Il Yong Chun (chun.ilyong at gmail)

Postdoctoral Research Fellow in Electrical Engineering and Computer Science
under the supervision of Professor Jeffrey A. Fessler
Research interests in compressed sensing, convolutional dictionary learning,
model-based computational imaging, and image analysis

Find me on Scholar, LinkedIn, 🎓 PNG.

Compressed Sensing and Parallel Acquisition: Theory and Application

Parallel acquisition systems are employed successfully in a variety of different sensing/imaging applications (e.g., parallel MRI, multi-view imaging, wireless sensor networks, light-field imaging with muptiple focal stacks, synthetic aperture radar imaging, derivative sampling in seismic imaging, etc.) when a single sensor cannot provide enough measurements for a high-quality signal recovery. Compressed sensing (CS), random sub-sampling theory dependent on the sparsity of signal, has been used to establish the theoretical improvements of such systems by providing recovery guarantees for which, subject to appropriate conditions, the number of measurements required per sensor decreases linearly with the total number of sensors. I am a pioneer in establishing theoretical improvements of CS parallel acquisition architecture, developing CS-based imaging fundamentals, and applying these theories in practical applications, e.g., parallel MRI (MRI using multiple receive coils) and light-field imaging with multiple focal stacks.

Convolutional Dictionary Learning: Acceleration and Convergence

Convolutional dictionary learning (CDL; or convolutional sparse coding) is a fundamental component to mathematically understand (deep) convolutional neural networks. Moreover, with the help of its single layer structure, the learned filters from CDL have been successfully applied to some image processing problems, e.g., image inpainting and denoising. An accelerated CDL algorithm development is the first essential issue in learning hundreds of filters from "big data" that consist of millions of training images. The convergence guarantee is another crucial issue. Without convergence theorem, one cannot guarantee whether the learned filters after many iterations are reasonable or not; in addition, convergence analysis can provide a new perspective to design faster algorithms. I am in the forefront of developing convergence-guaranteed and stable algorithms of CDL and accelerating the algorithms. While establishing accelerated and convergent algorithms for CDL, I am actively applying them to reconstruct images in medical imaging and computational photography.

Adaptive Computational Imaging: Theory and Application

Most imaging devices have complicated imaging physics and suffer from various types of noise. This is the main reason that underlying mathematical analyses are largely absent in their image recovery performance. If undersampling schemes are involved, the performance analysis becomes a tricky math problem. By exploiting signal processing estimation techniques (e.g., mean square error, MSE, and signal-to-noise ratio) and stochastic modeling, my third research interest is to adaptively control imaging techniques to improve the quality of reconstructed images. For example, I initially established the imaging fundamentals of (high-field) MRI using multiple transmit/receive coils and its relation to MSE, and proposed a new excitation pattern design which further reduces MSE and manages the specific absorption rate. In particular, adaptively considering the spatial information of transmit and receive coils and expected aliasing patterns, the proposed excitation pattern not only successfully reduces the error variances but also suppresses the aliasing artifacts caused by extremely accelerating (i.e., 8-fold) scanning.

Image Analysis in Neuroimaging

Recently, rapid interest has grown in the neuroscience community in evaluating the impact of brain changes caused by repetitive sub-concussive hits to the head. Using diffusion tensor MRI, I evaluated longitudinal white matter changes in high-school football players and examined how these changes may be linked to an athlete’s history of accumulated head collision events during practices and games.

On the other hand, an appropriate statistical image analysis framework (e.g., hypothesis testing) to reliably detect subtle changes in athletes who experienced repetitive sub-concussive head blows is largely absent. I initially proposed a stronger randomized hypothesis testing method that exploits both completely and incompletely paired data. The method successfully detects more significantly deviated regions in the sub-concussed brains, thereby providing a stronger evidence to suggest that head impacts commonly occur during contact sports have the potential for neurological injury although those impacts do not result in visible symptoms of neurological dysfunction.

To see the complete list of publications, please click here to access my CV.