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.
■ 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.
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.
■ 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.
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.
■ 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)
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.
■ 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)
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,
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.
■ 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.
The part of the electromagnetic spectrum (0.1-10THz) between microwaves and far infrared refers to Terahertz radiation. Terahertz beams easily penetrate dielectric substances such as paper, plastics and ceramics, which are opaque at optical frequencies and provide very low contrast for X-rays. These materials are relatively non-absorbing in this frequency range, yet different materials may be easily discriminated on the basis of their refractive index, which is extracted from the THz phase information. Unlike X-rays, Terahertz beams can be focused and are capable of producing phase-sensitive spectroscopic images with signature capability. The spectral information of the transmitted and/or scattered radiation could be used to detect hazardous chemicals, threat objects in luggage or concealed weapons, and defects in semiconductor wafers and packages. Low photon energy level of Terahertz spectrum is particularly attractive for the imaging of biological tissues with no harmful ionizing radiation. THz source can be used for high-resolution remote subsurface imaging, with spatial and depth resolution better than 1 mm, enabling differentiation of skin or breast cancers from normal tissues and tooth cavities. This research covers enhancement of THz waveforms and denoising, spectral signal classification, high-resolution image reconstruction based on the fusion of peak intensity and phase information, and segmentation techniques for the visualization and classification of terahertz images.
■ 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.
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.
■ 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.