Fabric image recolorization based on intrinsic image decomposition

2018 ◽  
Vol 89 (17) ◽  
pp. 3617-3631 ◽  
Author(s):  
Chen Xu ◽  
Yu Han ◽  
George Baciu ◽  
Min Li
Keyword(s):  
Image Segmentation ◽  
Image Reconstruction ◽  
Image Decomposition ◽  
Numerical Results ◽  
Color Design ◽  
Variational Framework ◽  
Classical Image ◽  
Interactive Operations ◽  
The Given

Fabric image recolorization is widely used in assisting designers to generate new color design proposals for fabric. In this paper, a new image recolorization method is proposed. Different from classical image recolorization methods, which need some complicated interactive operations from users, our proposed method can achieve automatic recolorization of images. The proposed method contains three sequential phases: a phase of extracting representative colors from fabric images; an image segmentation phase; and an image reconstruction phase by using given color themes. Integrated with intrinsic image decomposition, a new image segmentation model is designed in a variational framework, and an algorithm is given to solve the model. Our image recolorization results are images that are reconstructed by the composition of the image segmentation results and the given color themes. Numerical results demonstrate that our newly proposed intrinsic image decomposition-based image recolorization method can generate better results than the classical cartoon-and-texture decomposition-based method.

scholarly journals Optimization of a k-covering of a bounded set with circles of two given radii

2021 ◽  
Vol 11 (1) ◽  
pp. 232-240
Author(s):  
Alexander V. Khorkov ◽  
Shamil I. Galiev
Keyword(s):  
Linear Programming ◽  
Numerical Method ◽  
Lower Bounds ◽  
Integer Linear Programming ◽  
Numerical Results ◽  
Programming Models ◽  
Bounded Set ◽  
The Given

Abstract A numerical method for investigating k-coverings of a convex bounded set with circles of two given radii is proposed. Cases with constraints on the distances between the covering circle centers are considered. An algorithm for finding an approximate number of such circles and the arrangement of their centers is described. For certain specific cases, approximate lower bounds of the density of the k-covering of the given domain are found. We use either 0–1 linear programming or general integer linear programming models. Numerical results demonstrating the effectiveness of the proposed methods are presented.

Modified Gabor Wavelets for Image Decomposition and Perfect Reconstruction

2011 ◽  
pp. 298-309
Author(s):  
Reza Fazel-Rezai ◽  
Witold Kinsner
Keyword(s):  
Feature Extraction ◽  
Image Reconstruction ◽  
Visual System ◽  
Human Visual System ◽  
Image Decomposition ◽  
Perfect Reconstruction ◽  
Gabor Wavelets ◽  
Gabor Functions

This article presents a scheme for image decomposition and perfect reconstruction based on Gabor wavelets. Gabor functions have been used extensively in areas related to the human visual system due to their localization in space and bandlimited properties. However, since the standard two-sided Gabor functions are not orthogonal and lead to nearly singular Gabor matrices, they have been used in the decomposition, feature extraction, and tracking of images rather than in image reconstruction. In an attempt to reduce the singularity of the Gabor matrix and produce reliable image reconstruction, in this article, the authors used single-sided Gabor functions. Their experiments revealed that the modified Gabor functions can accomplish perfect reconstruction.

scholarly journals Spatially Adaptive Regularization in Image Segmentation

Algorithms ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 226
Author(s):  
Laura Antonelli ◽  
Valentina De Simone ◽  
Daniela di Serafino
Keyword(s):  
Image Segmentation ◽  
Split Bregman ◽  
Minimization Method ◽  
Piecewise Constant ◽  
Median Filters ◽  
Spatial Image ◽  
Local Regularization ◽  
Spatial Features ◽  
Spatially Adaptive ◽  
The Given

We present a total-variation-regularized image segmentation model that uses local regularization parameters to take into account spatial image information. We propose some techniques for defining those parameters, based on the cartoon-texture decomposition of the given image, on the mean and median filters, and on a thresholding technique, with the aim of preventing excessive regularization in piecewise-constant or smooth regions and preserving spatial features in nonsmooth regions. Our model is obtained by modifying a well-known image segmentation model that was developed by T. Chan, S. Esedoḡlu, and M. Nikolova. We solve the modified model by an alternating minimization method using split Bregman iterations. Numerical experiments show the effectiveness of our approach.

SCREEN IMAGE SEGMENTATION AND CORRECTION FOR A COMPUTER DISPLAY

2014 ◽  
Vol 28 (04) ◽  
pp. 1454002 ◽  
Author(s):  
YUNG-SHENG CHEN ◽  
KUN-LI LIN
Keyword(s):  
Computer Vision ◽  
Image Segmentation ◽  
Affine Transformation ◽  
Physical World ◽  
Screen Image ◽  
Digital World ◽  
The Look ◽  
The Given ◽  
Deformation Correction ◽  
Vision Application

Perception of content displayed on the screen of a computer display using computer vision is a challenging topic if the treated target is changed from physical world to digital world. Screen area from the given computer display image should be segmented and corrected primarily before perceiving the content displayed on the screen. An automatic approach is proposed to the segmentation and deformation correction of screen area for a computer display image. Due to some inherent characteristics existing on ordinary computer displays, the segmentation can be performed by contour tracing. After contouring the screen area, its four corner locations can be readily identified. By approximating the obtained corners to the closest normal screen region, the deformed screen image can be further restored with affine transformation. As a computer vision application on the "look at" screen image, the effectively segmented screen region can be fixed after a little time. The experiments demonstrate that about 70% cases can be fixed under 33 processed frames, others under 51 processed frames, and thus confirm the feasibility of the proposed approach.

scholarly journals An improved model for joint segmentation and registration based on linear curvature smoother

2016 ◽  
Vol 10 (4) ◽  
pp. 314-324 ◽  
Author(s):  
Mazlinda Ibrahim ◽  
Ke Chen ◽  
Lavdie Rada
Keyword(s):  
Image Segmentation ◽  
Medical Imaging ◽  
Large Deformation ◽  
Active Contour ◽  
Numerical Results ◽  
Variational Model ◽  
Multiple Objects ◽  
Proposed Model ◽  
Challenging Tasks ◽  
Improved Model

Image segmentation and registration are two of the most challenging tasks in medical imaging. They are closely related because both tasks are often required simultaneously. In this article, we present an improved variational model for a joint segmentation and registration based on active contour without edges and the linear curvature model. The proposed model allows large deformation to occur by solving in this way the difficulties other jointly performed segmentation and registration models have in case of encountering multiple objects into an image or their highly dependence on the initialisation or the need for a pre-registration step, which has an impact on the segmentation results. Through different numerical results, we show that the proposed model gives correct registration results when there are different features inside the object to be segmented or features that have clear boundaries but without fine details in which the old model would not be able to cope.

Integrating Feature Direction Information with a Level Set Formulation for Image Segmentation

2016 ◽  
Vol 6 (1) ◽  
pp. 1-22 ◽  
Author(s):  
Meng Li ◽  
Yi Zhan
Keyword(s):  
Image Segmentation ◽  
Level Set ◽  
Directional Derivative ◽  
Image Features ◽  
Second Order ◽  
Directional Derivatives ◽  
Level Set Function ◽  
Variational Framework ◽  
Level Set Evolution ◽  
Level Set Formulation

AbstractA feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and our method can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.

Sign in / Sign up

Export Citation Format

Share Document