Image Processing On Line

IPOL is a research journal of image processing and image analysis which emphasizes the role of mathematics as a source for algorithm design and the reproducibility of the research. Each article contains a text on an algorithm and its source code, with an online demonstration facility and an archive of experiments. Text and source code are peer-reviewed and the demonstration is controlled. IPOL is an Open Science and Reproducible Research journal.

  policy Editorial Policy   board Editorial Board   submit Submit an Article   email twitter feed Follow IPOL

  index Index · Articles 2011 2012 2013 2014 2015 2016 · Preprints · News · Citation score

Latest Articles

Implementation of the Midway Image Equalization
2016-06-21 · Thierry Guillemot, Julie Delon
Fundamental Matrix of a Stereo Pair, with A Contrario Elimination of Outliers
2016-05-17 · Lionel Moisan, Pierre Moulon, Pascal Monasse
Directional Filters for Cartoon + Texture Image Decomposition
2016-05-05 · Antoni Buades, Jose-Luis Lisani
On the Implementation of Collaborative TV Regularization: Application to Cartoon+Texture Decomposition
2016-04-20 · Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers
Computing an Exact Gaussian Scale-Space
2016-02-02 · Ives Rey Otero, Mauricio Delbracio

Series and Special Issues

{->}Special Issue on Discrete Geometry (DGCI 2011)

A Streaming Distance Transform Algorithm for Neighborhood-Sequence Distances We describe an algorithm that computes a “translated” 2D Neighborhood-Sequence Distance Transform (DT) using a look up table approach. It requires a single raster scan of the input image and produces one line of output for every line of input. The neighborhood sequence is specified either by providing one period of some integer periodic sequence or by providing the rate of appearance of neighborhoods. The full algorithm optionally derives the regular (centered) DT from the “translated” DT, providing the result image on-the-fly, with a minimal delay, before the input image is fully processed. Its efficiency can benefit all applications that use neighborhood- sequence distances, particularly when pipelined processing architectures are involved, or when the size of objects in the source image is limited.
Digital Level Layers for Digital Curve Decomposition and Vectorization The purpose of this paper is to present Digital Level Layers and show the motivations for working with such analytical primitives in the framework of Digital Geometry. We first compare their properties to morphological and topological counterparts, and then we explain how to recognize them and use them to decompose or vectorize digital curves and contours.
A Near-Linear Time Guaranteed Algorithm for Digital Curve Simplification Under the Fréchet Distance In this paper, we propose an algorithm that, from a maximum error and a digital curve (4- or 8-connected), computes a simplification of the curve (a polygonal curve) such that the Fréchet distance between the original and the simplified curve is less than the error. The Fréchet distance is known to nicely measure the similarity between two curves. The algorithm we propose uses an approximation of the Fréchet distance, but a guarantee over the quality of the simplification is proved. Moreover, even if the theoretical complexity of the algorithm is in O(n log(n)), experiments show a linear behaviour in practice.
Meaningful Scales Detection: an Unsupervised Noise Detection Algorithm for Digital Contours This work presents an algorithm which permits to detect locally on digital contour what is the amount of noise estimated from a given maximal scale. The method is based on the asymptotic properties of the length of the maximal segment primitive.
Interactive Segmentation Based on Component-trees Component-trees associate to a discrete gray-level image a descriptive data structure induced by the inclusion relation between the binary components obtained at successive level-sets. This article presents an interactive segmentation methodology based on component-trees. It consists of the extraction of a subset of the image component-tree, enabling the generation of a binary object which fits at best (with respect to the gray-level structure of the image) a given binary target selected beforehand in the image. Compared to other interactive segmentation methods, the proposed methodology has the following advantages: (i) the segmentation result is only composed of a union of connected components of the level-sets, which ensures that no 'false contours' are included; (ii) only one image marker is needed: in particular, there is no need to give a marker for the background (contrary to some other methods); (iii) the method is fast and efficient, leading to a result computed in real-time on common image sizes.
Extraction of Connected Region Boundary in Multidimensional Images This paper presents an algorithm to extract the boundary of a connected region(s) using classical topology definitions. From a given adjacency definition, the proposed method is able to extract the boundary of an object in a generic way, independently of the dimension of the digital space.

{->}SIIMS Companion Papers

Recovering the Subpixel PSF from Two Photographs at Different Distances In most typical digital cameras, even high-end digital single lens reflex ones (DSLR), the acquired images are sampled at rates below the Nyquist critical rate, causing aliasing effects. In this work we describe a new algorithm for the estimation of the point spread function (PSF) of a digital camera from aliased photographs, that achieves subpixel accuracy. The procedure is based on taking two parallel photographs of the same scene, from different distances leading to different geometric zooms, and then estimating the kernel blur between them.
The Implementation of SURE Guided Piecewise Linear Image Denoising SURE (Stein's Unbiased Risk Estimator) guided Piecewise Linear Estimation (S-PLE) is a recently introduced patch-based state-of-the-art denoising algorithm. In this article, we focus on its implementation and show its performance by comparing it with several other acclaimed algorithms.
Implementation of the "Non-Local Bayes" (NL-Bayes) Image Denoising Algorithm This article presents a detailed implementation of the Non-Local Bayes (NL-Bayes) image denoising algorithm. In a nutshell, NL-Bayes is an improved variant of NL-means. In the NL-means algorithm, each patch is replaced by a weighted mean of the most similar patches present in a neighborhood. Images being mostly self-similar, such instances of similar patches are generally found, and averaging them increases the SNR. The NL-Bayes strategy improves on NL-means by evaluating for each group of similar patches a Gaussian vector model. To each patch is therefore associated a mean (which would be the result of NL-means), but also a covariance matrix estimating the variability of the patch group. This permits to compute an optimal (in the sense of Bayesian minimal mean square error) estimate of each noisy patch in the group, by a simple matrix inversion. The implementation proceeds in two identical iterations, but the second iteration uses the denoised image of the first iteration to estimate better the mean and covariance of the patch Gaussian models. A discussion of the algorithm shows that it is close in spirit to several state of the art algorithms (TSID, BM3D, BM3D-SAPCA), and that its structure is actually close to BM3D. Thorough experimental comparison made in this paper also shows that the algorithm achieves the best state of the art on color images in terms of PSNR and image quality. On grey level images, it reaches a performance similar to the more complex BM3D-SAPCA (no color version is available for this last algorithm).
<TMPL_VAR raw_title> <TMPL_VAR raw_abstract>
Image Interpolation with Geometric Contour Stencils We consider the image interpolation problem where given an image v<sub>m,n</sub> with uniformly-sampled pixels vm,n and point spread function h, the goal is to find function u(x,y) satisfying v<sub>m,n</sub> = (h*u)(m,n) for all m,n in Z. This article improves upon the IPOL article Image Interpolation with Contour Stencils. In the previous work, contour stencils are used to estimate the image contours locally as short line segments. This article begins with a continuous formulation of total variation integrated over a collection of curves and defines contour stencils as a consistent discretization. This discretization is more reliable than the previous approach and can effectively distinguish contours that are locally shaped like lines, curves, corners, and circles. These improved contour stencils sense more of the geometry in the image. Interpolation is performed using an extension of the method described in the previous article. Using the improved contour stencils, there is an increase in image quality while maintaining similar computational efficiency.



Farman Institute 3D Point Sets - High Precision 3D Data Sets
2011-09-27 · Julie Digne, Nicolas Audfray, Claire Lartigue, Charyar Mehdi-Souzani, Jean-Michel Morel


Computing an Exact Gaussian Scale-Space
2016-02-02 · Ives Rey Otero, Mauricio Delbracio
A Survey of Gaussian Convolution Algorithms
2013-12-17 · Pascal Getreuer


Automatic Lens Distortion Correction Using One-Parameter Division Models
2014-11-20 · Miguel Alemán-Flores, Luis Alvarez, Luis Gomez, Daniel Santana-Cedrés
Recovering the Subpixel PSF from Two Photographs at Different Distances
2013-10-23 · Mauricio Delbracio, Andrés Almansa, Pablo Musé
Non-parametric Sub-pixel Local Point Spread Function Estimation
2012-03-23 · Mauricio Delbracio, Pablo Musé, Andrés Almansa
Algebraic Lens Distortion Model Estimation
2010-07-28 · Luis Alvarez, Luis Gomez, J. Rafael Sendra
An Iterative Optimization Algorithm for Lens Distortion Correction Using Two-Parameter Models
PREPRINT · Daniel Santana-Cedrés, Luis Gómez, Miguel Alemán-Flores, Agustín Salgado, Julio Esclarín, Luis Mazorra, Luis Álvarez

{->}Color and Contrast

Implementation of the Midway Image Equalization
2016-06-21 · Thierry Guillemot, Julie Delon
An Algorithmic Analysis of Variational Models for Perceptual Local Contrast Enhancement
2015-07-29 · Sira Ferradans, R. Palma-Amestoy, E. Provenzi
Multiscale Retinex
2014-04-16 · Ana Belén Petro, Catalina Sbert, Jean-Michel Morel
Screened Poisson Equation for Image Contrast Enhancement
2014-03-11 · Jean-Michel Morel, Ana-Belen Petro, Catalina Sbert
Selective Contrast Adjustment by Poisson Equation
2013-09-26 · Ana-Belen Petro, Catalina Sbert
Color and Contrast Enhancement by Controlled Piecewise Affine Histogram Equalization
2012-10-17 · Jose-Luis Lisani, Ana-Belen Petro, Catalina Sbert
Simplest Color Balance
2011-10-24 · Nicolas Limare, Jose-Luis Lisani, Jean-Michel Morel, Ana Belén Petro, Catalina Sbert
Local Color Correction
2011-09-27 · Juan Gabriel Gomila Salas, Jose Luis Lisani
Image Color Cube Dimensional Filtering and Visualization
2011-06-22 · Jose-Luis Lisani, Antoni Buades, Jean-Michel Morel
Retinex Poisson Equation: a Model for Color Perception
2011-04-05 · Nicolas Limare, Ana Belén Petro, Catalina Sbert, Jean-Michel Morel

{->}Computational Photography

The Flutter Shutter Code Calculator
2015-08-19 · Yohann Tendero
Obtaining High Quality Photographs of Paintings by Image Fusion
2015-06-27 · Antoni Buades, Gloria Haro, Enric Meinhardt-Llopis
The Flutter Shutter Camera Simulator
2012-10-17 · Yohann Tendero


Implementation of Nonlocal Pansharpening Image Fusion
2014-02-28 · Antoni Buades, Bartomeu Coll, Joan Duran, Catalina Sbert
Image Demosaicking with Contour Stencils
2012-03-24 · Pascal Getreuer
Zhang-Wu Directional LMMSE Image Demosaicking
2011-09-01 · Pascal Getreuer
Malvar-He-Cutler Linear Image Demosaicking
2011-08-14 · Pascal Getreuer
Self-similarity Driven Demosaicking
2011-06-01 · Antoni Buades, Bartomeu Coll, Jean-Michel Morel, Catalina Sbert


On the Implementation of Collaborative TV Regularization: Application to Cartoon+Texture Decomposition
2016-04-20 · Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers
The Noise Clinic: a Blind Image Denoising Algorithm
2015-01-28 · Marc Lebrun, Miguel Colom, Jean-Michel Morel
Chambolle's Projection Algorithm for Total Variation Denoising
2013-12-17 · Joan Duran, Bartomeu Coll, Catalina Sbert
Implementation of the "Non-Local Bayes" (NL-Bayes) Image Denoising Algorithm
2013-06-17 · Marc Lebrun, Antoni Buades, Jean-Michel Morel
Non-Local Means Denoising
2011-09-13 · Antoni Buades, Bartomeu Coll, Jean-Michel Morel
PARIGI: a Patch-based Approach to Remove Impulse-Gaussian Noise from Images
PREPRINT · Julie Delon, Agnès Desolneux, Thierry Guillemot


A Streaming Distance Transform Algorithm for Neighborhood-Sequence Distances
2014-09-01 · Nicolas Normand, Robin Strand, Pierre Evenou, Aurore Arlicot
Digital Level Layers for Digital Curve Decomposition and Vectorization
2014-07-30 · Laurent Provot, Yan Gerard, Fabien Feschet
Interactive Segmentation Based on Component-trees
2014-05-05 · Benoît Naegel, Nicolas Passat
Extraction of Connected Region Boundary in Multidimensional Images
2014-03-26 · David Coeurjolly, Bertrand Kerautret, Jacques-Olivier Lachaud


Non-uniformity Correction of Infrared Images by Midway Equalization
2012-07-12 · Yohann Tendero, Stéphane Landeau, Jérôme Gilles

{->}Learning and Detection


Variational Framework for Non-Local Inpainting
2015-12-26 · Vadim Fedorov, Gabriele Facciolo, Pablo Arias
E-PLE: an Algorithm for Image Inpainting
2013-12-04 · Yi-Qing Wang
Combined First and Second Order Total Variation Inpainting using Split Bregman
2013-07-12 · Konstantinos Papafitsoros, Carola Bibiane Schoenlieb, Bati Sengul
Total Variation Inpainting using Split Bregman
2012-07-30 · Pascal Getreuer


{->}Image Comparison

An Analysis of the SURF Method
2015-07-20 · Edouard Oyallon, Julien Rabin
Anatomy of the SIFT Method
2014-12-22 · Ives Rey Otero, Mauricio Delbracio
ASIFT: An Algorithm for Fully Affine Invariant Comparison
2011-02-24 · Guoshen Yu, Jean-Michel Morel
Geometric Expansion for Local Feature Analysis and Matching
PREPRINT · Erez Farhan, Elad Meir, Rami Hagege

{->}Optical Flow

An Implementation of Combined Local-Global Optical Flow
2015-06-25 · Jorge Jara-Wilde, Mauricio Cerda, José Delpiano, Steffen Härtel
Robust Optical Flow Estimation
2013-10-28 · Javier Sánchez Pérez, Nelson Monzón López, Agustín Salgado de la Nuez
Horn-Schunck Optical Flow with a Multi-Scale Strategy
2013-07-19 · Enric Meinhardt-Llopis, Javier Sánchez Pérez, Daniel Kondermann
TV-L1 Optical Flow Estimation
2013-07-19 · Javier Sánchez Pérez, Enric Meinhardt-Llopis, Gabriele Facciolo
Robust Discontinuity Preserving Optical Flow Methods
PREPRINT · Nelson Monzón, Agustín Salgado, Javier Sánchez
Joint TV-L1 Optical Flow and Occlusion Estimation
PREPRINT · Juan Francisco Garamendi Bragado, Coloma Ballester, Lluís Garrido, Vanel Lazcano, Vicent Caselles


Finite Difference Schemes for MCM and AMSS
2011-09-13 · Marco Mondelli, Adina Ciomaga
Poisson Image Editing
PREPRINT · J. Matías Di Martino, Gabriele Facciolo, Enric Meinhardt-Llopis
Image Curvature Microscope
PREPRINT · Adina Ciomaga, Lionel Moisan, Pascal Monasse, Jean-Michel Morel

{->}Segmentation and Edges

An Unsupervised Point Alignment Detection Algorithm
2015-12-15 · José Lezama, Gregory Randall, Jean-Michel Morel, Rafael Grompone von Gioi
A Review of Classic Edge Detectors
2015-06-07 · Haldo Spontón, Juan Cardelino
Chan-Vese Segmentation
2012-08-08 · Pascal Getreuer
LSD: a Line Segment Detector
2012-03-24 · Rafael Grompone von Gioi, Jérémie Jakubowicz, Jean-Michel Morel, Gregory Randall
A Real Time Morphological Snakes Algorithm
2012-03-23 · Luis Alvarez, Luis Baumela, Pablo Márquez-Neila, Pedro Henríquez
Unsupervised Smooth Contour Detection
PREPRINT · Rafael Grompone von Gioi, Gregory Randall
A C++ Implementation of Otsu’s Image Segmentation Method
PREPRINT · Juan Pablo Balarini, Sergio Nesmachnow
Vanishing Point Detection in Urban Scenes Using Point Alignments
PREPRINT · José Lezama, Gregory Randall, Rafael Grompone von Gioi


Fundamental Matrix of a Stereo Pair, with A Contrario Elimination of Outliers
2016-05-17 · Lionel Moisan, Pierre Moulon, Pascal Monasse
Bilaterally Weighted Patches for Disparity Map Computation
2015-03-11 · Laura Fernández Julià, Pascal Monasse
Integral Images for Block Matching
2014-12-16 · Gabriele Facciolo, Nicolas Limare, Enric Meinhardt-Llopis
Stereo Disparity through Cost Aggregation with Guided Filter
2014-10-23 · Pauline Tan, Pascal Monasse
Kolmogorov and Zabih’s Graph Cuts Stereo Matching Algorithm
2014-10-15 · Vladimir Kolmogorov, Pascal Monasse, Pauline Tan
Quasi-Euclidean Epipolar Rectification
2011-09-13 · Pascal Monasse


Directional Filters for Cartoon + Texture Image Decomposition
2016-05-05 · Antoni Buades, Jose-Luis Lisani
The Heeger & Bergen Pyramid Based Texture Synthesis Algorithm
2014-11-17 · Thibaud Briand, Jonathan Vacher, Bruno Galerne, Julien Rabin
Exemplar-based Texture Synthesis: the Efros-Leung Algorithm
2013-10-23 · Cecilia Aguerrebere, Yann Gousseau, Guillaume Tartavel
Micro-Texture Synthesis by Phase Randomization
2011-09-23 · Bruno Galerne, Yann Gousseau, Jean-Michel Morel
Cartoon+Texture Image Decomposition
2011-09-13 · Antoni Buades, Triet Le, Jean-Michel Morel, Luminita Vese

{->}Vision Through Turbulence

Implementation of the Centroid Method for the Correction of Turbulence
2014-07-31 · Enric Meinhardt-Llopis, Mario Micheli
Mao-Gilles Stabilization Algorithm
2013-07-19 · Jérôme Gilles
Study of the Principal Component Analysis Method for the Correction of Images Degraded by Turbulence
PREPRINT · Tristan Dagobert, Yohann Tendero, Stéphane Landeau

{->}Computer Graphics

Accelerating Monte Carlo Renderers by Ray Histogram Fusion
2015-03-11 · Mauricio Delbracio, Pablo Musé, Antoni Buades, Jean-Michel Morel

{->}Satellite Imaging

Attitude Refinement for Orbiting Pushbroom Cameras: a Simple Polynomial Fitting Method
2015-12-26 · Carlo de Franchis, Enric Meinhardt-Llopis, Daniel Greslou, Gabriele Facciolo

Latest News

IPOL at the RCBR Workshop of NTMS 2015
IPOL is now indexed by DBLP
IPOL accepts Matlab code
IPOL at ICM 2014
Training Session on Web Demos at RFIA Congress
IPOL at 8th Saclay CSIS Meeting