Blobworld: A System for Region-Based Image Indexing and Retrieval

Carson, Chad; Thomas, M. T.; Belongie, Serge; Hellerstein, Joseph M.; Malik, Jitendra

doi:10.1007/3-540-48762-x_63

Cited by 550 publications

(333 citation statements)

References 9 publications

Supporting

Mentioning

321

Contrasting

Unclassified

Order By: Relevance

“…Nowadays, the on-line image collections such as Flickr 7 or FaceBook 8 are orders of magnitude larger. Although many images are annotated, the keywords are less reliable due to subjective perception and less consistent due to uncontrolled vocabulary.…”

Section: Indexing Informationmentioning

confidence: 99%

Adaptive relevance feedback for large-scale image retrieval

Suditu

Fleuret

2015

Multimed Tools Appl

View full text Add to dashboard Cite

Section: Indexing Informationmentioning

confidence: 99%

Adaptive relevance feedback for large-scale image retrieval

Suditu

Fleuret

2015

Multimed Tools Appl

View full text Add to dashboard Cite

“…Another similar part-based image represenations that are proposed recentlty are visterms [15,23,24], SIFT-bags [39] blobs [7], and VLAD [14] vector representation of an image which aggregates descriptors based on a locality criterion in the feature space. The different approach is the one proposed by Morand et al [21].…”

Section: Analogy Between Information Retrieval and Cbirmentioning

confidence: 99%

Toward a higher-level visual representation for content-based image retrieval

Sayad

Martinet

Urruty

et al. 2010

Multimed Tools Appl

View full text Add to dashboard Cite

Having effective methods to access the desired images is essential nowadays with the availability of a huge amount of digital images. The proposed approach is based on an analogy between content-based image retrieval and text retrieval. The aim of the approach is to build a meaningful mid-level representation of images to be used later on for matching between a query image and other images in the desired database. The approach is based firstly on constructing different visual words using local patch extraction and fusion of descriptors. Secondly, we introduce a new method using multilayer pLSA to eliminate the noisiest words generated by the vocabulary building process. Thirdly, a new spatial weighting scheme is introduced that consists of weighting visual words according to the probability of each visual word to belong to each of the n Gaussian. Finally, we construct visual phrases from groups of visual words that are involved in strong association rules. Experimental results show that our approach outperforms the results of traditional image retrieval techniques.

show abstract

“…Even systems using segments and local features such as Blob world are still far away from identifying objects reliably. No system offers interpretation of images or even medium level concepts as they can easily be captured with text [3]- [4]. This loss of information from an image to a representation by features is called the semantic gap [5].In earlier stages, features were calculated in the spatial domain, and the statistical nature of texture was taken into account in the procedure, which was based on the assumption that the texture information in an image I was contained in the overall or "average" spatial relationship which the gray tones in the image have to one another [6].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Ultra Sound Kidney Image Features for Image Retrieval by Gray Level Co-Occurrence Matrices

Manikandan¹,

Rajamani²,

Murugan³

2013

LNSE

View full text Add to dashboard Cite

Abstract-Medical imaging is though expensive because of capital costs, is easy to perform because of its noninvasive nature. In order to provide better analysis and diagnosis, various features have been extracted from any images. In this paper many important features of the ultra sound kidney images have been extracted and analysis has been made for the proposed image retrieval from the image database. Quantitative establishment of use the features for detection of abnormalities in Ultra sound kidney images have been made. Here, we made an analysis that the texture has been used to discriminate among the various types of tissue in image applications. Various important features namely contrast, homogeneity, correlation, energy, autocorrelation, variance, co-variance, inertia, promenance, shade, dissimilarity, inverse difference moment (IDM), maximum probability and entropy have been extracted and analyzed for the application in connection of a image database for the image retrieval process.Index Terms-Extraction, features, statistical test image retrieval, ultra sound kidney image.I.

show abstract

Blobworld: A System for Region-Based Image Indexing and Retrieval

Cited by 550 publications

References 9 publications

Adaptive relevance feedback for large-scale image retrieval

Adaptive relevance feedback for large-scale image retrieval

Toward a higher-level visual representation for content-based image retrieval

Analysis of Ultra Sound Kidney Image Features for Image Retrieval by Gray Level Co-Occurrence Matrices

Contact Info

Product

Resources

About