An application of multiple viewpoints to content-based image retrieval

French, James C.; Chapin, A. C.; Martin, Worthy N.

doi:10.1109/jcdl.2003.1204853

Cited by 16 publications

(15 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image databases retain traditional searchable fields such as creation date and length/size, while offering additional fields such as color and texture. Furthermore, color-and texturebased image retrieval is notoriously difficult to communicate to the user [4,10,17]. For example, busy city scenes with beige brick backgrounds will match scenes of desert sand, because the color characteristics are the same despite vast differences in content.…”

Section: Improving the User Interfacementioning

confidence: 99%

Addressing the challenge of visual information access from digital image and video libraries

Christel

Conescu

2005

Proceedings of the 5th ACM/IEEE-CS Joint Conference on Digital Libraries

View full text Add to dashboard Cite

While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with visually oriented generic topics. A within-subjects study involving 24 novice participants on TRECVID 2004 tasks again confirms this result. The study shows that satisfaction is greater and performance is significantly better on specific and generic information retrieval tasks from news broadcasts when transcripts are available for search. Additional runs with 7 expert users reveal different novice and expert interaction patterns with the video library interface, helping explain the novices' lack of success with image search and visual feature browsing for visual information needs. Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries.

show abstract

Section: Improving the User Interfacementioning

confidence: 99%

Addressing the challenge of visual information access from digital image and video libraries

Christel

Conescu

2005

Proceedings of the 5th ACM/IEEE-CS Joint Conference on Digital Libraries

View full text Add to dashboard Cite

show abstract

“…So, such features are not in the neighborhood of the query image in the feature space and can be even located in disjoint regions that can be more or less far from each other in the feature space. 13 The use of only one query image will not retrieve an important set of relevant images (depending on the degree of variance in the database) since, in this case, these relevant images are not necessarily near the considered query image in the feature space. 14 We should also mention that with multiple queries, there is some computational overhead since we use several queries for the same user's need.…”

Section: Multiple Queriesmentioning

confidence: 99%

Tackling the Problem of Invariant Texture Retrieval Using Multiple Strategies

Abbadeni

Alhichri

Elmasry

2011

Int. J. Image Grap.

View full text Add to dashboard Cite

We present in this paper an approach based on multiple strategies to tackle the problem of invariance in the framework of texture-based image retrieval. This approach, rather than to consider invariance at the representation level, considers it at the query level. We use two models to represent the visual content of textures, namely, the autoregressive model and a perceptual model based on a set of perceptual features. The perceptual model is used with two viewpoints: the original image's viewpoint and the autocovariance function viewpoint. After a brief presentation and discussion of these multiple representation models/viewpoints, we present the invariant texture retrieval algorithm. This algorithm considers results fusion (merging) at two different levels: (1) the first level consists in merging results returned by different models/viewpoints (representations) for the same query in one results list using a linear results fusion model; (2) the second level consists in merging each fused list of different queries into a unique fused list using a round robin fusion scheme. Experimental retrieval results and benchmarking based on the precision/recall measures applied on a large image database show interesting results.

show abstract

“…The second class of invariant models consider invariance at the query level, rather than the representation level. Among the works that considered this approach, we cite (17) and (19). However, these works considered the problem of image retrieval in general and did not consider the problem of invariance in particular.…”

Section: Hodwhg Zrunmentioning

confidence: 99%

“…In fact, since content representation models are not, in general, invariant with respect to different transformations, features computed on the same image, which has been rotated for example, are not the same as the original image and can be very different. So, such features are not in the neighborhood of the query image in the feature space and can be even located in disjoint regions that can be more or less far from each other in the feature space (17). The use of only one query image will not retrieve an important set of relevant images (depending on the degree of variance in the database) since, in this case, these relevant images are not necessarily near the considered query image in the feature space.…”

Section: Xowlsoh 4xhulhvmentioning

confidence: 99%

Invariant Image Retrieval: An Approach Based On Multiple Representations and Multiple Queries

Abbadeni¹

2010

Multimedia

View full text Add to dashboard Cite

We present an approach based on multiple representations and multiple queries to tackle the problem of invariance in the framework of content-based image retrieval. We consider the case of textures. This approach, rather than to consider invariance at the representation level, considers it at the query level. We use two models to represent the visual content of textures, namely the autoregressive model and a perceptual model based on a set of perceptual features. The perceptual model is used with two viewpoints: the original image's viewpoint and the autocovariance function viewpoint. After a brief presentation and discussion of these multiple representation models/viewpoints, we present the invariant texture retrieval algorithm. This algorithm considers results fusion (merging) at two different levels: 1. The first level consists in merging results returned by different models/viewpoints (representations) for the same query in one results list using a linear results fusion model; 2. The second level consists in merging each fused list of different queries into a unique fused list using a round robin fusion scheme. Experimental retrieval results and benchmarking based on the precision/recall measures applied on a large image database show interesting results. ,QWURGXFWLRQContent-based image retrieval (CBIR) is a research area that has been active for more than a decade and many research results and prototypes have been carried out since then

show abstract

An application of multiple viewpoints to content-based image retrieval

Cited by 16 publications

References 1 publication

Addressing the challenge of visual information access from digital image and video libraries

Addressing the challenge of visual information access from digital image and video libraries

Tackling the Problem of Invariant Texture Retrieval Using Multiple Strategies

Invariant Image Retrieval: An Approach Based On Multiple Representations and Multiple Queries

Contact Info

Product

Resources

About