Limits...
Perspective texture synthesis based on improved energy optimization.

Bashir SM, Ghouri FA - PLoS ONE (2014)

Bottom Line: Using k- means clustering technique to build a search tree to accelerate the search.Hence, we make use of principal component analysis (PCA) technique to reduce dimensions of input vectors.The high quality results prove that our approach is feasible.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan; Quality Management Directorate General, Pakistan Space and Upper Atmosphere Research Commission (SUPARCO), Karachi, Pakistan.

ABSTRACT
Perspective texture synthesis has great significance in many fields like video editing, scene capturing etc., due to its ability to read and control global feature information. In this paper, we present a novel example-based, specifically energy optimization-based algorithm, to synthesize perspective textures. Energy optimization technique is a pixel-based approach, so it's time-consuming. We improve it from two aspects with the purpose of achieving faster synthesis and high quality. Firstly, we change this pixel-based technique by replacing the pixel computation with a little patch. Secondly, we present a novel technique to accelerate searching nearest neighborhoods in energy optimization. Using k- means clustering technique to build a search tree to accelerate the search. Hence, we make use of principal component analysis (PCA) technique to reduce dimensions of input vectors. The high quality results prove that our approach is feasible. Besides, our proposed algorithm needs shorter time relative to other similar methods.

Show MeSH
Perspective texture synthesis of a flower image.(a) the input example; (b) scale map with σ = 60°, τ = 20°; (c) our result; (d) optimization [Kwatra et al. 2005] result.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4197031&req=5

pone-0110622-g009: Perspective texture synthesis of a flower image.(a) the input example; (b) scale map with σ = 60°, τ = 20°; (c) our result; (d) optimization [Kwatra et al. 2005] result.

Mentions: The input example has no size limit and output texture (of course, the input sample cannot be too smaller to tell the texel) for our approach. The three texture images shown in Figure 1 are very representative, which are with rich perspective properties and can meet our experiment need. So we choose them as input samples. Using the improved energy optimization-based algorithm presented above, we finally obtain the synthesis results shown in Figure 8 and Figure 9 (The seawater image result has been proposed before to discuss the process of this algorithm, so is not shown here again). To better comparison, we provide their results for texture optimization algorithm in [4], separately shown in Figure 8(d) and Figure 9(d). The experiments are done on a computer with 2.4 GHz Intel Core i5 processor, 4 GB RAM, and 32- bit Windows 7 system, using MATLAB software to simulate. The given slant and tilt angles are: σ = 30°, τ = 18° and σ = 60°, τ = 20°, respectively.


Perspective texture synthesis based on improved energy optimization.

Bashir SM, Ghouri FA - PLoS ONE (2014)

Perspective texture synthesis of a flower image.(a) the input example; (b) scale map with σ = 60°, τ = 20°; (c) our result; (d) optimization [Kwatra et al. 2005] result.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4197031&req=5

pone-0110622-g009: Perspective texture synthesis of a flower image.(a) the input example; (b) scale map with σ = 60°, τ = 20°; (c) our result; (d) optimization [Kwatra et al. 2005] result.
Mentions: The input example has no size limit and output texture (of course, the input sample cannot be too smaller to tell the texel) for our approach. The three texture images shown in Figure 1 are very representative, which are with rich perspective properties and can meet our experiment need. So we choose them as input samples. Using the improved energy optimization-based algorithm presented above, we finally obtain the synthesis results shown in Figure 8 and Figure 9 (The seawater image result has been proposed before to discuss the process of this algorithm, so is not shown here again). To better comparison, we provide their results for texture optimization algorithm in [4], separately shown in Figure 8(d) and Figure 9(d). The experiments are done on a computer with 2.4 GHz Intel Core i5 processor, 4 GB RAM, and 32- bit Windows 7 system, using MATLAB software to simulate. The given slant and tilt angles are: σ = 30°, τ = 18° and σ = 60°, τ = 20°, respectively.

Bottom Line: Using k- means clustering technique to build a search tree to accelerate the search.Hence, we make use of principal component analysis (PCA) technique to reduce dimensions of input vectors.The high quality results prove that our approach is feasible.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan; Quality Management Directorate General, Pakistan Space and Upper Atmosphere Research Commission (SUPARCO), Karachi, Pakistan.

ABSTRACT
Perspective texture synthesis has great significance in many fields like video editing, scene capturing etc., due to its ability to read and control global feature information. In this paper, we present a novel example-based, specifically energy optimization-based algorithm, to synthesize perspective textures. Energy optimization technique is a pixel-based approach, so it's time-consuming. We improve it from two aspects with the purpose of achieving faster synthesis and high quality. Firstly, we change this pixel-based technique by replacing the pixel computation with a little patch. Secondly, we present a novel technique to accelerate searching nearest neighborhoods in energy optimization. Using k- means clustering technique to build a search tree to accelerate the search. Hence, we make use of principal component analysis (PCA) technique to reduce dimensions of input vectors. The high quality results prove that our approach is feasible. Besides, our proposed algorithm needs shorter time relative to other similar methods.

Show MeSH