News

MCL has a new Master’s student, Terna Kpamber, in Spring 2016. Let’s give him a warm welcome! Here is a briefly interview with him.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)
I’m from Nigeria and I moved to the UK in 2009 and studied there until I completed my undergraduate degree in Electronic Engineering in 2014. I worked at Tyco Safety Products form 2012 to 2013 as part of my degree during which I was an electrical hardware engineer. My final project there was to design a wirelessly controllable socket strip which monitored current consumption and sent real time updates to the control hub.
I began my masters at USC in the Spring of 2015 and I focused on engineering application courses in signal processing. Currently I’m working on a project in which we monitor the board game of scrabble through a camera and we want to be able to automatically detect words formed by players during the game and calculate their game points.
I’m more of an application person than a research person, so I regularly read research papers and write programs to implement their algorithms. My languages of choice are C++ and Python, but I also program in Swift for the iOS and OS X platforms.
Outside of engineering I really enjoy playing and watching soccer and since moving to America I’ve become interested in watching basketball.
 

2. What’s your first impression of USC and MCL?
I wasn’t sure what to expect before coming to USC because I had never been to America. Once I settled in I began to enjoy USC, because the weather was fantastic and there were always activities going on on campus.
I [...]

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.

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.

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.

Sachin Chachada, a MCL member, has passed his defense on Jan 14, 2016. Congratulations!
His dissertation title is “Classification and Retrieval of Environmental Sounds”. Speech and music signals have been extensively studied for several decades. Need for Environmental Sound Recognition (ESR) system has picked up the pace in recent years. Environmental sounds are quotidian sounds, both natural and artificial, i.e. sounds one encounters in daily life other than speech and music. In this thesis, Narrow Band Time Frequency features are proposed which characterize a signal using TF representation of its band limited filtered signal. In order to further improve the performance, use of a novel multi-classifier approach, Para-Boost (PB) model, is proposed. It takes the advantages of all the features and improves the overall performance of ESR system. Finally, considering the exponential growing environmental sound data on the Internet, the thesis tackles the problem of a good content based retrieval system. A two stage content based environmental sound retrieval system is proposed. This query-by-example retrieval system assumes that the database is partially labeled. In Stage I, a broad categorization of environmental sounds based on their signal-characteristic is done. For each category, a classifier is trained to predict labels for unlabeled data in the database and also narrow search range for a query by assigning it multiple, yet limited, class labels. In Stage II, a novel feature and a scoring scheme to do local matching and ranking is proposed. An audio signal is first segmented in an unsupervised manner using Mean Shift algorithm and each segment is represented by its point of convergence in the feature space. The audio signal is finally represented by its energy distribution over each segment thereby capturing the temporal variations [...]