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

Face recognition systems are designed to handle well-aligned images captured under controlled situations. However real-world images present varying orientations, expressions, and illumination conditions. Traditional face recognition algorithms perform poorly on such images. In this paper we present a method for face recognition adapted to real-world conditions that can be trained using very few training examples and is computationally efficient. Our method consists of performing a novel alignment process followed by classification using sparse representation techniques.

This paper proposes a novel inverse TMO, which enables to generate
HDR images from LDR ones,
not only without using any specific parameters but also at low
computing costs.
Furthermore, the inverse TMO has a new characteristic when an
LDR image is mapped from an HDR one by Reinhard's global operator.
In the case, the HDR image reconstructed by the proposed method
without parameters can be remapped into the same image as
that remapped from an HDR one reconstructed with parameters.

Detecting spot-like objects of different sizes in images is needed in many applications. Multiple image scales must then be handled for reliable spot segmentation.
We define an original criterion based on the a contrario approach and the LoG scale-space framework to automatically select the meaningful scales.
We then design a coarse-to-fine multi-scale spot segmentation scheme involving
a locally adaptive thresholding across scales, to come up with the final map of segmented spots.

In this paper, we solve blind image deconvolution problem that is to remove blurs form a signal degraded image without any knowledge of the blur kernel. Since the problem is ill-posed, an image prior plays a significant role in accurate blind deconvolution. Traditional image prior assumes coefficients in filtered domains are sparse. However, it is assumed here that there exist additional structures over the sparse coefficients. Accordingly, we propose new problem formulation for the blind image deconvolution, which utilize the structural

We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing tech- niques. Gesture features are extracted directly from the compressed measurements, which are the block averages and the coded linear combinations of the image sensor’s pixel values. We also improve both the computational efficiency and the memory requirement of the previous DTW-based K-NN gesture classifiers. Both simulation testing and hardware implementation strongly support the proposed algorithm.

Contextual information such as the co-occurrence of objects and the location of objects has played an important role in object detec- tion. We present candidate pruning and object rescoring methods that leverage contextual information and that can improve the state- of-the-art CNN-based object detection methods such as Fast R-CNN and Faster R-CNN. In our pruning method, we formulate candidate reduction as a Markov random field optimization problem. In our rescoring method, we employ a machine learning technique to recon- sider the detection scores of candidate windows.

We propose a full reference stereo video quality assessment
algorithm for assessing the perceptual quality of natural stereo
videos. We exploit the separable representation of motion
and binocular disparity in the visual cortex and develop a
four stage algorithm to measure the quality of a stereoscopic
video called FLOSIM3D. First, we compute the temporal features
by utilizing an existing 2D VQA metric which measures
the temporal annoyance based on patch level statistics such
as mean, variance and minimum eigen value and pools them

We propose a real-time plane detection method for projection-based Augmented Reality (AR) system in an unknown environment. While previous works usually designate space, the plane detection method automatically detects multiple planes based on the proposed constrained sampling strategy in RAndom SAmpleing Concensus (RANSAC). For each plane, an area for projection is selected for contents while considering occlusions by other objects.