Analyzing scenery images by monotonic tree

Song, Yuqing; Zhang, Aidong

doi:10.1007/s00530-002-0067-y

Cited by 28 publications

(27 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They propose the selection of the level lines that minimize the well known Mumford-Shah functional restricted to the tree of shapes. Finally, in [8] the authors use an alternative and independent formulation of the tree of shapes, the so-called Monotonic Tree. They define structural elements (some subsets of the tree) from which they extract certain features and classify them according to those features.…”

Section: Introductionmentioning

confidence: 99%

Region Based Segmentation Using the Tree of Shapes

Cardelino

Randall

Bertalmío

et al. 2006

2006 International Conference on Image Processing

View full text Add to dashboard Cite

The tree of shapes is a powerful tool for image representation which holds many interesting properties. There are many works in the literature that use it for image segmentation, but most of them use only boundary information along the level lines. In many real images this is not enough to achieve a good segmentation, and region information must be introduced. In this work we present a novel region-based segmentation algorithm using the tree of shapes. The approach taken consists in the selection of relevant level-lines according to region based descriptors computed from their interior. We describe a region using the histogram of its features and we select interesting regions by identifying parts of the tree with an homogeneous histogram. The main contribution of this work is the joint use of histograms and suitable metrics between them, with the powerful representation of the tree of shapes. This allows us to handle complex region models and thus improves on previous works which were only able to deal with piecewise constant models. We validate our approach with real images and we obtain results which are favorably compared with some well known related approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Region Based Segmentation Using the Tree of Shapes

Cardelino

Randall

Bertalmío

et al. 2006

2006 International Conference on Image Processing

View full text Add to dashboard Cite

show abstract

“…A unique and promising monotonic tree approach that models scenery images as discrete structural elements has been proposed recently to bridge the semantic gap in contentbased image retrieval [41]. Based on simple assumptions about the colour, location, harshness, and shape of scenery features, monotonic trees embody the domain knowledge about scenery images to classify image regions into eight scenery object types with high accuracy to support semantics-based image retrieval.…”

Section: Semantic Gapmentioning

confidence: 99%

“…The recent monotonic tree approach [41] provides a unique framework for analysing scenery images. Based on a new concept of monotonic line, image data are progressively represented as hierarchies of structural elements, which are classified and clustered into semantic regions of sky, building, tree, waves, placid water, lawn, snow, and others with qualifying scores.…”

Section: Semantic Extraction and Indexingmentioning

confidence: 99%

See 1 more Smart Citation

A structured learning framework for content-based image indexing and visual query

Lim

Jin

2005

Multimedia Systems

View full text Add to dashboard Cite

Abstract. Nonspecific images in a broad domain remain a challenge for content-based image retrieval. As a typical example, consumer photos exhibit highly varied content, diverse resolutions, and inconsistent quality. The objects are usually ill-posed, occluded, and cluttered with poor lighting, focus, and exposure. Traditional image retrieval approaches face many obstacles such as semantic description of images, robust semantic object segmentation, small sampling problem, semantic gaps between low-level features and high-level semantics, etc.To manage the high diversity of images in a broad domain, we propose a structured learning framework to systematically design domain-relevant visual semantics, known as semantic support regions, to support index and query in a contentbased image retrieval system. Semantic support regions are segmentation-free image regions that exhibit semantic meanings and that can be learned statistically to span a new indexing space. They are detected from image content, reconciled across multiple resolutions, and aggregated spatially to form local semantic histograms. The resulting compact and abstract representation can support both similarity-based query and compositional visual query efficiently. The query by spatial icons (QBSI) formulation is a unique visual query language to explicitly specify visual icons and spatial extents in a Boolean expression.For empirical evaluation, we perform the learning and indexing processes of 26 semantic support regions over 2400 heterogeneous consumer photos from a single family using Support Vector Machines. We report a 27% improvement in average precision over a very high dimension feature-based approach on 24 semantic queries based on multiple examples and pooled ground truths. Last but not least, we demonstrate the usefulness of the visual query language with 15 QBSI queries that have attained high precision values at top retrieved images on the 2400 consumer images.

show abstract

“…Much research has been done on problems of scene classification [1,2,5,8,9,12,13,14,16,18]. The majority of these systems employed a learning-by-example approach based on low-level vision features derived exclusively from scene content.…”

Section: Introductionmentioning

confidence: 99%