检索结果-南通市图书馆

Effective and Efficient Multi-Facet Web image annotation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2012年第3期27卷 541-553页

作者：陈佳朱一和王昊奋晋薇俞勇 Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science North Dakota State University1340 Administration Ave.FargoND 58102U.S.A.

The vast amount of images available on the Web request for an effective and efficient search service to help users find relevant images. The prevalent way is to provide a keyword interface for users to submit queries. However, the amount of images without any tags or annotations are beyond the reach of manual efforts. To overcome this, automatic image annotation techniques emerge, which are generally a process of selecting a suitable set of tags for a given image without user intervention. However, there are three main challenges with respect to Web-scale image annotation： scalability, noise- resistance and diversity. Scalability has a twofold meaning： first an automatic image annotation system should be scalable with respect to billions of images on the Web; second it should be able to automatically identify several relevant tags among a huge tag set for a given image within seconds or even faster. Noise-resistance means that the system should be robust enough against typos and ambiguous terms used in tags. Diversity represents that image content may include both scenes and objects, which are further described by multiple different image features constituting different facets in annotation. In this paper, we propose a unified framework to tackle the above three challenges for automatic Web image annotation. It mainly involves two components： tag candidate retrieval and multi-facet annotation. In the former content-based indexing and concept-based eodebook are leveraged to solve scalability and noise-resistance issues. In the latter the joint feature map has been designed to describe different facets of tags in annotations and the relations between these facets. Tag graph is adopted to represent tags in the entire annotation and the structured learning technique is employed to construct a learning model on top of the tag graph based on the generated joint feature map. Millions of images from Flickr are used in our evaluation. Experimental results show that we have a

关键词： image annotation multi-facet web-scale

维普期刊数据库

Automatic image annotation Using Adaptive Convolutional Deep Learning Model

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第4期36卷 481-497页

作者： R.Jayaraj S.Lokesh Department of Computer Science and Engineering Hindusthan College of Engineering and TechnologyCoimbatore641032TamilnaduIndia Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032TamilnaduIndia

Every day,websites and personal archives create more and more *** size of these archives is *** comfort of use of these huge digital image gatherings donates to their ***,not all of these folders deliver relevant indexing *** the outcomes,it is dif-ﬁcult to discover data that the user can be absorbed ***,in order to determine the signiﬁcance of the data,it is important to identify the contents in an informative *** annotation can be one of the greatest problematic domains in multimedia research and computer ***,in this paper,Adap-tive Convolutional Deep Learning Model(ACDLM)is developed for automatic image ***,the databases are collected from the open-source system which consists of some labelled images(for training phase)and some unlabeled images{Corel 5 K,MSRC v2}.After that,the images are sent to the pre-processing step such as colour space quantization and texture color class *** pre-processed images are sent to the segmentation approach for efﬁcient labelling technique using J-image segmentation(JSEG).Theﬁnal step is an auto-matic annotation using ACDLM which is a combination of Convolutional Neural Network(CNN)and Honey Badger Algorithm(HBA).Based on the proposed classiﬁer,the unlabeled images are *** proposed methodology is imple-mented in MATLAB and performance is evaluated by performance metrics such as accuracy,precision,recall and F1_*** the assistance of the pro-posed methodology,the unlabeled images are labelled.

关键词： Deep learning model J-image segmentation honey badger algorithm convolutional neural network image annotation

image annotation with Nearest Neighbor Based on Semantic Information

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Image Annotation with Nearest Neighbor Based on Semantic Inf...

2015年中国智能自动化学术会议

作者： Wei Wu Guanglai Gao Department of Computer Science Inner Mongolia University

Most of the Nearest Neighbor(NN)-based image annotation methods do not achieve desired performances. The main reason is that much valuable information is lost when extracting visual features from image. In this paper, we propose a novel weighted NN-based method. Instead of using Euclidean distance, we learn a new distance metric with image semantic information to calculate the distance between the two images. Meanwhile, we utilize textual information of each image tagged by users to form weights of NN-based model. When introducing the semantic information, our method can minimize the semantic gap for intraclass variations and interclass similarities, and improve the annotation *** on image annotation dataset of image CLEF2012 show that our method outperforms the traditional classifiers. Moreover, our method is simple,efficient, and competitive compared with state-of-the-art learning-based models.

关键词： image annotation Nearest neighbor Distance metric learning Entropy weight

Simultaneous image classification and annotation based on probabilistic model

在线全文

cnki会议

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2012年第2期19卷 107-115页

作者： LI Xiao-xu SUN Chao-bo LU Peng WANG Xiao-jie ZHONG Yi-xin Center for Intelligence Science and Technology Beijing University of Posts and TelecommunicationsBeijing 100876China

The paper proposes a novel probabilistic generative model for simultaneous image classification and annotation. The model considers the fact that the category information can provide valuable information for image annotation. Once the category of an image is ascertained, the scope of annotation words can be narrowed, and the probability of generating irrelevant annotation words can be reduced. To this end, the idea that annotates images according to class is introduced in the model. Using variational methods, the approximate inference and parameters estimation algorithms of the model are derived, and efficient approximations for classifying and annotating new images are also given. The power of our model is demonstrated on two real world datasets： a 1 600-images LabelMe dataset and a 1 791-images UIUC-Sport dataset. The experiment results show that the classification performance is on par with several state-of-the-art classification models, while the annotation performance is better than that of several state-of-the-art annotation models.

关键词： image classification image annotation probabilistic model variational inference

维普期刊数据库

Semi-supervised image annotation with Parallel Graph Convolutional Networks

在线全文

学校读者我要写书评

暂无评论

Semi-supervised Image Annotation with Parallel Graph Convolu...

第40届中国控制会议

作者： Qianqian Shao Mengke Wang Jiaoyue Li Weifeng Liu Kai Zhang Baodi Liu College of Oceanography and Space Informatics China University of Petroleum (East China) College of Control Science and Engineering China University of Petroleum (East China) School of Petroleum Engineering China University of Petroleum (East China)

Automatic image annotation has increasingly exerted a tremendous fascination on researchers with the development of digital imaging in recent years. First, most works exploit the sufficient labeled data to train the models and trigger the unfavorable experimental performance in semi-supervised learning. Second, some examinations solve the semi-supervised problem only by a samples graph or tags graph, limiting in improving the annotation results owing to the incomplete data structure. To this end,we propose a method called "Semi-supervised image annotation with Parallel Graph Convolutional Networks（SPGCN）". This algorithm combines graph convolutional networks（GCN） with image annotation to promote annotation performance under semisupervised learning. Furthermore, SPGCN, connecting the tags graph with the samples graph, is proposed to improve annotation results, further considering tags’ distribution and features’ distribution to aggregate the features. Experiments on three benchmark image annotation datasets show that our approach outperforms other existing state-of-the-art methods.

关键词： Semi-supervised Parallel Graph Convolutional Networks Multi-graph image annotation

Human-in-the-loop image segmentation and annotation

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第11期63卷 290-292页

作者： Xiaoya ZHANG Lianjie WANG Jin XIE Pengfei ZHU Department of Computer Science and Engineering Nanjing University of Science and Technology College of Intelligence and Computing Tianjin University

Dear editor,Semantic segmentation aims to assign the category information to all pixels of an image and plays a vital role in image understanding. In the past few years, deep convolutional neural networks have achieve... 详细信息

关键词： Semantic segmentation Active learning Human-machine collaboration Pseudo labelling image annotation

A Novel Approach to Enhance Web image annotation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Novel Approach to Enhance Web Image Annotation

第四届全国信息检索与内容安全学术会议

作者： Liu Zheng~(1,2,+) Ma Jun~1 ~1 School of computer science and technology,Shandong University,dinah 250101,China ~2 School of computer science and technology,Shandong Economic University,Jinan 250014,China

A novel approach to automatically enhance the initial annotations of Web images is presented in this paper. Given a Web image,a set of initial annotations is extracted from the surrounding text and other textual information of the hosting Web page.A concept ontology is used to achieve hierarchical probabilistic image concept reasoning for multi-level image *** this concept reasoning process,a set of extended annotations is *** initial annotations and the extended annotations are considered as two disjoint sets of graph vertices to construct a bipartite ***,an annotation enhancing algorithm is used to re-rank the candidate annotations based on the bipartite graph. Finally,the annotations with the highest ranking scores are reserved as the final *** results demonstrate the effectiveness of our approach for Web image annotation.

关键词： image Retrieval image annotation Bipartite Graph Concept Ontology

image Semantic annotation based on BP Neural Network Algorithm

在线全文

cnki会议

学校读者我要写书评

暂无评论

Image Semantic Annotation based on BP Neural Network Algorit...

中国电子学会第十五届信息论学术年会暨第一届全国网络编码学术年会

作者： Liu Gang Zhu Wen-qiu School of Computer and Communication,Hunan University of Technology,Hunan Zhuzhou,412008,China

Because of the"Semantic gab" problem in the traditional CBIR(content-based image retrieval)systems,they are not fit in some special *** appearance of image-Semantic-annotation can effectively resolve this *** paper repre- sents a method that first uses the Normalized Cuts to cut the image into several areas and then extract the low-level features,last use BP neural network algorithm to learn the relations between the areas and the annotation *** experiment’s results proved this method is valid and efficient.

关键词： image annotation BP Neural Network Normalized Cuts Low-level Feature

image categorization using a semantic hierarchy model with sparse set of salient regions

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2013年第6期7卷 838-851页

作者： Chunping LIU Yang ZHENG Shengrong GONG School of Computer Science and Technology Soochow University Suzhou 215006 China The Second Hospital of Nanjing Nanjing 210003 China

image categorization in massive image database is an important problem. This paper proposes an approach for image categorization, using sparse set of salient semantic information and hierarchy semantic label tree （HSLT） model. First, to provide more critical image semantics, the proposed sparse set of salient regions only at the focuses of visual attention instead of the entire scene was formed by our proposed saliency detection model with incorporating low and high level feature and Shotton＇s semantic texton forests （STFs） method. Second, we also propose a new HSLT model in terms of the sparse regional semantic information to automatically build a semantic image hierarchy, which explicitly encodes a general to specific image relationship. And last, we archived image dataset using image hierarchical semantic, which is help to improve the performance of image organizing and browsing. Extension experimefital results showed that the use of semantic hierarchies as a hierarchical organizing frame- work provides a better image annotation and organization, improves the accuracy and reduces human＇s effort.

关键词： salient region sparse set semantic hierarchy image annotation image categorization

维普期刊数据库