Ongoing Projects | In this project, we try to answer the question "where was a photo taken?". In particular, we are interested in 1) localizing a ground-level image with an aerial imagery gallery by cross-view image matching and 2) designing a human-in-the-loop system to learn and match the geographically meaningful v... |  | Automatic evaluation of human facial attractiveness is a challenging problem that has received little attention from the computer vision community. Here, we approach beauty from a relative ranking perspective. Our training data are faces sorted based on a individuals's personal preference, which we ... |  | Face recognition approaches have traditionally focused on direct
comparisons between aligned images, e.g using pixel values or local
image features. Such comparisons become prohibitively difficult
when comparing faces across extreme differences in pose,
illumination and expression.
We prop... |  | We design and implement a comprehensive study of the perception of gloss. This is the largest study of its kind to date, and the first to use real material measurements. In addition, we develop a novel Multi-Dimensional Scaling (MDS) algorithm for analyzing pairwise comparisons. The data from the p... |  | GrOCR is an ongoing research project for word recognition in unconstrained images. The name is derived from the original impetus of the project, OCR for reading text on products found in grocery stores. While the focus of the project has moved beyond just that domain, the name has remained the same. |  | Visipedia is a joint project between Pietro Perona's Vision Group at Caltech and Serge Belongie's Vision Group at UCSD. Visipedia, short for "Visual Encyclopedia," is an augmented version of Wikipedia, where pictures are first-class citizens alongside text. Goals of Visipedia include creation of h... |  | Across the world, coral reefs, with their delicate ecological balance, are suffering from the effects of climate change and pollution. In order to influence decisions makes to take action, accurate large scale monitoring systems need to be in place.
With the proliferation of digital cameras and a... |  | Face recognition is an important problem in computer vision with applications ranging from
surveillance to robotics to the organization of personal image collections. In this work we focus on unconstrained face recognition in videos. The setup consists of a set of gallery videos (or images) for eac... |  | The ground truth labeling of an image dataset is a task that often requires a large amount of human time and labor. We present an infrastructure for distributed human labeling that can exploit the modularity of common vision problems involving segmentation and recognition. We present the different e... |  | |  | In this line of work, we persent globally optimal solutions to several important problems in multiview geometry. Structure from motion problems are inherently non-convex and these works rely on efficient construction of relaxations using developments in convex optimization and algebraic geometry. |  | The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images present occlusion, poor quality, noise or background clutter, and this task becomes even more challenging when many objects are pres... |  | The contemporary urban environment is brimming with rich visual cues that provide valuable directional and informational content to sighted individuals. The goal of the GroZi project is to make significant advances toward making these visual cues universally accessible in a variety of real-world do... |
2011 | When fingers wrinkle in water, they become harder to recognize as similar
to a dry finger, based on fingerprint scans. Vision lab has taken this
problem forward by introducing the WWF(Wet and Wrinkled Finger) dataset
and baseline performances on a NBIS matcher and a commercial algorithm. We
have... |  | In this project we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called ``tracking by detection'' has been shown to give promising results at real-time speeds. These methods train a disc... |
2010 | Smoke detectors and heat detectors currently provide the first line of defense against catastrophic structure fires. However, these technologies are ineffective in large open spaces such as tunnels, lobbies, arenas, and in the outdoors. On the other hand, a video based fire detection system has no... |
2009 | Similarity metrics that are learned from labeled training
data can be advantageous in terms of performance
and/or efficiency. These learned metrics can then be used
in conjunction with a nearest neighbor classifier, or can be
plugged in as kernels to an SVM. For the task of categorization
two s... |  | |
2008 | Multiple Instance Learning (MIL) provides a framework for
training a discriminative classifier from data with ambiguous labels. This
framework is well suited for the task of learning object classifiers from
weakly labeled image data, where only the presence of an object in an
image is known,... |  | LSML is a method for determining a warping from a point on a manifold to its neighbors on the manifold. A direct application of this method is performed on video sequences where the ways of moving on the underlying manifold are learned and then used to move within and out of the training set. The wa... |  | This project focuses on visual learning with ambiguity. In particular, we have applied and extended the Multiple Instance Learning (MIL) paradigm to challenging computer vision problems. We propose two novel learning frameworks: Multiple Component Learning (MCL) for part-based object detection, and ... |
2007 | In this project we trained a distance function for local region matching. We show that when the application is relatively constrained, using a supervised learning approach produces better results than a generic system that was tuned by hand. |  | |  | |  | |
2006 | |  | |  | |  | |  | Smart Vivarium: automated monitoring of animal health and welfare. |  | We consider the problem of clustering in domains where the affinity relations are not dyadic (pairwise), but rather triadic, tetradic or higher. The problem is an instance of the hypergraph partitioning problem. We propose a two-step algorithm for solving this problem. In the first step we use a nov... |
2005 | |  | In this paper we present a completely automated algorithm for estimating the parameters of the contrast transfer function (CTF) of a transmission electron microscope. The primary contribution of this paper is the determination of the astigmatism prior to the estimation of the CTF parameters. The CT... |  | We present a photometric stereo method for non-diffuse materials that does not require an explicit reflectance model or reference object. By computing a data-dependent rotation of RGB color space, we show that the specular reflection effects can be separated from the much simpler, diffuse (approxima... |  | Computer icons are small artificial images designed to be perceived with minimal ambiguity by the human visual system. In order to make them easier to perceive by visually impaired people, we propose a solution to the super-resolution problem for color bitmap icons in a manner that exploits the uni... |  | Vehicle license plate and make and model recognition. |  | A method for detecting and segmenting periodic motion is presented. We exploit periodicity as a cue and detect periodic motion in complex scenes where common methods for motion segmentation are likely to fail. We note that periodic motion detection can be seen as an approximate case of sequence alig... |  | Matching with Shape Contexts and Thin-Plate Splines. |
2004 | A new learning-based approach is presented for particle detection in cryo-electron micrographs using the Adaboost learning algorithm. The approach builds directly on the successful detectors developed for the domain of face detection. It is a discriminative algorithm which learns important features... |  | |  | This paper presents a novel generalization of the optical flow equation to the case of refraction, and it describes a method for recovering the refractive structure of an object from a video sequence acquired as the background behind the refracting object moves. By structure here we mean a represen... |  | |
2003 | We introduce structured importance sampling, a new technique for efficiently rendering scenes illuminated by distant natural illumination given in an environment map. Our method handles occlusion, high-frequency lighting, and is significantly faster than alternative methods based on Monte Carlo samp... |  | The objective of mobile camera server (MCS)is providing a mechanism to access the (USB) camera from a remote computer. The application was primary developed to remotely request images from ER1 robot's camera. It was then extended to support multiple camera as well as AVI files, makes it more flexibl... |
2002 | Recent interest in region based image coding has given rise to graph coloring based partition encoding methods. These methods are based on the four color theorem for planar graphs, and assume that a coloring for a graph with the minimum possible number of colors will result in the most compressible ... |  | Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of such methods, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of th... |
Check out a sampling of the Undergraduate Research Projects from our lab.
|
