In many image processing applications, human eyes are often the ultimate judge for the goodness of reconstructed images (Yes, MSE-based metrics are also used but they often correlate more with the fidelity than the quality). It is almost by default that the objective of image processing is to turn bad-looking images into good-looking images (e.g., [...]
Archive for the ‘teaching’ Category
When is Seeing Not Believing?
Posted in ee565 on November 12, 2009 | Leave a Comment »
Multi-stabilities in Cognitive System
Posted in digital video processing on October 23, 2009 | Leave a Comment »
The following animation shows an intriguing property of motion perception: there exist two attractors (clock-wise and anti-clockwise) in this dynamic system.
Folktales tell you whether you see it clockwise or anticlockwise will determine whether your left brain or right brain is dominating. What is more interesting to me is how can we have two stable interpretation [...]
Nonlinearity in Image Processing
Posted in ee565 on October 23, 2009 | Leave a Comment »
This week ,we have discussed wavelet thresholding – an extremely simple operation but has shown effective in image denoising applications. Given the fact that thresholding is among the simplest nonlinear operators, there is a lot we can say about the role of nonlinearity in image processing.
What is wrong with linear models? Linear combination of Gaussian [...]
The Mystery of Translation Invariance
Posted in ee565 on October 23, 2009 | Leave a Comment »
In the class, I mentioned Translation Invariance (TI) is a difficult concept in image processing. To understand TI, you need to understand down-sampling first; to understand down-sampling, we need to talk about sampling theorem or Analog-Digital conversion. Nyquist-Shannon sampling theorem states the condition for perfect reconstruction of band-limited signals from their discrete samples. The interpolation [...]
Convexity in Image Processing
Posted in ee565 on October 23, 2009 | Leave a Comment »
Convexity is a concept you don’t see in image processing textbooks. It is a little advanced mathematical tool for engineering students. In the mathematical literature, you can refer to Rockafeller’s “Convex Analysis” (comprehensive and deep) and Boyd&Vandenberghe’s “Convex Optimization (online available at http://www.stanford.edu/~boyd/cvxbook/). In the literature of signal processing, Youla’s 1978 paper was likely the [...]
Curiosity is the best teacher
Posted in ee565 on October 8, 2009 | Leave a Comment »
In this week’s computer assignment, many of you faced the obstacle of It turns out only few students with biometrics background knows how to calculate this Receiver-Operational-Curve thing. You might feel disappointed since I never even mentioned the ROC in the class – “how am I supposed to work this out? it is not covered [...]
A Good Day for Engineers
Posted in ee565 on October 8, 2009 | Leave a Comment »
This year’s Nobel Prize in Physics was unexpectedly awarded to three engineers: one is the “father of fiber optics” Charles Kao (a Shanghaiese who was the Chancellor of CUHK) and the other two are inventors of CCD sensors. In the history of Nobel prize, last time engineers got lucky when two Bell Lab engineers accidentally [...]
Advices on Improving Mathematical and Programming Skills
Posted in ee565 on September 24, 2009 | Leave a Comment »
Based on my interaction with some of you, mathematics and programming skills are likely to be two deciding factors in your success of doing research in various fields (e.g., image processing, biometrics, communication, networking etc.). Therefore, it is inevitable to feel the frustration over some difficult papers (involving deep mathematics) or challenging projects (involving a [...]
What is More Important than Grade
Posted in ee565 on September 24, 2009 | Leave a Comment »
I understand some of you might be upset about losing some point in CA#2. Now here is the bright side: if you look at the grading system, an A grade is 90/100 – so there is a comfort zone where you can lose as many as 10 points. In fact, usually I also give out [...]
Stuff related to AR but not covered in the class
Posted in ee565 on September 17, 2009 | Leave a Comment »
Due to time constraint, we will have to say farewell to the topic of autoregressive(AR) model and move to a new chapter today. However, there are still many interesting stuff related to AR you can dig into:
1) Usefulness of AR. As I mentioned in the class, AR model is more successful on speech than image [...]
