Periodic pattern of texture analysis and synthesis based on texels distribution

Gui, Yan; Ma, Lizhuang

doi:10.1007/s00371-010-0470-x

Cited by 8 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each texture element in the texture sample can be represented by its bounding boxes, and the centers of these bounding boxes are used to define the element positions in the texture sample. According to the discrete positions information, the most suitable method used in [11,14] is to extract the Delaunay triangulation in order to get a connectivity among all texture elements. The connectivity also can be called the distribution of texture elements.…”

Section: Connectivity Construction and Analysismentioning

confidence: 99%

“…In Fig. 7, we compare our approach with existing techniques of texels distribution based [14], appearance-space synthesis [7], near regular texture synthesis [6], Graph-cut [5], image quilting [4], patch-based [3] and jump-map based [2]. The texture sample in Fig.…”

Section: Texture Elements Deformationmentioning

confidence: 99%

“…Potential solutions [9][10][11][12][13][14][15] have been explored through imitating the element distributions in input exemplars. For example, Dischler et al [9] generated 2D textures or textures on arbitrary surfaces by adding texture particles according to sets of co-occurrences.…”

Section: Introductionmentioning

confidence: 99%

“…Passos et al [13] presented an improved method for arrangement synthesis defined as 2D collection of elements, which provides control over local density of elements. Gui et al [14] proposed a similar method for periodic pattern of texture analysis and synthesis based on texels distribution. Recently, Huang et al [15] extend it to texture synthesis on arbitrary surfaces.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Texture Synthesis and Design based on Elements Distribution Creation

Gui¹,

Liu²,

Li³

2017

Proceedings of the First EAI International Conference on Computer Science and Engineering

Self Cite

View full text Add to dashboard Cite

The texture synthesis and design starts with an initial elements arrangement and expands it outward by using local and global growth, to obtain the new larger distribution of texture elements. There are two types of synthesized distributions, and their diversity consists in changing the layout of texture elements and decreasing or increasing the number of texture elements according to user's creation. Furthermore, we apply a set of deformation operations to locally change the shapes of texture elements when placing the extracted texture elements into the synthesized distribution, in order to guarantee structure consistency in final synthesized textures. Experimental results show that our method creates a large variety of textures from a given texture sample.

show abstract

Section: Connectivity Construction and Analysismentioning

confidence: 99%

Section: Texture Elements Deformationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Texture Synthesis and Design based on Elements Distribution Creation

Gui¹,

Liu²,

Li³

2017

Proceedings of the First EAI International Conference on Computer Science and Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…From the structural point of view, it is widely accepted to define the texture as a conjunction of two components: i) a texture element (texel), which is the fundamental microstructure in the image [22], and ii) a set of rules for texel placement into the field of view. Such components can be used in several applications like shape from texture [2], texture synthesis [13,11,4], texture compression [14], among others. Furthermore, the texel can be used as a reference to improve the performance in classification [6,12] and segmentation [18] tasks, and to achieve scale invariant texture analysis [21].…”

Section: Introductionmentioning

confidence: 99%

Homogeneity Cues for Texel Size Estimation of Periodic and Near-Periodic Textures

Lizarraga-Morales

Sánchez-Yáñez

Ayala-Ramírez

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Texel size determination on periodic and near-periodic textures, is a problem that has been addressed for years, and currently it remains as an important issue in structural texture analysis. This paper proposes an approach to determine the texel size based on the computation and analysis of the texture homogeneity properties. We analyze the homogeneity feature computed from difference histograms, while varying the displacement vector for a preferred orientation. As we vary this vector, we expect a maximum value in the homogeneity data if its magnitude matches the texel size in a given orientation. We show that this approach can be used for both periodic and near-periodic textures, it is robust to noise and blur perturbations, and its advantages over other approaches in computation time and memory storage.

show abstract

Texture Synthesis and Design Based on Element Distribution Creation

Gui

Liu

2017

Modeling, Simulation, and Optimization

View full text Add to dashboard Cite

Periodic pattern of texture analysis and synthesis based on texels distribution

Cited by 8 publications

References 27 publications

Texture Synthesis and Design based on Elements Distribution Creation

Texture Synthesis and Design based on Elements Distribution Creation

Homogeneity Cues for Texel Size Estimation of Periodic and Near-Periodic Textures

Texture Synthesis and Design Based on Element Distribution Creation

Contact Info

Product

Resources

About