Periodicity Extraction using Superposition of Distance Matching Function and One-dimensional Haar Wavelet Transform
This method addresses periodicity extraction for texture analysis, which is essential in applications like texture synthesis and compression, but it appears incremental as it builds on existing techniques.
The authors tackled the problem of extracting periodicity from noisy images by proposing a method based on superposition of distance matching function and Haar wavelet transform, which successfully determines periodicities in row and column directions without requiring de-noising.
Periodicity of a texture is one of the important visual characteristics and is often used as a measure for textural discrimination at the structural level. Knowledge about periodicity of a texture is very essential in the field of texture synthesis and texture compression and also in the design of frieze and wall papers. In this paper, we propose a method of periodicity extraction from noisy images based on superposition of distance matching function (DMF) and wavelet decomposition without de-noising the test images. Overall DMFs are subjected to single-level Haar wavelet decomposition to obtain approximate and detailed coefficients. Extracted coefficients help in determination of periodicities in row and column directions. We illustrate the usefulness and the effectiveness of the proposed method in a texture synthesis application.