Monthly Archives: February 2016

Interview with new MCL member Ronald Salloum

In spring 2016, MCL has a new PhD student, Ronald Salloum. We welcomed him and had an interview with him.

 

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

I received a B.S. degree in Electrical Engineering from California State Polytechnic University, Pomona. After receiving my B.S. degree, I worked for a few years in the industry as a systems engineer. I am currently pursuing a PhD degree in Electrical Engineering at USC, under Professor Kuo’s supervision. My research interests include machine learning, biometrics, medical imaging, and computer vision.

 

2. What’s your first impression of USC and MCL?

I was very impressed by how Professor Kuo is able to supervise such a large group of students. He is very enthusiastic about his students’ research work and does an excellent job in motivating the group. Also, I was impressed by how organized and systematic MCL is.

 

3. What’s your future expectation for MCL?

I am very excited to be joining MCL and look forward to collaborating with other students in the group, enhancing my skills, and broadening my knowledge of various fields, including machine learning, biometrics, and computer vision.

By |February 28th, 2016|News|Comments Off on Interview with new MCL member Ronald Salloum|

Congratulations to Young Ju Jeong for Passing Her Defense

Young Ju Jeong, a MCL member, has passed her defense on Feb 16, 2016. Congratulations!

Her dissertation title is “Autostereoscopic 3D Display Rendering from Stereo Sequences”. Rapid developments in 3D display technologies have enabled consumers to enjoy 3D environments in an increasingly immersive manner through various display systems such as stereoscopic, multiview, and light field displays. Sufficient 3D contents for various display systems play important role for further commercial viability of 3D display products. The common 3D content, however, is only stereo sequences for 3D stereoscopic displays and it is not guaranteed that the stereo sequences are well calibrated. 3D display rendering algorithm is a key to generating 3D contents from the conventional stereo sequences. In this dissertation we investigate 3D display rendering framework for various type 3D display systems from conventional stereo contents.

Young Ju gave a nice talk with clarity and smooth flow. The Committee was impressed by her high quality research work and results. About her future plan, she wants to generate real like 3D displays which enables us to enjoy wonderful 3D world through conventional devices such as mobiles, tablets, and laptops. When talking about her success in her research work, Young Ju shares her experience with us. She thinks that she couldn’t continue her PhD about 9 years ago and she almost gave up to finish it. However, she could resume PhD again because of others’ help and eventually she can pass the defense exam. She really appreciates for the help and support especially for Prof. Kuo’s sincere guidance.

 

By |February 21st, 2016|News|Comments Off on Congratulations to Young Ju Jeong for Passing Her Defense|

Interview with MCL member Wenchao Zheng

MCL has a new PhD student, Wenchao Zheng, in Spring 2016. Let’s give him a warm welcome!

He received the B.S. degree from the University of Electronic Science and Technology of China, Chengdu, China in 2014. We had a briefly interview with him.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

Before coming to USC, I got my B.S. degree from the University of Electronic Science and Technology of China, Chengdu, China in 2014. I previously was a Ph.D. student in EE-Electrophysics until December 2014 when I found myself more interested in Computer Vision and Machine Learning. I get the precious opportunity to do research in this field at MCL thanks to Prof. Kuo.

 

2. What’s your first impression of USC and MCL?

My first impression on MCL is that it is a very big group, I was wondering how Prof. Kuo could have so much energy to take care of every student. It turns out that my thought was unnecessary. Prof. Kuo is a very energetic and active researcher on the frontier. He knows a lot and is very experienced. He exerts his lifelong knowledge to help his students in every way that a student can be helped. I feel lucky to be a member at MCL.

 

3. What’s your future expectation for MCL?

I wish all the members at MCL work hard together and make MCL a famous lab in computer vision and machine learning in the world.

By |February 13th, 2016|News|Comments Off on Interview with MCL member Wenchao Zheng|

Interview with new MCL member Yuanhang Su

In spring 2016, MCL has a new PhD student, Yuanhang Su. We welcomed him and had an interview with him.

 

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

Before I join in the MCL lab, I had worked in the industry for five years. But my work mainly focused on video codecs, image/video processing, and system/algorithmic design for digital cameras. Over the years, I have realized that big data analytics and machine learning is in vogue in the industry right now. I believe machine learning combined with video and image data is the future.

 

2. What’s your first impression of USC and MCL?

I choose MCL, which is guided by Professor Kuo. He is very much invested into this field. I wish I can also learn the state of the art in machine learning from my MCL colleagues.

 

3. What’s your future expectation for MCL?

Wish MCL can continue leading its way and hopefully I can make my own contribution to this field.

By |February 8th, 2016|News|Comments Off on Interview with new MCL member Yuanhang Su|

MCL-JCI: a new dataset about perceptual quality of image

MCL lab is proud to release a new dataset about compressed images. It consists of 50 source images with resolution 1920×1080 and 100 JPEG-coded images for each source image. More than 150 volunteers participated in the subjective test. Each individual set of compressed images was evaluated by 30 subjects in a controlled environment.

This dataset was proposed to challenge the traditional approaches to measure the quality of compressed image/video. Based on the characteristics of the Human Visual System (HVS), a Just Noticeable Difference (JND) framework was proposed to investigate the limitation of HVS on compressed images. It means to boost large-scale statistical study on human-perceived image quality as well as the future development of perceptual-based image/video coding standards.

By |February 7th, 2016|News|Comments Off on MCL-JCI: a new dataset about perceptual quality of image|