Unsupervised extraction of salient region-descriptors for content based image retrieval

Dimai, Alexander

doi:10.1109/iciap.1999.797674

Cited by 11 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another similar approach considers the input image(s) at different resolutions, but with different features. As an example in [7], luminance, color, and texture at several scales are computed at every position in the image. The strength of inhomogeneities of luminance, color, and textures are used as indicators of edge evidence.…”

Section: Image Processingmentioning

confidence: 99%

“…This step may use statistical classification [41], edge detection [12], region detection [7], or a combination of these techniques [15]. Each method has its own parameters.…”

Section: Detail Detectionmentioning

confidence: 99%

“…Feature computation for regions is presented in [7,13,20,25]. Cinque [6] simply uses the mean color of a region.…”

Section: Feature Computationmentioning

confidence: 99%

“…An alternative to global features is salient details to represent the image content where salient details can be points [12,21,34], lines [18,26], or regions [7,25,40].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Relevance feedback based saliency adaptation in CBIR

Nguyen

Worring

2005

Multimedia Systems

View full text Add to dashboard Cite

Content-based image retrieval (CBIR) has been under investigation for a long time, with many systems built to meet different application demands. However, in all systems there is still a gap between user expectations and system retrieval capabilities. Therefore, user interaction is an essential component of any CBIR system. Interaction up to now has mostly focused on changing global image features or similarities between images. We consider the interaction with salient details in an image, i.e., points, lines, and regions. Interactive salient detail definition goes further than summarizing the image into a set of salient details. We aim to dynamically update the user-and context-dependent definition of saliency based on relevance feedback. To that end, we propose an interaction framework for salient details from the perspective of the user. A number of instantiations of the framework are presented. Finally, we apply our approach for query refinement in a detail-based image retrieval system with salient points and regions. Experimental results prove the effectiveness of adapting the saliency from user feedback in the retrieval process.

show abstract

Section: Image Processingmentioning

confidence: 99%

“…This step may use statistical classification [41], edge detection [12], region detection [7], or a combination of these techniques [15]. Each method has its own parameters.…”

Section: Detail Detectionmentioning

confidence: 99%

“…Feature computation for regions is presented in [7,13,20,25]. Cinque [6] simply uses the mean color of a region.…”

Section: Feature Computationmentioning

confidence: 99%

“…An alternative to global features is salient details to represent the image content where salient details can be points [12,21,34], lines [18,26], or regions [7,25,40].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Relevance feedback based saliency adaptation in CBIR

Nguyen

Worring

2005

Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…Generic, complete and to-the-pixel accurate unsupervised segmentation is virtually impossible [11]. Fortunately, less-accurate segmentations are useful enough for applications of image content analysis.…”

Section: Requirements For Segmentation Subsystemmentioning

confidence: 99%