The Promise and Perils of Near-Regular Texture

Liu, Yanxi; Tsin, Yanghai; Lin, Wen‐Chieh

doi:10.1023/b:visi.0000046593.03875.01

Cited by 16 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These represent "deformations" or "distortions" of the image due to, for instance, a change of vantage point, or a deformation of the scene [19]. Given a group G, a set ω and a function φ ω , we say that the distribution dP (I) is G-stationary in φ ω if there exists a g ∈ G such that E(φ g(ω) ) is translation-invariant, that is (1) is satisfied only for T that belong to a discrete subgroup of planar translations (Frieze symmetries, see [11]), then the process is cyclo-stationary.…”

Section: Stationaritymentioning

confidence: 99%

Texture Compression

Georgiadis

Chiuso

Soatto

2013

2013 Data Compression Conference

View full text Add to dashboard Cite

We characterize "visual textures" as realizations of a stationary, ergodic, Markovian process, and propose using its approximate minimal sufficient statistics for compressing texture images. We propose inference algorithms for estimating the "state" of such process and its "variability". These represent the encoding stage. We also propose a non-parametric sampling scheme for decoding, by synthesizing textures from their encoding. While these are not faithful reproductions of the original textures (so they would fail a comparison test based on PSNR), they capture the statistical properties of the underlying process, as we demonstrate empirically. We also quantify the tradeoff between fidelity (measured by a proxy of a perceptual score) and complexity.

show abstract

Section: Stationaritymentioning

confidence: 99%

Texture Compression

Georgiadis

Chiuso

Soatto

2013

2013 Data Compression Conference

View full text Add to dashboard Cite

show abstract

“…Similar to the work proposed in [31] and [32], the proposed algorithm can accept some user intervention for choosing the frequency components required for periodicity detection, including the number of frequencies around the fundamentals. As mentioned in Section II-B1, directly affects the textural structure's regularity and periodicity.…”

Section: Conclusion and Discussionmentioning

confidence: 93%

“…Visual comparisons are important in order to illustrate how the proposed technique is "better." More specifically, comparisons with three other works (Efros [17], Liu [31], [32], Gimel'farb [39]) are presented. These techniques are chosen as being representative of their category.…”

Section: Resultsmentioning

confidence: 99%

“…Liu et al [31] proposed a method to detect periodicity from frieze and wallpaper groups, including hexagonal structures. This work was extended in [32] for synthesis of near-regular textures, while deformable textures were also considered. Gimel'farb [39] has also proposed a modification of his Gibbs-based technique [38] for periodic textures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Texture synthesis: textons revisited

Charalampidis

2006

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper introduces a technique for synthesizing natural textures, with emphasis on quasiperiodic and structural textures. Textures are assumed to be composed of three components, namely illumination, structure, and stochastic. The contribution of this work is that, in contrast to previous techniques, it proposes a joint approach for handling the texture's global illumination, irregular structure, and stochastic component which may be correlated to the other two components. Furthermore, the proposed technique does not produce verbatim copies in the synthesized texture. More specifically, a top-down approach is used for extraction of texture elements (textons) in which, in contrast to previous texton-based approaches, no assumptions regarding perfect periodicity are made. The structure itself can be modeled as a stochastic process. Consequently, textons are allowed to have irregular and nonidentical shapes. In the synthesis stage, a new nonregular textural structure is designed from the original one that defines the place holders for textons. We call such place holders empty textons (e-textons). The e-textons are filled in by a representative texton. Since e-textons do not have identical shapes, a texton shape-matching procedure is required. After adding the illumination to the structural component, a strictly localized version of a block sampling technique is applied to add the stochastic component. The block sampling technique combined with the addition of the illumination component provides a significant improvement in the appearance of synthesized textures. Results show that the proposed method is successful in synthesizing structural textures visually indistinguishable to the original. Moreover, the method is successful in synthesizing a variety of stochastic textures.

show abstract

“…Texture periodicity analysis has become popular lately and has been used for texture tracking [14], synthesis [22,11,31], retrieval [8,9] and in Islamic Geometry Pattern (IGP) analysis [17,23].…”

mentioning

confidence: 99%

A Genetic Based Algorithm for Automatic Motif Detection of Periodic Patterns

Nasri¹,

Benslimane²,

Ouaazizi³

2014

2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems

View full text Add to dashboard Cite

90 t t , ϕ = ≠ D (2): Parallelogram, 1 2 90 t t , ϕ ≠ ≠ D , (3): Centered rectangular 1 2 90 t t , ϕ = ≠ D (4): Square, 1 2 0 t t = , ϕ = 9 D (5): Hexagonal, 1 2 0 t tIn this paper, we introduce a new method to extract the basic unit cell of a periodic Islamic Geometrical Pattern (IGP). This method is based on the autocorrelation function (ACF), a function known to be appropriate to analyze and draw out a repetitive motif from a regular texture. The motif can be successfully extracted when the detected peaks in the autocorrelation function of an image are pertinent. In this paper, the pertinent peaks detection is considered as an optimization problem. For this purpose, we propose a criterion function that we optimize by using genetic algorithm. The proposed method is tolerant to geometric distortion, and photometric quality of the input image compared to classical ones. Tests on 166 images with different visual quality demonstrate the capability of the proposed method to extract the periodic motif automatically.

show abstract

The Promise and Perils of Near-Regular Texture

Cited by 16 publications

References 13 publications

Texture Compression

Texture Compression

Texture synthesis: textons revisited

A Genetic Based Algorithm for Automatic Motif Detection of Periodic Patterns

Contact Info

Product

Resources

About