Wavelets are a powerful tool that can be applied to problems in image processing and analysis. They provide a multi-scale decomposition of an original image into average terms and detail terms that capture the characteristics of the image at different scales. In this project, we develop a figure of merit for macro-uniformity that is based on wavelets. We use the Haar basis to decompose the image of the scanned page into eleven levels. Starting from the lowest frequency level, we group the eleven levels into three non-overlapping separate frequency bands, each containing three levels. Each frequency band image consists of the superposition of the detail images within that band. We next compute 1-D horizontal and vertical projections for each frequency band image. For each frequency band image projection, we develop a structural approximation that summarizes the essential visual characteristics of that projection. For the coarsest band comprising levels 9,10,11, we use a generalized square-wave approximation. For the next coarsest band comprising levels 6,7,8, we use a piecewise linear spline approximation. For the finest bands comprising levels 3,4,5, we use a spectral decomposition. For each 1-D approximation signal, we define an appropriate set of scalar-valued features. These features are used to design two predictors one based on linear regression and the other based on the support vector machine, which are trained with data from our image quality ruler experiments with human subjects.
%0 Conference Paper
%1 citeulike:13582211
%A Liu, Xing
%A Overall, Gary
%A Riggs, Travis
%A Silveston-Keith, Rebecca
%A Whitney, Julie
%A Chiu, George
%A Allebach, Jan
%B Image Quality and System Performance X
%D 2013
%I SPIE
%K 94a08-image-processing 68u10-image-processing 65t60-wavelets
%P 86530Q--86530Q-8
%R 10.1117/12.2008515
%T Wavelet-based Figure of Merit for Macro-uniformity
%U http://dx.doi.org/10.1117/12.2008515
%V 8653
%X Wavelets are a powerful tool that can be applied to problems in image processing and analysis. They provide a multi-scale decomposition of an original image into average terms and detail terms that capture the characteristics of the image at different scales. In this project, we develop a figure of merit for macro-uniformity that is based on wavelets. We use the Haar basis to decompose the image of the scanned page into eleven levels. Starting from the lowest frequency level, we group the eleven levels into three non-overlapping separate frequency bands, each containing three levels. Each frequency band image consists of the superposition of the detail images within that band. We next compute 1-D horizontal and vertical projections for each frequency band image. For each frequency band image projection, we develop a structural approximation that summarizes the essential visual characteristics of that projection. For the coarsest band comprising levels 9,10,11, we use a generalized square-wave approximation. For the next coarsest band comprising levels 6,7,8, we use a piecewise linear spline approximation. For the finest bands comprising levels 3,4,5, we use a spectral decomposition. For each 1-D approximation signal, we define an appropriate set of scalar-valued features. These features are used to design two predictors one based on linear regression and the other based on the support vector machine, which are trained with data from our image quality ruler experiments with human subjects.
@inproceedings{citeulike:13582211,
abstract = {{Wavelets are a powerful tool that can be applied to problems in image processing and analysis. They provide a multi-scale decomposition of an original image into average terms and detail terms that capture the characteristics of the image at different scales. In this project, we develop a figure of merit for macro-uniformity that is based on wavelets. We use the Haar basis to decompose the image of the scanned page into eleven levels. Starting from the lowest frequency level, we group the eleven levels into three non-overlapping separate frequency bands, each containing three levels. Each frequency band image consists of the superposition of the detail images within that band. We next compute 1-D horizontal and vertical projections for each frequency band image. For each frequency band image projection, we develop a structural approximation that summarizes the essential visual characteristics of that projection. For the coarsest band comprising levels 9,10,11, we use a generalized square-wave approximation. For the next coarsest band comprising levels 6,7,8, we use a piecewise linear spline approximation. For the finest bands comprising levels 3,4,5, we use a spectral decomposition. For each 1-D approximation signal, we define an appropriate set of scalar-valued features. These features are used to design two predictors one based on linear regression and the other based on the support vector machine, which are trained with data from our image quality ruler experiments with human subjects.}},
added-at = {2017-06-29T07:13:07.000+0200},
author = {Liu, Xing and Overall, Gary and Riggs, Travis and Silveston-Keith, Rebecca and Whitney, Julie and Chiu, George and Allebach, Jan},
biburl = {https://www.bibsonomy.org/bibtex/29d2eadff6455999983bc23f00e47ba1c/gdmcbain},
booktitle = {Image Quality and System Performance X},
citeulike-article-id = {13582211},
citeulike-attachment-1 = {liu_13_wavelet.pdf; /pdf/user/gdmcbain/article/13582211/1013520/liu_13_wavelet.pdf; 9c7463795d8291358fda96275aaae2141f6a2946},
citeulike-linkout-0 = {http://dx.doi.org/10.1117/12.2008515},
doi = {10.1117/12.2008515},
file = {liu_13_wavelet.pdf},
interhash = {00303a5517bb205de60ab3dfe75f177f},
intrahash = {9d2eadff6455999983bc23f00e47ba1c},
keywords = {94a08-image-processing 68u10-image-processing 65t60-wavelets},
organization = {SPIE},
pages = {86530Q--86530Q-8},
posted-at = {2015-04-15 00:59:31},
priority = {2},
publisher = {SPIE},
timestamp = {2020-02-19T00:13:46.000+0100},
title = {{Wavelet-based Figure of Merit for Macro-uniformity}},
url = {http://dx.doi.org/10.1117/12.2008515},
volume = 8653,
year = 2013
}