Please post your thoughts on Schneiderman & Kanade and Viola & Jones here. Which one do you like better?

This paper presents an object detection framework capable of processing images at real-time speeds while achieving high accuracy. This paper introduces a few novel ideas (integral images) and also brings together many existing concepts (feature selection using AdaBoost and heirarchical classification).

However, I have a few concerns (which might be shared by others too):

0) Given the specific (and rather inflexible) nature of the features, I am wondering if this is indeed an object detection system, or just a frontal-face detection system. Although authors mention in passing towards the end that this can be applied to pedestrian detection, their features seem to be very specific for faces.

1) Another issue is that this method doesn't seem to be invariant to anything: pose or translation, even though authors mention that it can 'absorb' small translations. It seems to work well on frontal-face dataset; for more credibility, they should have provided results on other harder datasets.

2) The training time (order of weeks) seems too long. Although, I have to admit that I am not familiar with the 'par training time' for current systems.

3) Since they are working with small 24x24 patches, and have difference of intensities of image parts as features: I am just curious how well a naive pixel intensity based classifier would work (576 dimensional feature vector). These features will need a lot less time to train on?

A problem with these window-scanning approaches is that the idea of training a separate classifier for each object in the world (and even different classifiers for different poses) just doesn't scale with the large number of objects present in the world.


Surely one does not want 1 million classifiers being independently applied to each window in an image.

I agree that faces are easy and contains lots of internal features, so that wavelet features can represent the characteristics of the face well. Still, they have pulled the performance of this "easy" problem up to a level that it actually meets the normal people's standards, not to just vision people's who are pretty generous.

Regarding Schneiderman's paper, I like the general attitude of the author. There isn't much mathematically solid foundation or any fancy model from the machine learning community, but the author has a good idea of what is going on in each step and what the advantages and limitations are. He doesn't over-generalize or make overstatement of his methods.

The limitations are, of course, that they are looking at a tiny subwindow each step and doesn't take any global information into account.

I came across your discussion using google and Im glad I did. Im in Scotland and I just wanted to leave a short message encouraging you to keep on doing! buspar medication webpage devoted to buspar medication. ritalin picture webpage devoted to ritalin picture. rules!

Samuel you are misleading people…..i clicked on the link and there was nothing related to buspar medication but there was some free web hosting site. I suffer from anxiety and i use buspar so I thought I can get some more information about anxiety here but there was nothing as such. For people that suffer from anxiety just like me then I would like to share my experience with you guys….i use Buspar medicine as well as I do yoga and meditation to overcome my anxiety. If one wants real information about buspar then there is an article on page http://www.drugdelivery.ca/s3132-s-BUSPAR.aspx try to read it.

Welcome come to Nike Store, we specialize in collecting Nike Shoes, Air Jordan shoes, Nike Air Force Ones, Nike Shox and Nike Air Max online since 2003, we get cheap Nike Dunk SB and new Adidas Shoes every month, our Adidas Sneakers are in highest quality, if you see our Air Jordan shoes you will definitely love those Air Jordans.

lM66pA

Perfect site, i like it!