ABSTRACT
Research Interests:
Research Interests: Cognitive Science, Algorithms, Computer Graphics, Face Recognition, Statistical Analysis, and 22 moreFace, Facial expression, Multivariate Analysis, Factor analysis, Humans, Wavelet Transforms, Female, Male, Facial Features, Feature Extraction, Structure Analysis, Facial Landmarking, High resolution satelite image, Mixture Model, Reproducibility of Results, Sensitivity and Specificity, Biometric Identification, Facial Expression Recognition, Electrical And Electronic Engineering, Low Resolution, Video Recording, and Gabor Wavelets
Research Interests:
ABSTRACT
Research Interests:
Research Interests: Psychophysics, Algorithms, Computer Vision, Visual perception, Machine Vision, and 18 moreColor Perception, Color Constancy, Humans, Color, Female, Lighting, Male, Color Vision, Distance Perception, Young Adult, Human Vision, Optical physics, Optometry and Ophthalmology, Observer Variation, Adult, Electrical And Electronic Engineering, Performance Measure, and Image Generation
Research Interests:
Research Interests: Computer Vision, Image Processing, Pattern Recognition, Modeling, Imaging, and 20 moreTemporal Data Mining, Temporal Databases, Image segmentation, Learning, Negative Affect, Photometry, Object Recognition, Classification, Skin, Image recognition, Redundancy, Invariance, Visual Cues, Repeatability, Invariant, Reflectance, Color Models, Object Detection, Parameter Tuning, and Data Uncertainty
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Psychophysics, Algorithms, Computer Vision, Visual perception, Machine Vision, and 18 moreColor Perception, Color Constancy, Humans, Color, Female, Lighting, Male, Color Vision, Distance Perception, Young Adult, Human Vision, Optical physics, Optometry and Ophthalmology, Observer Variation, Adult, Electrical And Electronic Engineering, Performance Measure, and Image Generation
Research Interests:
In this paper, indexing is used as a common framework to represent, index and retrieve images on the basis of color and shape invariants. To evaluate the use of color and shape invariants for the purpose of image retrieval, experiments... more
In this paper, indexing is used as a common framework to represent, index and retrieve images on the basis of color and shape invariants. To evaluate the use of color and shape invariants for the purpose of image retrieval, experiments have been conducted on a database consisting of 500 images of multicolored objects. Images in the database show a considerable amount of noise, specularities, occlusion and fragmentation resulting in a good representation of views from everyday life as it appears in home video and consumer photography in general. The experimental results show that image retrieval based on both color and shape invariants provides excellent retrieval accuracy. Image retrieval based on shape invariants yields poor discriminative power and worst computational performance whereas color based invariants image retrieval provides high discrimination power and best computational performance. Furthermore, the experimental results reveal that identifying multicolored objects entirely on the basis of color invariants is to a large degree robust to partial occlusion and a change in viewing position.
Research Interests:
Research Interests:
Research Interests:
Color histograms computed from the normalized and hue color space are negatively affected by sensor noise due to the instability of these color space transforms at many RGB values. To suppress the effect of sensor noise, in this paper... more
Color histograms computed from the normalized and hue color space are negatively affected by sensor noise due to the instability of these color space transforms at many RGB values. To suppress the effect of sensor noise, in this paper density estimations are computed using variable kernels. To that end, models are proposed for the propagation of sensor noise through the
Research Interests:
Research Interests:
... Overview. Top Sellers in this Category. Apple Pro Training Series: Final Cut Pro 7 by Diana Weynand. YouTube® and Video Marketing: An Hour a Day by Greg Jarboe; Suzie Reider. Adobe® Premiere® Pro CS4 Classroom in a Book® by Adobe... more
... Overview. Top Sellers in this Category. Apple Pro Training Series: Final Cut Pro 7 by Diana Weynand. YouTube® and Video Marketing: An Hour a Day by Greg Jarboe; Suzie Reider. Adobe® Premiere® Pro CS4 Classroom in a Book® by Adobe Creative Team. ...
Research Interests:
Research Interests:
Research Interests:
In this paper we present a system for the localisation and tracking of billboards in streamed soccer matches. The application area for this research is the delivery of customised content to end users. When international soccer matches are... more
In this paper we present a system for the localisation and tracking of billboards in streamed soccer matches. The application area for this research is the delivery of customised content to end users. When international soccer matches are broadcast, the diversity of the audience is ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This book constitutes the refereed proceedings of the First International Workshop on Human Behavior Understanding, HBU 2010, a satellite workshop of the International Conference on Pattern Recognition in Istanbul, Turkey, on August 22,... more
This book constitutes the refereed proceedings of the First International Workshop on Human Behavior Understanding, HBU 2010, a satellite workshop of the International Conference on Pattern Recognition in Istanbul, Turkey, on August 22, 2010. The 13 revised full papers presented were carefully reviewed and selected from 29 submissions. The papers are organized in topical sections on analysis of human activities; non-verbal action dynamics; visual action recognition; and social signals.
Research Interests:
Research Interests:
Experiments on the PASCAL VOC07 and VOC10 datasets show that the proposed method significantly outperforms single object detectors, DPM (8.4%), CN (6.8%) and EES (17.0%) on VOC07 and DPM (6.5%), CN (5.5%) and EES (16.2%) on VOC10.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
... The invari-ant image can be obtained as follows: ... while the error denotes the ratio of misclassified patches when a test patch is classified using maximum posterior ... In this paper, shadow edgedetection is performed on a data set... more
... The invari-ant image can be obtained as follows: ... while the error denotes the ratio of misclassified patches when a test patch is classified using maximum posterior ... In this paper, shadow edgedetection is performed on a data set containing manually annotated shadow and non ...