Image Auto-annotation Research Articles

Face Mask Detection using Deep Learning to Manage Pandemic Guidelines

The field of Computer Vision is a branch of science of the computers and systems of software in which one can visualize and as well as comprehend the images and scenes given in the input. This field is consisting of numerous aspects for example image recognition, the detection of objects, generation of images, image super-resolution and more others. Object detection is broadly utilized for the detection of faces, the detection of vehicles, counting of pedestrians on a certain street, images displayed on the web, security systems and cars with the feature of self-driving. This process also encompasses the precision of every technique for recognizing the objects. The detection of objects is a crucial task; however, it is also a very challenging vision task. It is an analytical subdivide of various applications such as searching of images, image auto-annotation or scene understanding and tracking of various objects. The tracking of objects in motion of video image sequence was one of the most important subjects in computer vision.

CM-supplement network model for reducing the memory consumption during multilabel image annotation.

With the rapid development of the Internet and the increasing popularity of mobile devices, the availability of digital image resources is increasing exponentially. How to rapidly and effectively retrieve and organize image information has been a hot issue that urgently must be solved. In the field of image retrieval, image auto-annotation remains a basic and challenging task. Targeting the drawbacks of the low accuracy rate and high memory resource consumption of current multilabel annotation methods, this study proposed a CM-supplement network model. This model combines the merits of cavity convolutions, Inception modules and a supplement network. The replacement of common convolutions with cavity convolutions enlarged the receptive field without increasing the number of parameters. The incorporation of Inception modules enables the model to extract image features at different scales with less memory consumption than before. The adoption of the supplement network enables the model to obtain the negative features of images. After 100 training iterations on the PASCAL VOC 2012 dataset, the proposed model achieved an overall annotation accuracy rate of 94.5%, which increased by 10.0 and 1.1 percentage points compared with the traditional convolution neural network (CNN) and double-channel CNN (DCCNN). After stabilization, this model achieved an accuracy of up to 96.4%. Moreover, the number of parameters in the DCCNN was more than 1.5 times that of the CM-supplement network. Without increasing the amount of memory resources consumed, the proposed CM-supplement network can achieve comparable or even better annotation effects than a DCCNN.

Neural ranking for automatic image annotation

Automatic image annotation aims to predict labels for images according to their semantic contents and has become a research focus in computer vision, as it helps people to edit, retrieve and understand large image collections. In the last decades, researchers have proposed many approaches to solve this task and achieved remarkable performance on several standard image datasets. In this paper, we propose a novel learning to rank approach to address image auto-annotation problem. Unlike typical learning to rank algorithms for image auto-annotation which directly rank annotations for image, our approach consists of two phases. In the first phase, neural ranking models are trained to rank image’s semantic neighbors. Then nearest-neighbor based models propagate annotations from these semantic neighbors to the image. Thus our approach integrates learning to rank algorithms and nearest-neighbor based models, including TagProp and 2PKNN, and inherits their advantages. Experimental results show that our method achieves better or comparable performance compared with the state-of-the-art methods on four challenging benchmarks including Corel5K, ESP Games, IAPR TC-12 and NUS-WIDE.

Training Visual-Semantic Embedding Network for Boosting Automatic Image Annotation

Image auto-annotation which annotates images according to their semantic contents has become a research focus in computer vision, as it helps people to edit, retrieve and understand large image collections. In the last decades, researchers have proposed many approaches to solve this task and achieved remarkable performance on several standard image datasets. In this paper, we train neural networks using visual and semantic ranking loss to learn visual-semantic embedding. This embedding can be easily applied to nearest-neighbor based models to boost their performance on image auto-annotation. We test our method on four challenging image datasets, reporting comparison results with existing works. Experimental results show that our method can be applied to several state-of-the-art nearest-neighbor based models including TagProp and 2PKNN, and significantly improves their performance.

A Method of the Semantic on Image Auto-Annotation

Recently, due to the existence of semantic gap between image visual features and human concepts, the seman- tic of image auto-annotation has become an important topic. Firstly, by extract low-level visual features of the image, and the corresponding Hash method, mapping the feature into the corresponding Hash coding, eventually, transformed that into a group of binary string and store it, image auto-annotation by search is a popular method, we can use it to design and implement a method of image semantic auto-annotation. Finally, Through the test based on the Corel image set, and the results show that, this method is effective.

Image auto-annotation via concept interdependency network

With the explosive growth of multimedia data such as unlabeled images on the Web, image auto-annotation has been receiving increasing research interest. By automatically assigning a set of concepts...

Web Image Annotation By Diffusion Maps Manifold Learning Algorithm

Automatic image annotation is one of the most challenging problems in machine vision areas. The goal of this task is to predict number of keywords automatically for images captured in real data. Many methods are based on visual features in order to calculate similarities between image samples. But the computation cost of these approaches is very high. These methods require many training samples to be stored in memory. To lessen this burden, a number of techniques have been developed to reduce the number of features in a dataset. Manifold learning is a popular approach to nonlinear dimensionality reduction. In this paper, we investigate Diffusion maps manifold learning method for web image auto-annotation task. Diffusion maps manifold learning method is used to reduce the dimension of some visual features. Extensive experiments and analysis on NUS-WIDE-LITE web image dataset with different visual features show how this manifold learning dimensionality reduction method can be applied effectively to image annotation.

Image tag completion via dual-view linear sparse reconstructions

User-provided textual tags of web images are widely utilized for facilitating image management and retrieval. Yet they are usually incomplete and insufficient to describe the whole semantic content of the corresponding images, resulting in performance degradations of various tag-dependent applications. In this paper, we propose a novel method denoted as DLSR for automatic image tag completion via Dual-view Linear Sparse Reconstructions. Given an incomplete initial tagging matrix with each row representing an image and each column representing a tag, DLSR performs tag completion from both views of image and tag, exploiting various available contextual information. Specifically, for a to-be-completed image, DLSR exploits image-image correlations by linearly reconstructing its low-level image features and initial tagging vector with those of others, and then utilizes them to obtain an image-view reconstructed tagging vector. Meanwhile, by linearly reconstructing the tagging column vector of each tag with those of others, DLSR exploits tag-tag correlations to get a tag-view reconstructed tagging vector with the initially labeled tags. Then both image-view and tag-view reconstructed tagging vectors are combined for better predicting missing related tags. Extensive experiments conducted on benchmark datasets and real-world web images well demonstrate the reasonableness and effectiveness of the proposed DLSR. And it can be utilized to enhance a variety of tag-dependent applications such as image auto-annotation.

Image auto-annotation via tag-dependent random search over range-constrained visual neighbours

The quantity setting of visual neighbours can be critical for the performance of many previously proposed visual-neighbour-based (VNB) image auto-annotation methods. And in those methods, each candidate tag of a to-be-annotated image would be better to have its own trustworthy part of visual neighbours for score prediction. Hence in this paper we propose to use a constrained range rather than an identical and fixed number of visual neighbours for VNB methods to allow more flexible choices of neighbours, and then put forward a novel tag-dependent random search process to estimate the tag-dependent trust degrees of visual neighbours for each candidate tag. We further propose an effective image auto-annotation method termed TagSearcher based on a widely-used conditional probability model for auto-annotation, considering image-dependent weights of visual neighbours, tag-dependent trust degrees of visual neighbours and votes for a candidate tag from visual neighbours. Extensive experiments conducted on both a benchmark dataset and real-world web images present that the proposed TagSearcher can yield inspiring annotation performance and also reduce the performance sensitivity to the quantity setting of visual neighbours.

Image auto-annotation with automatic selection of the annotation length

Developing a satisfactory and effective method for auto-annotating images that works under general conditions is a challenging task. The advantages of such a system would be manifold: it can be used to annotate existing, large databases of images, rendering them accessible to text search engines; or it can be used as core for image retrieval based on a query image’s visual content. Manual annotation of images is a difficult, tedious and time consuming task. Furthermore, manual annotations tend to show great inter-person variance: considering an image, the opinions about what elements are significant and deserve an annotation vary strongly. The latter poses a problem for the evaluation of an automatic method, as an annotation’s correctness is greatly subjective. In this paper we present an automatic method for annotating images, which addresses one of the existing methods’ major limitation, namely a fixed annotation length. The proposed method, PATSI, automatically chooses the resulting annotation’s length for each query image. It is held as simple as possible and a build-in parameter optimization procedure renders PATSI de-facto parameter free. Finally, PATSI is evaluated on standard datasets, outperforming various state-of-the-art methods.

Resulted word counts optimization—A new approach for better automatic image annotation

One of major problems in image auto-annotation is the difference between the expected word counts vector and the resulted word counts vector. This paper presents a new approach to automatic image annotation—an algorithm called resulted word counts optimizer which is an extension to existing methods. An ideal annotator is defined in terms of recall quality measure. On the basis of the ideal annotator an optimization criterion is defined. It allows to reduce the difference between resulted and expected word counts vectors. The proposed algorithm can be used with various image auto-annotation algorithms because its generic nature. Additionally, it does not increase the computational complexity of the original annotation method processing phase. It changes output word probabilities according to a pre-calculated vector of correction coefficients.

Erratum: Inverting a Sum of Matrices

Previous article Next article Full AccessErratum: Inverting a Sum of MatricesWalter W. Piegorsch and George CasellaWalter W. Piegorsch and George Casellahttps://doi.org/10.1137/1032080PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAbout"Erratum: Inverting a Sum of Matrices." SIAM Review, 32(3), p. 470[1] M. S. Bartlett, An inverse matrix adjustment arising in discriminant analysis, Ann. Math. Statistics, 22 (1951), 107–111 12,639c 0042.38203 CrossrefISIGoogle Scholar[2] E. Bodewig, Matrix calculus, 2nd revised and enlarged edition, North-Holland Publishing Co., Amsterdam, 1959xi+452 23:B563 0086.32501 Google Scholar[3] Alston S. Householder, The theory of matrices in numerical analysis, Blaisdell Publishing Co. Ginn and Co. New York-Toronto-London, 1964xi+257 30:5475 0161.12101 Google Scholar[4] Walter W. Piegorsch and , George Casella, The early use of matrix diagonal increments in statistical problems, SIAM Rev., 31 (1989), 428–434 10.1137/1031089 90g:65044 0686.65013 LinkISIGoogle Scholar[5] J. Sherman and , W. J. Morrison, Adjustment of an inverse matrix corresponding to changes in the elements of a given column or given row of the original matrix, Ann. Math. Statist., 20 (1949), 621– ISIGoogle Scholar[6] M. A. Woodbury, Inverting modified matrices, Tech. Report, 42, Statistical Research Group, Princeton University, Princeton, NJ, 1950 Google Scholar Previous article Next article FiguresRelatedReferencesCited byDetails A Survey on Personalized PageRank Computation AlgorithmsIEEE Access, Vol. 7 Cross Ref Attributed Network Alignment: Problem Definitions and Fast SolutionsIEEE Transactions on Knowledge and Data Engineering Cross Ref Reducing seed noise in personalized PageRank5 January 2016 | Social Network Analysis and Mining, Vol. 6, No. 1 Cross Ref Random Walk with Restart on Large Graphs Using Block Elimination11 May 2016 | ACM Transactions on Database Systems, Vol. 41, No. 2 Cross Ref Locality-sensitive and Re-use Promoting Personalized PageRank computations18 June 2015 | Knowledge and Information Systems, Vol. 47, No. 2 Cross Ref SimRank Based Top-k Query Aggregation for Multi-Relational Networks6 June 2015 Cross Ref Gateway finder in large graphs: problem definitions and fast solutions16 February 2012 | Information Retrieval, Vol. 15, No. 3-4 Cross Ref A CFAR Adaptive Subspace Detector for First-Order or Second-Order Gaussian Signals Based on a Single ObservationIEEE Transactions on Signal Processing, Vol. 59, No. 11 Cross Ref Image Auto-annotation with Graph Learning Cross Ref A fast solution for automatic image annotation based on multi-modal graph Cross Ref Proximity Tracking on Dynamic Bipartite Graphs: Problem Definitions and Fast Solutions13 August 2010 Cross Ref BASSET: Scalable Gateway Finder in Large Graphs Cross Ref Fast Manifold-Ranking for Content-Based Image Retrieval Cross Ref Measuring Proximity on Graphs with Side Information Cross Ref Fast Monitoring Proximity and Centrality on Time-evolving Bipartite GraphsStatistical Analysis and Data Mining, Vol. 1, No. 3 Cross Ref Random walk with restart: fast solutions and applications4 July 2007 | Knowledge and Information Systems, Vol. 14, No. 3 Cross Ref Fast Random Walk with Restart and Its Applications Cross Ref Volume 32, Issue 3| 1990SIAM Review History Submitted:17 January 1990Accepted:31 January 1990Published online:03 August 2006 InformationCopyright © 1990 © Society for Industrial and Applied MathematicsPDF Download Article & Publication DataArticle DOI:10.1137/1032080Article page range:pp. 470-470ISSN (print):0036-1445ISSN (online):1095-7200Publisher:Society for Industrial and Applied Mathematics