Summer 2009 Research Fellowships

UCSB Center for Bio-Image Informatics is currently offering fellowships to qualified undergraduate students for a summer research program in Biology and Information Technology. The newly established Center for Bioimage Informatics is supported by the National Science Foundation and its mission is to establish a searchable digital library for bio-molecular images and to develop new information processing technologies for a better understanding of complex biological processes at the cellular and molecular level.

The summer scholars will interact with researchers and faculty involved in this project as well as participate in various activities designed to develop the skills necessary for success at the graduate level.                                                                                                                

This is an 8 week program running from June 23th through August 14th, 2009.

The application process is now closed.

High School Students:

Four high school students are participating in the program as a part of Apprentice Researchers (AR) program.

Undergraduate Students:

Four undergraduate students are also participating in the program.

Project descriptions:

1)  Brian Ruttenberg/Cari : Cari is assisting Brian Ruttenberg with the prediction and modeling of the cytoplasm of retinal Astrocytes. Astrocytes are a glial cell in the retina, and visualizing the complete morphology of the cell is a difficult and cumbersome process. Cari is helping to develop and test a neighborhood classification scheme to predict the extent of Astrocyte cytoplasm from GFAP labeled cells, in order that Astrocyte interaction can be modeled on a large scale.  Cari will quantify and present the results on a series of hand injected ground truth images.

2) Emre Sargin/Ellen Feldman : Recent research suggests that there is a link between psychopathic behavior and brain structure. One method of analyzing this relationship is Magnetic Resonance Imaging (MRI), an innovative technique that allows certain regions of the brain to be visualized. This provides useful information about the structural differences between people exhibiting normal behavior, contrasted with those who exhibit psychopathic behavior. Furthermore, current computer vision tools can mark these regions on the MRI image. Given these regions, we are interested in measuring their thickness because it is known that the thickness is one way of representing the structure. This information is fundamental in identifying the people with psychopathic behavior from their MRI images. This project focuses on extraction of interfaces between the brain regions in the images taken with the Structural MRI technique. The interfaces will then be used to measure the thickness of these regions. We will be working with three main brain regions: Gray Matter, White Matter , Cerebrospinal fluid (CSF)

3)  Swapna Joshi/Natalie Williams : Modern tomographic imaging methods are playing an increasingly important role in understanding brain structure and function, as well as in understanding the way in which these change during development , aging and pathology Information obtained through the analysis of brain images can be used to explain anatomical differences between normal and pathologic populations, as well as to potentially help in the early diagnosis of pathology . Recent studies have shown, approximately 5% of males are characterized by a pattern of antisocial behavior that onsets in early childhood and remains stable across the life-span. These men are responsible for 50% to 70% of all violent crimes scribed, and not comparable.  The goal of this project is to help Psychologists identify patterns that can distinguish psychopaths brains from that of normal brains. It is not known if such men present abnormalities in brain structure. To our knowledge, no other quantitative data have been reported on the neuroanatomy of persistent violent offenders with a history of antisocial behavior going back to at least mid-adolescence.

Camera Networks

4)  Thomas Kuo/Eli Flores : One goal with a network of smart cameras is to track objects across the views of the cameras.  This means that a person appearing in one camera can be identified in another camera even if it leaves the views of both for a short period of time.  Part of this project will involve investigating methods for this type of tracking.  Another part of this project involves the physical implementation of the cameras.  Our network consists of both ground cameras and aerial cameras mounted on helicopters.  Currently the helicopters are remote-controlled, but that makes them difficult to control.  Thus they are being retrofitted with better sensors that will allow them to fly autonomously.  The project will include working on the controls to this system to allow it to stay in one place.

5) Carter De Leo/Anina Cooter: This project is focused on the development of rapidly-deployed sensor networks. The concept is to be able to enter a new environment without any special modifications and quickly drop any number of self-contained sensors (right now wireless-enabled smart video cameras) without much care in their placement. When the sensors are in place, they should be able to automatically discover their positions relative to each other and start exchanging information about what they can see. This collaboration should enable automatic tracking of interesting objects, like people, through the environment and allow the network to report its results in real-time.  An important part of this effort is that each sensor needs to reliably discover when and how its view overlaps with the views of the other sensors in the network. Traditionally, this is accomplished by moving a known calibration pattern, such as a large chessboard, through the scene. Each camera can look for the pattern and report to the network when it is in view. When two or more cameras see the pattern at the same time, they can extract features in their image, such as the corners of the chessboard blocks, and share the results with the other cameras. This allows the network to discover the correspondences between sensors with overlapping views, which is necessary for later computer vision tasks. In the rapidly-deployable setting, however, moving a calibration pattern through the area is not feasible. To help solve this problem, this project will use infrared lasers to give our sensors the ability to briefly project a pattern onto the scene, allowing overlapping cameras to find their correspondences without relying on outside objects.

Image Forensics and Tamper Detection

6)  Anindya Sarkar/Erick Spaan : Digital image forensics is a topic of enormous current interest and involves various challenges, especially with regards to authentication of images and estimating the reliability of the image content. With easy-to-use image editing tools, portions of an image are easily cropped and inserted into other images; image resizing is also done followed by suitable blending so as to make the insertion of external image content appear perceptually transparent. Seam carving is another state-of-the-art content-aware image resizing method that is used for removing local regions of interests (e.g. objects). During the course of the summer project, we will strive to improve upon various state-of-the-art tamper detection methods and study their performance even under severe compression attacks. E.g. most current re-sampling detection methods fail when the re-sampled image is subjected to mild/severe JPEG compression. Also, when JPEG images at different quality factors are combined, the change can be easily captured when a coarser quality (lower quality factor JPEG) image is inserted into a finer quality image (higher quality factor). We will look at avenues to tackle the reverse and more difficult problem of inserting a higher quality image into a relatively poorer quality JPEG image. Apart from seam-carving based object detection, there are other techniques which look to seamlessly remove the salient content – e.g. image impainting based approaches. We aim to come up with generic methods to detect and localize image regions which are more likely to correspond to the removed object. The final aim will be to develop a holistic view of the challenges that lie ahead in image forensics and identify the image editing software functions (e.g. Photoshop filters) which can be detected using our proposed schemes.

Object Recognition

7)  Aruna Jammalamadaka/Chris Wiest : The project will focus on existing methods of object recognition. The bag of words model, parts based model and models based on boosting texton features have gained popularity in the vision community over the past decade. Model performance is tied very closely to the type of descriptors (local and global) driving these models. The goal would be to evolve a matlab toolbox bringing together open source implementations of the different models, along with the descriptors driving these models.  Based on time availability, the project would also investigate the applicability of manifold learning in the above mentioned models of object recognition. The project is part of our effort to investigate the applicability of object recognition models on natural images to biological images (to recognize recurring structures e.g syanpses).