检索结果-南通市图书馆

Enhanced Object Detection and Classification via Multi-Method Fusion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 3315-3331页

作者： Muhammad Waqas Ahmed Nouf Abdullah Almujally Abdulwahab Alazeb Asaad Algarni Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Engineering Tech University of Korea237 Sangidaehak-roSiheung-siGyeonggi-do15073South Korea

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented *** substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled *** address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection *** proposed approach involves the integration ofmultiple methods in a complementary *** process commences with the application of Gaussian filters tomitigate the impact of noise *** images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent *** Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented *** precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms *** Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved *** method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize *** minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall *** proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,***,detection accuracies of 87.2%and 86.6%have been *** ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex *** these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

关键词： BRIEF features saliency map fuzzy c-means object detection object recognition

Visual perception driven collage synthesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第1期8卷 79-91页

作者： Zuyi Yang Qinghui Dai Junsong Zhang Department of Artificial Intelligence Xiamen UniversityXiamen 361005China.

A collage is a composite artwork made from the spatial layout of multiple pictures on a canvas,collected from the Internet or user ***,usually made by skilled artists,involve a complex manual process,especially when searching for component pictures and adjusting their spatial layout to meet artistic *** this paper,we present a visual perception driven method for automatically synthesizing visually pleasing *** previous works,we focus on how to design a collage layout which not only provides easy access to the theme of the overall image,but also conforms to human visual *** achieve this goal,we formulate the generation of collages as a mapping problem:given a canvas image,first,compute a saliency map for it and a vector field for each sub-region of ***,using a divide-and-conquer strategy,generate a series of patch sets from the canvas image,where the salient map and the vector field are used to determine each patch’s size and direction ***,construct a Gestalt-based energy function to choose the most visually pleasing and orderly patch set as the final ***,using a semantic-color metric,map the picture set to the patch set to generate the final *** experimental and user study results show that this method can generate visual pleasing collages.

关键词： collage gestalt psychology saliency map layout optimization human visual perception

维普期刊数据库

Interpreting Randomly Wired Graph Models for Chinese NER

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第1期134卷 747-761页

作者： Jie Chen Jiabao Xu Xuefeng Xi Zhiming Cui Victor S.Sheng The School of Electronic and Information Engineering SuzhouUniversity of Science and TechnologySuzhouChina The School of Computer Science Texas Tech UniversityTexasUSA

Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)***,most existing approaches only focus on improving the performance of models but ignore their *** this work,we propose a Randomly Wired Graph Neural Network(RWGNN)by using graph to model the structure of Neural Network,which could solve two major problems(word-boundary ambiguity and polysemy)of ***,we develop a pipeline to explain the RWGNNby using saliency map and Adversarial *** results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.

关键词： Named entity recognition graph neural network saliency map random graph network interpretation

ELM-Based Shape Adaptive DCT Compression Technique for Underwater Image Compression

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第5期45卷 1953-1970页

作者： M.Jamuna Rani C.Vasanthanayaki Sona College of Technology SalemIndia Government College of Engineering SalemIndia

Underwater imagery and transmission possess numerous challenges like lower signal bandwidth,slower data transmission bit rates,Noise,underwater blue/green light haze *** factors distort the estimation of Region of Interest and are prime hurdles in deploying efficient compression *** to the presence of blue/green light in underwater imagery,shape adaptive or block-wise compression techniques faces failures as it becomes very difficult to estimate the compression levels/coefficients for a particular *** method is proposed to efficiently deploy an Extreme Learning Machine(ELM)model-based shape adaptive Discrete Cosine Transformation(DCT)for underwater *** color image restoration techniques based on veiling light estimation and restoration of images followed by saliency map estimation based on Gray Level Cooccurrence Matrix(GLCM)features are *** ELM network is modeled which takes two parameters,signal strength and saliency value of the region to be compressed and level of compression(DCT coefficients and compression steps)are predicted by *** method ensures lesser errors in the Region of Interest and a better trade-off between available signal strength and compression level.

关键词： Extreme learning machine discrete cosine transform saliency map

The Cat's Eye Effect Target Recognition Method Based on Visual Attention

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第5期28卷 1080-1086页

作者： WANG Xingbin ZHANG Jun WANG Shuaihui State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Science University of Chinese Academy of Sciences Hubei University of Arts and Science Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences

The Cat’s eye effect target recognition method based on visual attention(CTRVA) is *** difference image can be processed by a designed second-directional derivative filter at eight directional channels. Morphological method is employed to deal with the filtered image in all directions, which ensures that target can be easily distinguished from background. The salient maps for each channel where the potential targets exist are calculated through the spectral residual approach,and the "target-saliency" map is computed by a designed saliency fusing method. The coarse detection is performed by the adaptive threshold to extract candidate targets from the "target-saliency" map. The real target region is identified by the characteristics of the cat’s eye effect target. Experimental results show that the proposed method is efficient and has an outstanding performance for cat’s eye effect target detection.

关键词： Cat’s eye effect target recognition method based on visual attention(CTRVA) Target recognition saliency map

A Convolutional Neural Network Classifier VGG-19 Architecture for Lesion Detection and Grading in Diabetic Retinopathy Based on Deep Learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第1期66卷 827-842页

作者： V.Sudha T.R.Ganeshbabu Department of Electronics and Communication Engineering Pavai College of TechnologyNamakkal637018India Department of Electronics and Communication Engineering Muthayammal Engineering CollegeRasipuram637408India

Diabetic Retinopathy(DR)is a type of disease in eyes as a result of a diabetic condition that ends up damaging the retina,leading to blindness or loss of *** and physiological retinal variations involving slowdown of blood flow in the retina,elevation of leukocyte cohesion,basement membrane dystrophy,and decline of pericyte cells,*** DR in its initial stage has no symptoms,early detection and automated diagnosis can prevent further visual *** this research,using a Deep Neural Network(DNN),segmentation methods are proposed to detect the retinal defects such as exudates,hemorrhages,microaneurysms from digital fundus images and then the conditions are classified accurately to identify the grades as mild,moderate,severe,no PDR,PDR in ***,saliency detection is applied on color images to detect maximum salient foreground objects from the ***,structure tensor is applied powerfully to enhance the local patterns of edge elements and intensity changes that occur on edges of the ***,active contours approximation is performed using gradient descent to segment the lesions from the ***,the output images from the proposed segmentation process are subjected to evaluate the ratio between the total contour area and the total true contour arc length to label the classes as mild,moderate,severe,No PDR and *** on the computed ratio obtained from segmented images,the severity levels were ***,statistical parameters like the mean and the standard deviation of pixel intensities,mean of hue,saturation and deviation clustering,are estimated through K-means,which are computed as features from the output images of the proposed segmentation *** these derived feature sets as input to the classifier,the classification of DR was ***,a VGG-19 deep neural network was trained and tested using the derived feature sets from the KAGGLE fundus image dataset containing 35,126 images in

关键词： Diabetic retinopathy saliency map structure tensor gradient descent method exudates haemorrhages microaneurysms VGG-19

Infrared and Visible Image Fusion Based on Region of Interest Detection and Nonsubsampled Contourlet Transform

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2013年第5期18卷 526-534页

作者：刘欢喜朱天竑赵佳佳 School of Electronic Information and Electrical Engineering Shanghai Jiaotong University Jiangsu Junlong Power Technology Co. Ltd. Beijing Institute of Mechanical and Electrical Engineering

In order to enhance the contrast of the fused image and reduce the loss of fine details in the process of image fusion,a novel fusion algorithm of infrared and visible images is *** of all,regions of interest(RoIs)are detected in two original images by using saliency ***,nonsubsampled contourlet transform(NSCT)on both the infrared image and the visible image is performed to get a low-frequency sub-band and a certain amount of high-frequency ***,the coefcients of all sub-bands are classified into four categories based on the result of RoI detection:the region of interest in the low-frequency sub-band(LSRoI),the region of interest in the high-frequency sub-band(HSRoI),the region of non-interest in the low-frequency sub-band(LSNRoI)and the region of non-interest in the high-frequency sub-band(HSNRoI).Fusion rules are customized for each kind of coefcients and fused image is achieved by performing the inverse NSCT to the fused *** results show that the fusion scheme proposed in this paper achieves better efect than the other fusion algorithms both in visual efect and quantitative metrics.

关键词： image fusion region of interest(RoI) detection saliency map nonsubsampled contourlet transform(NSCT)

维普期刊数据库

Seamlet carving for shape-aware image resizing

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2012年第5期55卷 1073-1081页

作者： LIN Xiao 1,2,SHENG Bin 1,MA LiZhuang 1,SHEN Yang 1 & CHEN ZhiHua 3 1 Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China 2 Academy of Information Technology,Luoyang Normal University,Luoyang 471022,China 3 Department of Computer Science and Engineering,East China University of Science and Technology,Shanghai 200237,China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Academy of Information Technology Luoyang Normal University Luoyang China Department of Computer Science and Engineering East China University of Science and Technology Shanghai China

In this paper we propose an optimized seam-carving approach for anti-shearing image *** image/video seam-carving strategy only focuses on deleting the pixels along 8-connected seams,which may lead to the obvious information loss during *** the traditional seam-carving methods,our approach can construct a seamlet to handle the discontinuous pixels and further achieve an optimized image resizing results with *** particular,to suppress zigzag artifacts,we introduce the anti-shearing energy into the seamlet generation,which includes two steps:1) the energy map is formalized by using Gabor filtering and the saliency map;2) The energy computation is optimized in Gabor feature space to obtain the resizing results without the connectivity *** experimental results and comparisons show the effectiveness of our method.

关键词： image resizing seamlet carving saliency map

Remote Sensing Image Scene Classification via Multi-feature Fusion

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Remote Sensing Image Scene Classification via Multi-feature ...