Sorry, you need to enable JavaScript to visit this website.

Image/Video Processing

PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization


Interior point methods have been known for decades to be useful for the resolution of small to medium size constrained optimization problems. These approaches have the benefit of ensuring feasibility of the iterates through a logarithmic barrier. We propose to incorporate a proximal forward-backward step in the resolution of the barrier subproblem to account for non-necessarily differentiable terms arising in the objective function.

Paper Details

Authors:
Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet
Submitted On:
17 April 2018 - 9:36pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_presentation.pdf

(85 downloads)

Keywords

Subscribe

[1] Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet, "PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2718. Accessed: Jul. 16, 2018.
@article{2718-18,
url = {http://sigport.org/2718},
author = {Marie-Caroline Corbineau; Emilie Chouzenoux; Jean-Christophe Pesquet },
publisher = {IEEE SigPort},
title = {PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization},
year = {2018} }
TY - EJOUR
T1 - PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization
AU - Marie-Caroline Corbineau; Emilie Chouzenoux; Jean-Christophe Pesquet
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2718
ER -
Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet. (2018). PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization. IEEE SigPort. http://sigport.org/2718
Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet, 2018. PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization. Available at: http://sigport.org/2718.
Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet. (2018). "PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization." Web.
1. Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet. PIPA : A New proximal Interior Point Algorithm for Large-Scale Convex Optimization [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2718

STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING


This paper studies the problem of full reference visual quality assessment of denoised images with a special emphasis on images with low contrast and noise-like texture. Denoising of such images together with noise removal often results in image details loss or smoothing. A new test image database, FLT, containing 75 noise-free ‘reference’ images and 300 filtered (‘distorted’) images is developed. Each reference image, corrupted by an additive white Gaussian noise, is denoised by the BM3D filter with four different values of threshold parameter (four levels of noise suppression).

Paper Details

Authors:
Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev
Submitted On:
13 April 2018 - 6:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides of ICASSP 2018 presentation

(38 downloads)

Keywords

Additional Categories

Subscribe

[1] Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev, "STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2681. Accessed: Jul. 16, 2018.
@article{2681-18,
url = {http://sigport.org/2681},
author = {Karen Egiazarian; Mykola Ponomarenko; Vladimir Lukin; Oleg Ieremeiev },
publisher = {IEEE SigPort},
title = {STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING},
year = {2018} }
TY - EJOUR
T1 - STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING
AU - Karen Egiazarian; Mykola Ponomarenko; Vladimir Lukin; Oleg Ieremeiev
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2681
ER -
Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev. (2018). STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING. IEEE SigPort. http://sigport.org/2681
Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev, 2018. STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING. Available at: http://sigport.org/2681.
Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev. (2018). "STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING." Web.
1. Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiev. STATISTICAL EVALUATION OF VISUAL QUALITY METRICS FOR IMAGE DENOISING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2681

A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection


Visual surface inspection is a challenging task due to the highly inconsistent appearance of the target surfaces and the abnormal regions. Most of the state-of-the-art methods are highly dependent on the labelled training samples, which are difficult to collect in practical industrial applications. To address this problem, we propose a generative adversarial network based framework for unsupervised surface inspection. The generative adversarial network is trained to generate the fake images analogous to the normal surface images.

Paper Details

Authors:
Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang
Submitted On:
13 April 2018 - 5:01am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

This is the presentation slides of ICASSP 2018.

(69 downloads)

Keywords

Subscribe

[1] Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang, "A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2660. Accessed: Jul. 16, 2018.
@article{2660-18,
url = {http://sigport.org/2660},
author = {Wei Zhai;Jiang Zhu;Yang Cao; Zengfu Wang },
publisher = {IEEE SigPort},
title = {A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection},
year = {2018} }
TY - EJOUR
T1 - A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection
AU - Wei Zhai;Jiang Zhu;Yang Cao; Zengfu Wang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2660
ER -
Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang. (2018). A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection. IEEE SigPort. http://sigport.org/2660
Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang, 2018. A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection. Available at: http://sigport.org/2660.
Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang. (2018). "A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection." Web.
1. Wei Zhai,Jiang Zhu,Yang Cao, Zengfu Wang. A Generative Adversarial Network Based Framework For Unsupervised Visual Surface Inspection [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2660

COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL

Paper Details

Authors:
Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai
Submitted On:
13 April 2018 - 4:42am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICASSP2018yamanaka_0412.pdf

(35 downloads)

Keywords

Subscribe

[1] Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai, "COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2654. Accessed: Jul. 16, 2018.
@article{2654-18,
url = {http://sigport.org/2654},
author = {Seisuke Kyochi; Shunsuke Ono; Keiichiro Shirai },
publisher = {IEEE SigPort},
title = {COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL},
year = {2018} }
TY - EJOUR
T1 - COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL
AU - Seisuke Kyochi; Shunsuke Ono; Keiichiro Shirai
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2654
ER -
Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai. (2018). COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL. IEEE SigPort. http://sigport.org/2654
Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai, 2018. COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL. Available at: http://sigport.org/2654.
Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai. (2018). "COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL." Web.
1. Seisuke Kyochi, Shunsuke Ono, Keiichiro Shirai. COLOR AFFINE SUBSPACE PURSUIT FOR COLOR ARTIFACT REMOVAL [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2654

L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS

Paper Details

Authors:
M. Oliver, G. Haro, V. Fedorov, C. Ballester
Submitted On:
13 April 2018 - 3:48am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MariaOliver.pdf

(44 downloads)

Keywords

Subscribe

[1] M. Oliver, G. Haro, V. Fedorov, C. Ballester, "L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2638. Accessed: Jul. 16, 2018.
@article{2638-18,
url = {http://sigport.org/2638},
author = {M. Oliver; G. Haro; V. Fedorov; C. Ballester },
publisher = {IEEE SigPort},
title = {L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS},
year = {2018} }
TY - EJOUR
T1 - L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS
AU - M. Oliver; G. Haro; V. Fedorov; C. Ballester
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2638
ER -
M. Oliver, G. Haro, V. Fedorov, C. Ballester. (2018). L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS. IEEE SigPort. http://sigport.org/2638
M. Oliver, G. Haro, V. Fedorov, C. Ballester, 2018. L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS. Available at: http://sigport.org/2638.
M. Oliver, G. Haro, V. Fedorov, C. Ballester. (2018). "L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS." Web.
1. M. Oliver, G. Haro, V. Fedorov, C. Ballester. L1 PATCH-BASED IMAGE PARTITIONING INTO HOMOGENEOUS TEXTURED REGIONS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2638

Statistical t+2D Subband Modelling for Crowd Counting


Counting people automatically in a crowded scenario is important to assess safety and to determine behaviour in surveillance operations. In this paper we propose a new algorithm using the statistics of the spatio-temporal wavelet subbands. A t+2D lifting based wavelet transform is exploited to generate a motion saliency map which is then used to extract novel parametric statistical texture features. We compare our approach to existing crowd counting approaches and show improvement on standard benchmark sequences, demonstrating the robustness of the extracted features.

Paper Details

Authors:
Deepayan Bhowmik, Andrew Wallace
Submitted On:
13 April 2018 - 3:34am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018-poster-dbhowmik.pdf

(33 downloads)

Keywords

Subscribe

[1] Deepayan Bhowmik, Andrew Wallace, "Statistical t+2D Subband Modelling for Crowd Counting", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2635. Accessed: Jul. 16, 2018.
@article{2635-18,
url = {http://sigport.org/2635},
author = {Deepayan Bhowmik; Andrew Wallace },
publisher = {IEEE SigPort},
title = {Statistical t+2D Subband Modelling for Crowd Counting},
year = {2018} }
TY - EJOUR
T1 - Statistical t+2D Subband Modelling for Crowd Counting
AU - Deepayan Bhowmik; Andrew Wallace
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2635
ER -
Deepayan Bhowmik, Andrew Wallace. (2018). Statistical t+2D Subband Modelling for Crowd Counting. IEEE SigPort. http://sigport.org/2635
Deepayan Bhowmik, Andrew Wallace, 2018. Statistical t+2D Subband Modelling for Crowd Counting. Available at: http://sigport.org/2635.
Deepayan Bhowmik, Andrew Wallace. (2018). "Statistical t+2D Subband Modelling for Crowd Counting." Web.
1. Deepayan Bhowmik, Andrew Wallace. Statistical t+2D Subband Modelling for Crowd Counting [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2635

AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES


Uneven illumination and shadows in document images cause a challenge for digitization applications and automated workflows. In this work, we propose a new method to recover un-shadowed document images from images with shadows/uneven illumination. We pose this problem as one of estimating the shading and reflectance components of the given original image. Our method first estimates the shading and uses it to compute the reflectance. The output reflectance map is then used to improve the shading and the process is repeated in an iterative manner.

Paper Details

Authors:
Vineet Gandhi
Submitted On:
13 April 2018 - 2:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_poster.pdf

(114 downloads)

Keywords

Subscribe

[1] Vineet Gandhi, "AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2621. Accessed: Jul. 16, 2018.
@article{2621-18,
url = {http://sigport.org/2621},
author = {Vineet Gandhi },
publisher = {IEEE SigPort},
title = {AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES},
year = {2018} }
TY - EJOUR
T1 - AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES
AU - Vineet Gandhi
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2621
ER -
Vineet Gandhi. (2018). AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES. IEEE SigPort. http://sigport.org/2621
Vineet Gandhi, 2018. AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES. Available at: http://sigport.org/2621.
Vineet Gandhi. (2018). "AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES." Web.
1. Vineet Gandhi. AN ITERATIVE APPROACH FOR SHADOW REMOVAL IN DOCUMENT IMAGES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2621

PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO


A large-scale video quality dataset called the VideoSet has been constructed recently to measure human subjective experience of H.264 coded video in terms of the just-noticeable-difference (JND). It measures the first three JND points of 5-second video of resolution 1080p, 720p, 540p and 360p. Based on the VideoSet, we propose a method to predict the satisfied-user-ratio (SUR) curves using a machine learning framework. First, we partition a video clip into local spatial-temporal segments and evaluate the quality of each seg- ment using the VMAF quality index.

Paper Details

Authors:
Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo
Submitted On:
18 April 2018 - 11:47am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

JND_prediction_ICASSP_v2.pdf

(33 downloads)

Keywords

Subscribe

[1] Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo, "PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2605. Accessed: Jul. 16, 2018.
@article{2605-18,
url = {http://sigport.org/2605},
author = {Ioannis Katsavounidis; Qin Huang; Xin Zhou; and C.-C. Jay Kuo },
publisher = {IEEE SigPort},
title = {PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO},
year = {2018} }
TY - EJOUR
T1 - PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO
AU - Ioannis Katsavounidis; Qin Huang; Xin Zhou; and C.-C. Jay Kuo
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2605
ER -
Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo. (2018). PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO. IEEE SigPort. http://sigport.org/2605
Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo, 2018. PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO. Available at: http://sigport.org/2605.
Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo. (2018). "PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO." Web.
1. Ioannis Katsavounidis, Qin Huang, Xin Zhou, and C.-C. Jay Kuo. PREDICTION OF SATISFIED USER RATIO FOR COMPRESSED VIDEO [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2605

NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE

Paper Details

Authors:
Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen
Submitted On:
13 April 2018 - 12:15am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Feifan Guan_ICASSP2018_Paper#1018.pdf

(32 downloads)

Keywords

Subscribe

[1] Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen , "NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2581. Accessed: Jul. 16, 2018.
@article{2581-18,
url = {http://sigport.org/2581},
author = {Gangyi Jiang; Yang Song; Mei Yu; Zongju Peng; Fen Chen },
publisher = {IEEE SigPort},
title = {NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE},
year = {2018} }
TY - EJOUR
T1 - NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE
AU - Gangyi Jiang; Yang Song; Mei Yu; Zongju Peng; Fen Chen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2581
ER -
Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen . (2018). NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE. IEEE SigPort. http://sigport.org/2581
Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen , 2018. NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE. Available at: http://sigport.org/2581.
Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen . (2018). "NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE." Web.
1. Gangyi Jiang, Yang Song, Mei Yu, Zongju Peng, Fen Chen . NO-REFERENCE HDR IMAGE QUALITY ASSESSMENT METHOD BASED ON TENSOR SPACE [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2581

Cross-Modal Message Passing for Two-stream Fusion

Paper Details

Authors:
Dong Wang, Yuan Yuan, Qi Wang
Submitted On:
12 April 2018 - 9:41pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides for the paper

(31 downloads)

Keywords

Subscribe

[1] Dong Wang, Yuan Yuan, Qi Wang, "Cross-Modal Message Passing for Two-stream Fusion", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2546. Accessed: Jul. 16, 2018.
@article{2546-18,
url = {http://sigport.org/2546},
author = {Dong Wang; Yuan Yuan; Qi Wang },
publisher = {IEEE SigPort},
title = {Cross-Modal Message Passing for Two-stream Fusion},
year = {2018} }
TY - EJOUR
T1 - Cross-Modal Message Passing for Two-stream Fusion
AU - Dong Wang; Yuan Yuan; Qi Wang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2546
ER -
Dong Wang, Yuan Yuan, Qi Wang. (2018). Cross-Modal Message Passing for Two-stream Fusion. IEEE SigPort. http://sigport.org/2546
Dong Wang, Yuan Yuan, Qi Wang, 2018. Cross-Modal Message Passing for Two-stream Fusion. Available at: http://sigport.org/2546.
Dong Wang, Yuan Yuan, Qi Wang. (2018). "Cross-Modal Message Passing for Two-stream Fusion." Web.
1. Dong Wang, Yuan Yuan, Qi Wang. Cross-Modal Message Passing for Two-stream Fusion [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2546

Pages