■ Gaze
Estimation and Tracking
■ 3-D
Modeling of Human Face from 2-D Images
■ Multimodal Face
Recognition with Visible and Infrared Imaging
■ Hyperspectral
Image Analysis for Medical Diagnosis and Target Detection
■ Forensic Imaging and
Analysis
■ Signal Restoration in
Terahertz Imaging and Spectroscopy
■ Evolvable Block-based
Neural Networks for ECG Signal Monitoring
This work estimates the gaze point of a person using the pupil center and head pose angles for human-computer interaction. Gaze estimation refers to determining where a person is looking on the computer monitor screen through visual analysis of the human face in a video taken from a camera mounted on the monitor. Applications of gaze estimation include hands-free control of the mouse cursor, human-computer interaction in video gaming, estimating the preferences of consumers on a certain product in marketing survey, monitoring the alertness level of a vehicle driver, and diagnosis of a patient with a psychological disorder having difficulty to effectively communicate. Many existing gaze estimation approaches require active illumination devices such as infrared (IR) LEDs, which can limit operating distance of the gaze tracker and prevent from working in outdoor environments. The proposed method combines the pupil center and head pose angles to determine the gaze point in real time with an off-the-shelf camera with no IR illuminators. The pupil centers are detected in every frame from a face object in a live video stream. Head pose angles are estimated by matching the users detected facial features to those projected onto a generic 3-D head model. The gaze point is expressed as a linear combination of the pupil center and head pose angles, which can be solved by a linear regression model.
Related
Publications:
■
R.
Oyini Mbouna, S. G. Kong,
and M. G. Chun, Visual Analysis of
Eye State and Head Pose for Driver Alertness Monitoring, IEEE Transactions on Intelligent
Transportation Systems, Vol. 14, No. 3, pp.1462-1469, September 2013.
■
R. Oyini Mbouna and S. G. Kong, Pupil Center Detection with a
Single Webcam for Gaze Tracking, Journal of Measurement Science and
Instrumentation, Vol. 3, No. 2, pp.133-136, June 2012.
■ I. S. Kim, H. S.
Choi, K. M. Yi, J. Y. Choi, and S. G. Kong, Intelligent Visual Surveillance A Survey, International Journal of Control,
Automation, and Systems, Vol. 8, No. 5, pp.926-939, October 2010.
3-D Modeling of Human Face from 2-D Images
Since a human face is
essentially a 3-D object, changes in head pose along with illumination
variations decrease the performance of face recognition significantly. The use
a 3-D model of a human face has promised robust face recognition invariant to
pose and lighting. The 3-D structure of a persons facial surface does not
change over time. This research estimates head pose angles and 3-D depth
information from a 2-D query face image using a reference 3-D face model of the
same gender and ethnicity as those of a query image. The depth information is
obtained by minimizing the disparity between a set of facial feature points on
2-D face and the 2-D projection of corresponding feature points on the 3-D
reference face model. The resulting 3-D face model is compared with a ground-truth
3-D face model canned using a Kinect sensor. The 3-D objects obtained are
printed using a 3-D printer to confirm the accuracy of 3-D shape.
Related
Publications:
■
R.
Oyini Mbouna and S. G.
Kong, Head pose estimation from a 2-D Face Image using a morphed 3-D head
model with minimum feature disparity, In
Preparation, 2014.
■
Multimodal Face
Recognition with Visible and Infrared Imaging
This work finds an adaptive data fusion technique of visible and thermal infrared (IR) images for robust face recognition regardless of illumination variations, partially supported by the Office of Naval Research. The combined use of visible and thermal IR image sensors offers a viable means for improving the performance of face recognition techniques based on single imaging modalities. Visual imaging demonstrates difficulty in recognizing the faces in low illumination conditions. Thermal IR sensor measures energy radiation from the object, which is less sensitive to illumination changes and operable in darkness. Data fusion of visible and thermal images can reproduce face images robust to illumination variations. However, thermal face images with eyeglasses may fail to provide useful information around the eyes since glass blocks a large portion of thermal energy. Adaptive data fusion detects the presence of eyeglasses to enhance the quality of visual-thermal image fusion in terms of information content for robust face recognition.
Related
Publications:
■ I. S. Kim, H. S.
Choi, K. M. Yi, J. Y. Choi, and S. G. Kong, Intelligent Visual Surveillance A Survey,
International Journal of Control,
Automation, and Systems, Vol. 8, No. 5, pp.926-939, October 2010.
■ S. G. Kong, J. Heo, F. Boughorbel, Y. Zheng, B. R. Abidi, A. Koschan, M. Yi, and M. A. Abidi, Multi-scale Fusion of Visible and Thermal IR Images for Illumination-Invariant Face Recognition, International Journal of Computer Vision, Vol. 71, No. 2, pp.215-233, Feb. 2007.
■ S. Moon and S. G. Kong, Adaptive
Fusion of Visible and Thermal Images based on Multiscale
Analysis for Face Recognition, Proc. IEEE Intl Conf. on Computational
Intelligence for Homeland Security and Personal Safety (CIHSPS06),
Alexandria, VA, Oct. 2006.
■ S. G. Kong, J. Heo,
B. R. Abidi, J. Paik, and M. A. Abidi, Recent Advances in Visual and
Infrared Face Recognition - A Review, Computer Vision and Image
Understanding, Vol. 97, No. 1, pp.103-135, January 2005. (Most Cited Paper Award)
■ J. Heo, S. G. Kong, B. Abidi, and M. Abidi, Fusion of
Visual and Thermal Signatures with Eyeglass Removal for Robust Face Recognition,
Proc. Workshop on Object Tracking and Classification Beyond the Visible
Spectrum (OTCBVS04), Washington, DC, July 2004. (Best Paper Award)
Hyperspectral Image
Analysis for Medical Diagnosis and Target Detection
This research aims
at developing hyperspectral imaging and signature
classification techniques for real-time, non-invasive diagnosis of skin
cancers. The application focus involves the study and correlation of
reflectance/fluorescence image signals with neoplastic properties of normal and
tumor tissues. A technical innovation of this project is the combination of an
advanced computing algorithm based on the support vector machine with a
real-time hyperspectral imaging system for detecting
small differences in reflectance and fluorescence profiles of normal and
malignant tumor tissues. This approach leads to significant advances in
effective and rapid detection of tumors over large areas of organs and in the
understanding of cancer in general. The developed skin cancer detection
technique will be translatable to other diseases in other organ sites as well
changing the future of diagnostic medicine. Early phase of this research has
been successfully applied to the detection of skin tumors on poultry carcasses
for food safety inspection.
Related
Publications:
■
Y.
Zhao, X. Wu, S. G. Kong, and L. Zhang, Joint
Segmentation and Pairing of Multispectral Chromosome Images, Pattern Analysis and Applications, Vol.
16, Issue 4, pp.497-506, November 2013.
■
Y.
Zhao and S. G. Kong, Automated
Classification of Touching or Overlapping M-FISH Chromosomes by Region Fusion
and Homolog Pairing, Pattern
Analysis and Applications, Vol. 16, Issue 1, pp.31-39, February 2013.
■ Z. Du, Y. Jeong, M. K. Jeong, and S. G.
Kong, Multidimensional Local Spatial
Autocorrelation Measure for Integrating Spatial and Spectral Information in Hyperspectral Image Band Selection, Applied Intelligence, Vol. 36, Issue 3,
pp.542-552, April 2012.
■ Y. Zhao, L. Zhang,
and S. G. Kong, Band Subset Based
Clustering and Fusion for Hyperspectral Imagery
Classification, IEEE Transactions on
Geoscience and Remote Sensing, Vol. 49, No. 2, pp.747-756, February 2011.
■
Z.
Du, M. K. Jeong, and S. G. Kong, Band Selection of Hyperspectral
Images for Automatic Detection of Poultry Skin Tumors, IEEE
Transactions on Automation Science and Engineering, Vol. 4, No. 3,
pp.332-339, 2007.
■
S.
G. Kong, M. Martin, and T. Vo-Dinh, Hyper-spectral Fluorescence Imaging for
Mouse Skin Tumor Detection, ETRI Journal, Vol. 28, No. 6,
pp.770-776, December 2006
■
S.
G. Kong, Z. Du, M. Martin, and T. Vo-Dinh, Hyper-spectral Fluorescence Image Analysis
for Use in Medical Analysis, Proc. of SPIE Conf. on Biomedical Optics,
San Jose, CA, 2005.
■
I.
Kim, Y. R. Chen, M. S. Kim, and S. G. Kong, Detection of Skin Tumors on Chicken
Carcasses using Hyperspectral Fluorescence Imaging,
Transactions of the American Society of Agricultural Engineers, Vol. 47,
No. 5, pp.1785-1792, 2004. (Honorable Mention Paper Award)
■
S.
G. Kong, Y. R. Chen, I. Kim, and M. S. Kim, Analysis of
Hyperspectral Fluorescence Images for Poultry Skin
Tumor Inspection, Applied Optics, Vol. 43, No. 4, pp.824-833,
February 2004.
Forensic imaging provides investigative images, photographic processing,
and visual analysis to find evidences for investigation by law enforcement
agencies. Research focuses are imaging techniques in challenging environments,
enhancement, restoration from degraded images, video
analysis, authentication, evaluation, and latent fingerprint examination.
Forged seal detection finds a computational procedure to verify the
authenticity of a seal impression imprinted on a document based on the seal
overlay metric, which is defined as the ratio of
an effective seal impression pattern and the noise in the neighborhood of the
reference seal impression region. Detection of transcribed seal impressions use
a 3-D scanner to generate a 3-D pressure trace map to detect forged seal
impressions transferred from a genuine document to a target document using
transcription media. Sequence discrimination of heterogeneous crossing of seal
impressions discriminates the sequence of stamped seal impressions and
ink-printed text in a document to detect falsely signed documents. Invisible
ink detection reveals invisible ink patterns in the visible spectrum without
the aid of special equipment such as UV lighting or IR filters using absorption
difference. Frame-based recovery of corrupted video files hep recover corrupted
video frames based on video frames.
Related
Publications:
■
J.
Lee, S. G. Kong, T. Y. Kang, and B. Kim, Invisible
Ink Mark Detection in the Visible Spectrum using Absorption Difference, Forensic Science International, Vol.
236, pp.77-83, March 2014.
■
M.
G. Chun and S. G. Kong, Focusing in
Thermal Imagery using Morphological Gradient Operator, Pattern Recognition Letters, Vol. 38,
Issue 4, pp.20-25, March 2014.
■
G.
Na, K. Shim, G. Moon, S. G. Kong, E. Kim, and J. Lee, Frame-based Recovery of Corrupted Video Files
using Video Codec Specifications, IEEE
Transactions on Image Processing, Vol. 23, No. 2, pp.517-526, February
2014.
■ K. Y. Lee, J. Lee,
S. G. Kong, and B. Kim, Sequence
Discrimination of Heterogeneous Crossing of Seal Impression and Ink-printed
Text using Adhesive Tapes, Forensic
Science International, Vol. 234, pp.120-125, January 2014.
■
J.
Lee, S. G. Kong, Y. Lee, J. Kim, and N. Jung, Detection of Transcribed Seal Impressions
using 3-D Pressure Traces, Journal
of Forensic Sciences, Vol. 57, Issue 6, pp.1531-1536, November 2012.
■ J. Lee, S. G. Kong, Y. Lee, K. Moon, O. Jeon,
J. H. Han, B. Lee, and J. Seo, Forged Seal Detection based on Seal Overlay
Metric, Forensic Science
International, Vol. 214, Issue 1, pp.200-206, January 2012.
■ C. Ryu, S. G. Kong, and H. Kim, Enhancement of Feature Extraction for
Low-Quality Fingerprint Images using Stochastic Resonance, Pattern Recognition Letters, Vol. 32,
Issue 2, pp.107-113, January 2011.
Signal Restoration in Terahertz Imaging and
Spectroscopy
Related
Publications:
■ C. Ryu and S. G. Kong, Boosting Terahertz Radiation in THz-TDS using Continuous-Wave Laser, Electronics Letters, Vol.
46, No. 5, pp.359-360, March 4, 2010.
■ C. Ryu and S. G. Kong, Atmospheric Degradation Correction of Terahertz Beams using Multiscale Signal Restoration, Applied Optics, Vol. 49, No.
5, pp.927-935, February 2010.
■ S. G. Kong and D. H. Wu, "Signal Restoration from Atmospheric Degradation in Terahertz
Spectroscopy," Journal of
Applied Physics, Vol. 103, No. 11, 113105 (6 pages), June 2008.
■ S. G. Kong and D.
H. Wu, Terahertz Time-Domain Spectroscopy
for Explosive Trace Detection, Proc. IEEE Intl Conf. on
Computational Intelligence for Homeland Security and Personal Safety
(CIHSPS06), Alexandria, VA, Oct. 2006.
Evolvable Block-based
Neural Networks for ECG Signal Monitoring
This work aims at
developing evolvable neural networks that reconfigure their structures and
connection weights autonomously in dynamic operating environments. The
block-based neural network model consist of a 2-D array of basic blocks that
can modify network structure and connection weights using evolutionary
algorithms to be implemented on reconfigurable digital hardware. Block-based
neural networks demonstrated the potential for analyzing electrocardiogram
(ECG) signals to monitor human health conditions online that are insensitive to
variations over individuals, time of day, and under different body conditions.
People working in dangerous environments (e.g. military personnel, firemen, and
truck drivers) as well as older people will benefit from constant monitoring of
their health conditions for prediction of various dangerous states such as
detection of losing consciousness and heart infarct.
Related
Publications:
■ W. Jiang and S. G. Kong, Block-based Neural Networks for Personalized ECG Signal Classification, IEEE Transactions on Neural Networks, Vol. 18, No. 6,
pp.1750-1761, November 2007.
■ W. Jiang and S. G. Kong, A
Least-Squares Learning for Block-based Neural Networks, Dynamics
of Continuous, Discrete and Impulsive Systems, Vol. 14, No. S1, pp.242-247,
2007.
■ S. Merchant, G. D. Peterson, S. Park, and S. G.
Kong, FPGA Implementation of Evolvable Block-based Neural Networks, Proc. Congress on Evolutionary Computation,
Vancouver, July 2006.
■ W. Jiang, S. G. Kong, and G. Peterson, ECG
Signal Classification using Block-based Neural Networks, Proc. International Joint Conf. on Neural
Networks, Montreal, Canada, 2005.
■ S. W. Moon and S.
G. Kong, Block-based Neural Networks, IEEE
Transactions on Neural Networks, Vol. 12, No. 2, pp.307-317, March 2001.