM) is introduced in the decoder of U-Net++ network. CBAM further enhances the ability to model the global contextual information linkage and effectively improves the network's attention to the weak light region. The network adopts a progressive recursive structure. The entire network includes four recursive units, and the output of the previous recursive unit is used as the input of the next recursive unit. Comparative experiments are conducted on seven public datasets, and the results are analyzed quantitatively and qualitatively. The results show that despite the simple structure of the network in this paper, the network in this paper outperforms other methods in image quality compared to other methods.

关键词： Low light enhancement lbp algorithm Double UNet Attention model Recursive calculation

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Method Based on Siamese Networks Under Non-Restricted Conditions

引用

IEEE ACCESS 2022年 10卷 40432-40444页

作者： Song, Cunli Ji, Shouyong Dalian Jiaotong Univ Coll Software Dalian 116052 Liaoning Peoples R China

Face recognition is an important part of computer vision, and has a vital role to play in public safety. Because of the problems of low accuracy and low efficiency in the case of uneven image quality and occlusion due to sudden changes in light in face recognition, we design a Siamese Neural Network based on Local Binary Pattern (also called lbp) and Frequency Feature Perception. The network is based on the Siamese neural network and adopts the Uniform lbp algorithm and Frequency Feature perception to achieve face recognition under non-restricted conditions. the lbp algorithm can eliminate the effect of lighting on the image and provide vector-level input to the network model;the frequency feature perception divides the image features into low-frequency features and high-frequency features, and compresses the low-frequency features in the Siamese neural network to increase the network's recognition efficiency while exchanging information with high-frequency features to retain their feature data while eliminating target noise data. This maintains the recognition rate of the network and improves the computational speed of the network. Simulation experiments are conducted on the standard face datasets CASIA-WebFace, Yale-B, and LFW, and compared with other network models. The experimental results show that the proposed SN-LF network structure in this paper can improve the recognition accuracy of the algorithm and obtain a better recognition accuracy.

关键词： Face recognition Feature extraction Neural networks Image recognition Target recognition Licenses Convolution Artificial intelligence face recognition Siamese neural network lbp algorithm frequency feature perception

来源：评论

学校读者我要写书评

暂无评论

Local features integration for content-based image retrieval based on color, texture, and shape

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第18期80卷 28245-28263页

作者： Ghahremani, Mona Ghadiri, Hamid Hamghalam, Mohammad Darolfonoon Univ Dept Control Elect Engn Qazvin Iran Islamic Azad Univ Fac Elect Biomed & Mechatron Engn Qazvin Branch Qazvin Iran

Imaging techniques like computed tomography (CT) and ultrasound are employed to provide valuable information for physicians, including size, contour, and internal organs' anatomical information. Information retrieval systems can be used to deliver on-time information to the radiologists when some sections of scans are lost. In this study, a new content-based image retrieval (CBIR) model based on an effective combination of color, texture, and shape features is proposed to reconstruct these images' corrupted portions. For this purpose, image scans are normalized, and their noise is reduced by employing a median filter. Then, the color channel shift is modified utilizing the Simple Linear Iterative Clustering (SLIC) superpixel. Afterward, a Histogram of Oriented Gradients (HOG) descriptor is introduced to enhance image contrast and feature extraction. Finally, local thresholding based on Local Binary Patterns (lbp) is performed to separate the image details into three components to examine the light and edge intensity. The proposed method is experimented on several images by evaluating the texture, color, and shape morphology of the reconstructed images compared to the ground truth. The highest content retrieval rate of 90.54% on a liver CT scan image demonstrates the proposed method's efficiency compared with former state-of-the-art approaches.

关键词： Content-based image retrieval (CBIR) Medical image processing Morphology lbp algorithm HOG descriptor

来源：评论

学校读者我要写书评

暂无评论

Research on the Identification of Hand-Painted Thangka and Printed Thangka Based on Computer Vision Processing Method 1

引用

3rd EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2021

作者： Pan, Chunhua Zhao, Decai Ren, Jinglong Cui, Shumin Li, Wenjing Computer College of Qinghai Nationalities University Qinghai Xining810007 China Physics and Electronic Information Engineering College of Qinghai Nationalities University Qinghai Xining810007 China Qinghai Qianxun Information Technology Co. Ltd. Qinghai Xining810007 China

ISBN: (数字)9783030901998

ISBN: (纸本)9783030901981

Thangka is a unique painting art form in Tibetan culture. As Thangka was listed as the first batch of national intangible cultural heritage, it has received more and more attention. At the same time, many printed thangkas appeared on the market, and some merchants mixed printed thangkas with hand-painted thangkas and sold them at high prices. How to distinguish between hand-painted thangkas and machine-printed thangkas, and to guide the inheritance and protection of hand-painted thangkas is an important issue. Based on the analysis of the characteristics of thangkas, combined with related computer vision processing methods, this paper conducts method research and model construction, uses the lbp algorithm to analyze the texture of the canvas, identifies the canvas of the thangka based on the training results, and uses restricted Boltzmann's light transmittance analysis of thangkas, and the use of clustering method to analyze the gold line of thangkas and other methods combined, proposed a feasible method of identifying hand-painted thangkas and machine-printed thangkas. This method should play a significant role in the protection and inheritance of the country. This specification is set for scientific papers published in "Computer Applications and Software". The author is requested to read and implement one by one, if it does not meet the requirements, it will affect the publication of the article. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Clustering method Hand-painted thangka lbp algorithm Machine-printed thangka Restricted Boltzmann algorithm

来源：评论

学校读者我要写书评

暂无评论

A Quantitative and Comparative Analysis on Variations of a Method for Segmentation of Similar Images 38

A Quantitative and Comparative Analysis on Variations of a M...

引用

38th International Conference of the Chilean-Computer-Science-Society (SCCC)

作者： de Souza, Juliana Goncalves Flores, Franklin Cesar Neto, Joao Choma Univ Estadual Maringa Dept Informat Maringa Parana Brazil

ISBN: (纸本)9781728156132

Segmenting images is one of the most famous image processing and computer vision's challenge. In this work we present an approach to a method of segmentation of similar images based on hierarchical segmentation and texture information. An empirical study was conducted, it was made of three experiments. First experiment evaluated the P parameter's variation of the lbp texture extractor and the use of external edges of analyzed region;the second one evaluated the variation of eight gradients, being 7 colored gradients;and the last one compares results between Kullback-Leibler measure and Euclidean distance. The obtained results show the best configurations.

关键词： Segmentation of similar images Hierarchical segmentation Texture analysis lbp algorithm Image matching

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Mixed-Scheduling Belief Propagation for LDPC Decoders in OFDM System under Double Fading Channels 7

Performance Analysis of Mixed-Scheduling Belief Propagation ...

引用

7th International Electrical Engineering Congress (iEECON)

作者： Prakodrat, Mayura Sopon, Thanomsak Puntsri, Kidsanapong Wongsuthavas, Sasiphan Wongtrairat, Wanaree Rajamangala Univ Technol Isan Fac Engn & Architecture Dept Elect Engn Nakhon Ratchasima Thailand Rajamangala Univ Technol Isan Fac Engn Dept Elect & Telecommun Engn Khonkhaen Campus Nakhon Ratchasima Thailand Rajamangala Univ Technol Isan Fac Sci & Liberal Arts Dept Agr Technol & Environm Nakhon Ratchasima Thailand

ISBN: (纸本)9781728107295

This paper presents the performance analysis of orthogonal frequency division multiplexing (OFDM) system using a mixed-scheduling belief propagation (MBP) algorithm for LDPC decoding where a double fading channels is considered. The MBP method is designed based on the lbp algorithm for the left-to-right direction (lbp-LR) and right-to-left direction (lbp-RL). Additionally, the bit error rate (BER) performance comparison of the BP, lbp, and MBP algorithms for LDPC decoding is proposed. The simulation results showed that the bit error rate (BER) performance of the MBP gave better BER than the BP and lbp algorithms, respectively.

关键词： OFDM system LDPC decoding MBP algorithm lbp algorithm BP algorithm double fading

来源：评论

学校读者我要写书评

暂无评论

Research on Image Feature Extraction in Efficient Visual Modeling System

引用

AGRO FOOD INDUSTRY HI-TECH 2017年第3期28卷 1958-1962页

作者： Zhou Xiaoning Jie, Li Yue, Chen Nanhang Jincheng Coll Nanjing 211156 Jiangsu Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing 210016 Jiangsu Peoples R China

As an important part of visual information, texture feature has become the focus of image feature extraction. In the case of texture feature extraction, the traditional lbp algorithm is based on the gray level algorithm, and it only extracts the low resolution image, so its recognition rate is usually low. lbp algorithm based on wavelet transform was proposed in this paper. The algorithm can combine the characteristics of the lbp algorithm and wavelet transform rotation, so as to decompose the high resolution image by wavelet transform. It has optimized the image texture feature extraction method.

关键词： Visual information lbp algorithm wavelet transform texture feature

来源：评论

学校读者我要写书评

暂无评论

A RELIABLE METHOD FOR PAPER CURRENCY RECOGNITION BASED ON lbp

A RELIABLE METHOD FOR PAPER CURRENCY RECOGNITION BASED ON LB...

引用

2010 2nd IEEE International Conference on Network Infrasturcture & Digital Content(2010年第二届IEEE网络基础设施与数字内容国际会议 IC-NIDC 2010)

作者： Junfang Guo Yanyun Zhao Anni Cai Multimedia Communication and Pattern Recognition Labs Beijing University of Posts and Telecommunicat Multimedia Communication and Pattern Recognition Labs Beijing University of Posts and Telecommunica

Paper currency recognition with good accuracy and high processing speed has great importance for banking system. How to extract high quality monetary features from currency images is a key problem in paper currency recognition. Based on the traditional local binary pattern (lbp) method, an improved lbp algorithm, called block-lbp algorithm, is proposed in this paper for characteristic extraction. The proposed method has advantages of simplicity and high speed. The experimental results show that this improved method has a high recognition rate, as well as robustness for noise and illumination change.

关键词： paper currency recognition feature extraction lbp algorithm

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：