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

Image/Video Processing

Fitness Heart Rate Measurement Using Face Videos


Recent studies showed that subtle changes in human’s face color due to the heartbeat can be captured by digital video recorders. Most work focused on still/rest cases or those with relatively small motions. In this work, we propose a heart-rate monitoring method for fitness exercise videos. We focus on building a highly precise motion compensation scheme with the help of the optical flow, and use motion information as a cue to adaptively remove ambiguous frequency components for improving the heart rates estimates.

Paper Details

Authors:
Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu
Submitted On:
19 October 2017 - 11:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation slides (pdf version)

(33 downloads)

Presentation slides (ppt version)

(33 downloads)

Keywords

Additional Categories

Subscribe

[1] Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu, "Fitness Heart Rate Measurement Using Face Videos", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2244. Accessed: Dec. 15, 2017.
@article{2244-17,
url = {http://sigport.org/2244},
author = {Qiang Zhu; Chau-Wai Wong; Chang-Hong Fu; Min Wu },
publisher = {IEEE SigPort},
title = {Fitness Heart Rate Measurement Using Face Videos},
year = {2017} }
TY - EJOUR
T1 - Fitness Heart Rate Measurement Using Face Videos
AU - Qiang Zhu; Chau-Wai Wong; Chang-Hong Fu; Min Wu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2244
ER -
Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu. (2017). Fitness Heart Rate Measurement Using Face Videos. IEEE SigPort. http://sigport.org/2244
Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu, 2017. Fitness Heart Rate Measurement Using Face Videos. Available at: http://sigport.org/2244.
Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu. (2017). "Fitness Heart Rate Measurement Using Face Videos." Web.
1. Qiang Zhu, Chau-Wai Wong, Chang-Hong Fu, Min Wu. Fitness Heart Rate Measurement Using Face Videos [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2244

Mondrian Stereo


Untextured scenes with complex occlusions still present challenges to modern stereo algorithms. We consider the pathological case of Mondrian Stereo—scenes consisting solely of solid-colored planar regions, inspired by paintings by Piet Mondrian. We analyze assumptions that allow disambiguating such scenes and present a novel stereo algorithm employing symbolic reasoning about matched edge segments. We demonstrate compelling stereo matching results on synthetic scenes and discuss how our insights could be utilized in robust real-world stereo algorithms for untextured environments.

Paper Details

Authors:
Daniel Scharstein
Submitted On:
20 September 2017 - 1:18pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

mondrian_stereo.pdf

(42 downloads)

Keywords

Subscribe

[1] Daniel Scharstein, "Mondrian Stereo", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2241. Accessed: Dec. 15, 2017.
@article{2241-17,
url = {http://sigport.org/2241},
author = {Daniel Scharstein },
publisher = {IEEE SigPort},
title = {Mondrian Stereo},
year = {2017} }
TY - EJOUR
T1 - Mondrian Stereo
AU - Daniel Scharstein
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2241
ER -
Daniel Scharstein. (2017). Mondrian Stereo. IEEE SigPort. http://sigport.org/2241
Daniel Scharstein, 2017. Mondrian Stereo. Available at: http://sigport.org/2241.
Daniel Scharstein. (2017). "Mondrian Stereo." Web.
1. Daniel Scharstein. Mondrian Stereo [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2241

FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS


The reconstruction of real world objects becomes even more important in the view of creating highly realistic scenes for Virtual Reality applications. In this paper, we present a fully automated algorithmic pipeline for high-quality 3D reconstruction of real world objects. The proposed method refines an initial 3D model by exploiting the results of additional pairwise stereo depth estimation. An automatic camera selection approach provides different point clouds, which are fused into a common coherent and highly detailed 3D model.

Paper Details

Authors:
Thomas Ebner, Oliver Schreer, Ingo Feldmann
Submitted On:
20 September 2017 - 3:30am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2017_ICIP_Poster.pdf

(43 downloads)

Keywords

Subscribe

[1] Thomas Ebner, Oliver Schreer, Ingo Feldmann, "FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2239. Accessed: Dec. 15, 2017.
@article{2239-17,
url = {http://sigport.org/2239},
author = {Thomas Ebner; Oliver Schreer; Ingo Feldmann },
publisher = {IEEE SigPort},
title = {FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS},
year = {2017} }
TY - EJOUR
T1 - FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS
AU - Thomas Ebner; Oliver Schreer; Ingo Feldmann
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2239
ER -
Thomas Ebner, Oliver Schreer, Ingo Feldmann. (2017). FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS. IEEE SigPort. http://sigport.org/2239
Thomas Ebner, Oliver Schreer, Ingo Feldmann, 2017. FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS. Available at: http://sigport.org/2239.
Thomas Ebner, Oliver Schreer, Ingo Feldmann. (2017). "FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS." Web.
1. Thomas Ebner, Oliver Schreer, Ingo Feldmann. FULLY AUTOMATED HIGHLY ACCURATE 3D RECONSTRUCTION FROM MULTIPLE VIEWS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2239

HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST


In this paper, we propose a method for automatic hand gesture recognition using a random regression forest with a novel set of feature descriptors created from skeletal data acquired from the Leap Motion Controller. The efficacy of our proposed approach is evaluated on the publicly available University of Padova Microsoft Kinect and Leap Motion dataset, as well as 24 letters of the English alphabet in American Sign Language. The letters that are dynamic (e.g. j and z) are not evaluated.

Paper Details

Authors:
Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin
Submitted On:
19 September 2017 - 8:27pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST

(50 downloads)

Keywords

Subscribe

[1] Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin, "HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2236. Accessed: Dec. 15, 2017.
@article{2236-17,
url = {http://sigport.org/2236},
author = {Shaun Canavan; Walter Keyes; Ryan McCormick; Julie Kunnumpurath; Tanner Hoelzel; Lijun Yin },
publisher = {IEEE SigPort},
title = {HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST},
year = {2017} }
TY - EJOUR
T1 - HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST
AU - Shaun Canavan; Walter Keyes; Ryan McCormick; Julie Kunnumpurath; Tanner Hoelzel; Lijun Yin
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2236
ER -
Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin. (2017). HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST. IEEE SigPort. http://sigport.org/2236
Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin, 2017. HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST. Available at: http://sigport.org/2236.
Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin. (2017). "HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST." Web.
1. Shaun Canavan, Walter Keyes, Ryan McCormick, Julie Kunnumpurath, Tanner Hoelzel, Lijun Yin. HAND GESTURE RECOGNITION USING A SKELETON-BASED FEATURE REPRESENTATION WITH A RANDOM REGRESSION FOREST [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2236

Combining Gaze and Demographic Feature Desciptors for Autism Classification


People with autism suffer from social challenges and communication difficulties, which may prevent them from leading a fruitful and enjoyable life. It is imperative to diagnose and start treatments for autism as early as possible and, in order to do so, accurate methods of identifying the disorder are vital. We propose a novel method for classifying autism through the use of eye gaze and demographic feature descriptors that include a subject’s age and gender. We construct feature descriptors that incorporate the subject’s age and gender, as well as features based on eye gaze data.

Paper Details

Authors:
Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin
Submitted On:
19 September 2017 - 8:23pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Combining Gaze and Demographic Feature Desciptors for Autism Classification

(28 downloads)

Keywords

Subscribe

[1] Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin, "Combining Gaze and Demographic Feature Desciptors for Autism Classification", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2235. Accessed: Dec. 15, 2017.
@article{2235-17,
url = {http://sigport.org/2235},
author = {Shaun Canavan; Melanie Chen; Song Chen; Robert Valdez; Miles Yaeger; Huiyi Lin; Lijun Yin },
publisher = {IEEE SigPort},
title = {Combining Gaze and Demographic Feature Desciptors for Autism Classification},
year = {2017} }
TY - EJOUR
T1 - Combining Gaze and Demographic Feature Desciptors for Autism Classification
AU - Shaun Canavan; Melanie Chen; Song Chen; Robert Valdez; Miles Yaeger; Huiyi Lin; Lijun Yin
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2235
ER -
Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin. (2017). Combining Gaze and Demographic Feature Desciptors for Autism Classification. IEEE SigPort. http://sigport.org/2235
Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin, 2017. Combining Gaze and Demographic Feature Desciptors for Autism Classification. Available at: http://sigport.org/2235.
Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin. (2017). "Combining Gaze and Demographic Feature Desciptors for Autism Classification." Web.
1. Shaun Canavan, Melanie Chen, Song Chen, Robert Valdez, Miles Yaeger, Huiyi Lin, Lijun Yin. Combining Gaze and Demographic Feature Desciptors for Autism Classification [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2235

Presentation Slides for paper #3118


Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the problem of vanishing or exploding gradients. They achieve this by setting the eigenvalues of the temporal Jacobian to 1 across the time steps. In this work, batch normalized recurrent highway networks are proposed to control the gradient flow in an improved way for network convergence. Specifically, the introduced model can be formed by batch normalizing the inputs at each recurrence loop.

Paper Details

Authors:
Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio
Submitted On:
19 September 2017 - 1:59am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_presentation.pdf

(29 downloads)

Keywords

Subscribe

[1] Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio, "Presentation Slides for paper #3118", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2233. Accessed: Dec. 15, 2017.
@article{2233-17,
url = {http://sigport.org/2233},
author = {Chi Zhang; Thang Nguyen; Shagan Sah; Raymond Ptucha; Alexander Loui; Carl Salvaggio },
publisher = {IEEE SigPort},
title = {Presentation Slides for paper #3118},
year = {2017} }
TY - EJOUR
T1 - Presentation Slides for paper #3118
AU - Chi Zhang; Thang Nguyen; Shagan Sah; Raymond Ptucha; Alexander Loui; Carl Salvaggio
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2233
ER -
Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio. (2017). Presentation Slides for paper #3118. IEEE SigPort. http://sigport.org/2233
Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio, 2017. Presentation Slides for paper #3118. Available at: http://sigport.org/2233.
Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio. (2017). "Presentation Slides for paper #3118." Web.
1. Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio. Presentation Slides for paper #3118 [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2233

Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising

Paper Details

Authors:
Submitted On:
29 November 2017 - 8:09pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

未命名-2.pdf

(0)

presentationicip2017.pdf

(6 downloads)

Keywords

Subscribe

[1] , "Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2230. Accessed: Dec. 15, 2017.
@article{2230-17,
url = {http://sigport.org/2230},
author = { },
publisher = {IEEE SigPort},
title = {Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising},
year = {2017} }
TY - EJOUR
T1 - Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2230
ER -
. (2017). Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising. IEEE SigPort. http://sigport.org/2230
, 2017. Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising. Available at: http://sigport.org/2230.
. (2017). "Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising." Web.
1. . Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2230

Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising

Paper Details

Authors:
Submitted On:
18 September 2017 - 8:48pm
Short Link:
Type:
Event:
Paper Code:

Document Files

未命名-2.pdf

(0)

Keywords

Subscribe

[1] , "Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2229. Accessed: Dec. 15, 2017.
@article{2229-17,
url = {http://sigport.org/2229},
author = { },
publisher = {IEEE SigPort},
title = {Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising},
year = {2017} }
TY - EJOUR
T1 - Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2229
ER -
. (2017). Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising. IEEE SigPort. http://sigport.org/2229
, 2017. Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising. Available at: http://sigport.org/2229.
. (2017). "Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising." Web.
1. . Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2229

MVIRT - A Toolbox for manifold-value image restoration


In many real life application measured data takes its values on Riemannian manifolds. For the special case of the Euclidean space this setting includes the classical grayscale and color images. Like these classical images, manifold-valued data might suffer from measurement errors in form of noise or missing data. In this paper we present the manifold-valued image restoration toolbox (MVIRT) that provides implementations of classical image processing tasks.

Paper Details

Authors:
Submitted On:
18 September 2017 - 6:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP-MVIRT-sigport-web.pdf

(33 downloads)

Keywords

Subscribe

[1] , "MVIRT - A Toolbox for manifold-value image restoration", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2225. Accessed: Dec. 15, 2017.
@article{2225-17,
url = {http://sigport.org/2225},
author = { },
publisher = {IEEE SigPort},
title = {MVIRT - A Toolbox for manifold-value image restoration},
year = {2017} }
TY - EJOUR
T1 - MVIRT - A Toolbox for manifold-value image restoration
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2225
ER -
. (2017). MVIRT - A Toolbox for manifold-value image restoration. IEEE SigPort. http://sigport.org/2225
, 2017. MVIRT - A Toolbox for manifold-value image restoration. Available at: http://sigport.org/2225.
. (2017). "MVIRT - A Toolbox for manifold-value image restoration." Web.
1. . MVIRT - A Toolbox for manifold-value image restoration [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2225

Image Quality Assessment to Enhance Infrared Face Recognition


Automatic quality evaluation of infrared images has not been researched as extensively as for images of the visible spectrum. Moreover, there is a lack of studies on the influence of degradation of image quality on the performance of computer vision tasks operating on thermal images. Here, we quantify the impact of common image distortions on infrared face recognition, and present a method for aggregating perceptual quality-aware features to improve the identification rates.

Paper Details

Authors:
Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik
Submitted On:
18 September 2017 - 8:55am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2017 Presentation Slides

(36 downloads)

Keywords

Additional Categories

Subscribe

[1] Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik, "Image Quality Assessment to Enhance Infrared Face Recognition", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2223. Accessed: Dec. 15, 2017.
@article{2223-17,
url = {http://sigport.org/2223},
author = {Camilo G. Rodríguez Pulecio; Hernan D. Benítez-Restrepo; Alan C. Bovik },
publisher = {IEEE SigPort},
title = {Image Quality Assessment to Enhance Infrared Face Recognition},
year = {2017} }
TY - EJOUR
T1 - Image Quality Assessment to Enhance Infrared Face Recognition
AU - Camilo G. Rodríguez Pulecio; Hernan D. Benítez-Restrepo; Alan C. Bovik
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2223
ER -
Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik. (2017). Image Quality Assessment to Enhance Infrared Face Recognition. IEEE SigPort. http://sigport.org/2223
Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik, 2017. Image Quality Assessment to Enhance Infrared Face Recognition. Available at: http://sigport.org/2223.
Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik. (2017). "Image Quality Assessment to Enhance Infrared Face Recognition." Web.
1. Camilo G. Rodríguez Pulecio, Hernan D. Benítez-Restrepo, Alan C. Bovik. Image Quality Assessment to Enhance Infrared Face Recognition [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2223

Pages