A Hierarchical Image Annotation Method Based on SVM and Semi-supervised EM

Gao, Yanyu; Yin, Yixin; Uozumi, Takashi

doi:10.1016/s1874-1029(09)60041-0

Cited by 3 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gao, Yin and Uozumi [12] developed a hierarchical Image annotation technique by classifying the multiple labels through SVM and fine tuning the annotation by using Expectation Maximization (EM) algorithm. The 1300 images pre-processed by semantic keywords into several labels, and the images were extracted Gaussian mixture model followed subsequently by feature extraction.…”

Section: Role Of Image Annotationmentioning

confidence: 99%

An Insight on Image Annotation Approaches and their Performances

Et. al.

2021

TURCOMAT

View full text Add to dashboard Cite

Image Annotation (IA) followed by Image Retrieval (IR) plays a significant role in today’s computer vision world. As the manual IA is a tedious and time-consuming process, the automated IA became very predominant in the computer vision applications. IA deals with the assigning of meaningful labels to various objects in the image. The objective of this article is to represent the various IA approaches adopted in the last decade. Observation of the existing IA methods and their performances leads to identify the pitfalls the existing approaches. Few approaches used standard datasets and images downloaded from internet to evaluate the performance of the Image Annotation.

show abstract

Section: Role Of Image Annotationmentioning

confidence: 99%

An Insight on Image Annotation Approaches and their Performances

Et. al.

2021

TURCOMAT

View full text Add to dashboard Cite

show abstract

“…Recently, Jiang, et al, [50] adopt learning vector quantization (LVQ) technique to optimize low-level features extracted from given images, and then select some representative vectors with LVQ to train SVM classifiers instead of using all feature data for semantic image annotation. In [51], a hierarchical annotation scheme is presented by considering that human's visual identification to a scenery object is a rough-to-fine hierarchical process. To be specific, the input image is first segmented into multiple regions and each segmented region is roughly labeled with a general keyword using the multi-classification SVM, then an active semi-supervised expectation-maximization (EM) algorithm is employed to find the representative pattern of each fine class and classify the roughly labeled regions into corresponding fine classes, finally the contextual relationship is applied again to revise the improper fine labels.…”

Section: Hybrid Svm For Aiamentioning

confidence: 99%

“…Classifiers Image Datasets Cusano, et al, [28] SVM WWW Dataset Li, et al, [30] Ensemble SVMs COREL/WWW Datasets Shi, et al, [31] SVM COREL/Other Datasets Goh, et al, [32] Ensemble SVMs COREL Dataset Tsai, et al, [34] Ensemble SVMs COREL Dataset Qi, et al, [35] SVM, MIL COREL Dataset Chapelle, et al, [37] SVM COREL14/COREL7 Datasets Wei, et al, [42] SVM COREL Dataset Tian, et al, [43] SVM-MK COREL Dataset Chen, et al, [45] DD-SVM COREL/MUSK Datasets Han and Qi [46] MIL, SVM COREL Dataset Yang, et al, [47] SVM, MIL COREL Dataset Zhao, et al, [48] TSVM, HMM COREL Dataset Lu, et al, [49] SVM COREL Dataset Jiang, et al, [50] SVM, LVQ COREL Dataset Gao, et al, [51] SVM, Semi-supervised EM COREL Dataset Huang, et al, [52] SVM, GMM, ACM COREL Dataset Lei, et al, [53] HMM-SVM COREL Dataset Alham, et al, [54] MRSVM, SMO, MapReduce COREL Dataset Alham, et al, [55] MRESVM, SMO, MapReduce COREL Dataset Qiu [56] SVM ImageCLEF2006 Dataset Serrano, et al, [59] Ensemble SVMs Other Dataset Feng, et al, [67] Ensemble SVMs COREL Dataset Boutell, et al, [68] SVM COREL/Other Datasets Fan, et al, [69] SVM COREL/WWW Datasets International Journal of Hybrid Information Technology Vol. 8, No.11 (2015)…”

Section: Sourcesmentioning

confidence: 99%

Support Vector Machine for Automatic Image Annotation

Tian¹

2015

IJHIT

View full text Add to dashboard Cite

Automatic image annotation (AIA) is an active topic of research in computer vision and pattern recognition. In the last two decades, large amount of researches on AIA have been proposed, mainly including classification-based methods and probabilistic modeling methods. As one of the most common methods for AIA, support vector machine (SVM) has been widely applied in the multimedia research community, especially for image classification, image annotation and retrieval. However, compared with various SVM methods and their corresponding applications in the literature, there is almost no review research and analysis about SVM related studies. So the current paper, to start with, elaborates the basic principles of SVM. Followed by it summarizes SVM with applications to image annotation from three aspects of SVM ensemble for AIA, SVM with mixture of kernels for AIA and hybrid SVM for AIA respectively. In addition, SVM exploited in several other applications are also briefly reviewed. Finally, we end this paper with a summary of some important conclusions and highlight the potential research directions of SVM in automatic image annotation for the future.[11], regularized latent Dirichlet allocation (rLDA) [12] and TagProp [13], etc. By comparison, the former approach is relatively direct and natural to be understood. However, its performance is limited with the increase of the number of the semantic concepts and explosive multimedia data on the web. On the other hand, the latter often requires large-scale parameters to be estimated and the accuracy is strongly affected by the quantity and quality of the training data available. Furthermore, it has been argued that the discriminative approach can result in superior performance than that by generative method which is more powerful in capturing decision boundaries among different classes and more widely applied in recognition tasks. For this reason, it is highly desirable to develop approaches with the flexibility of generative learning and the performance of discriminative methods. At present, several hybrid generative discriminative schemes have been proposed to combine the strengths of these two kinds of models in a number of applications, from scene classification [14-16], object recognition [17,18], image annotation [19], image classification [20][21][22], speech recognition [23] to biological sequence analysis [24], resulting in state-of-the-art performance. Support vector machine (SVM) is a well-known example of discriminative methods. As a theoretically rich method and because of its advantages such as its use of over-fitting protect-ion independently from the number of features and its effectiveness in the case of sparse data, SVM has been extensively applied to a wide variety of domains such as computer vision, pattern recognition, object detection and function estimation, etc. In its basic form, an SVM creates a hyperplane as the decision plane, which separates the positive and negative classes with the largest margin. This paper aims to conduct a survey of SVM f...

show abstract

Automatic Image Annotation Based on Particle Swarm Optimization and Support Vector Clustering

Hao

2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the progress of network technology, there are more and more digital images of the internet. But most images are not semantically marked, which makes it difficult to retrieve and use. In this paper, a new algorithm is proposed to automatically annotate images based on particle swarm optimization (PSO) and support vector clustering (SVC). The algorithm includes two stages: firstly, PSO algorithm is used to optimize SVC; secondly, the trained SVC algorithm is used to annotate the image automatically. In the experiment, three datasets are used to evaluate the algorithm, and the results show the effectiveness of the algorithm.

show abstract

A Hierarchical Image Annotation Method Based on SVM and Semi-supervised EM

Cited by 3 publications

References 15 publications

An Insight on Image Annotation Approaches and their Performances

An Insight on Image Annotation Approaches and their Performances

Support Vector Machine for Automatic Image Annotation

Automatic Image Annotation Based on Particle Swarm Optimization and Support Vector Clustering

Contact Info

Product

Resources

About