Comments for Computer Vision for Dummies http://inperc.com/blog2 From a newcomer, hence the name Fri, 05 Sep 2008 23:57:01 +0000 http://wordpress.org/?v=2.0.2 Comment on Our R&D Plans by Lim Ee Hai http://inperc.com/blog2/2008/08/03/our-rd-plans/#comment-451 Fri, 22 Aug 2008 16:44:04 +0000 http://inperc.com/blog2/2008/08/03/our-rd-plans/#comment-451 Being a maths teacher, sometimes I find it hard to find examples to related math to real applications. Examples can be found easily but an in-depth one with interesting applications are hard to come by. In this post of yours, I found exciting examples to quote and potential sharing quality. I have worked with images before and really appreciate the application of maths (especially matrices) to image processing. Well written post! Being a maths teacher, sometimes I find it hard to find examples to related math to real applications. Examples can be found easily but an in-depth one with interesting applications are hard to come by. In this post of yours, I found exciting examples to quote and potential sharing quality. I have worked with images before and really appreciate the application of maths (especially matrices) to image processing.
Well written post!

]]> Comment on What is image segmentation? by Peter http://inperc.com/blog2/2008/06/15/what-is-image-segmentation/#comment-383 Mon, 14 Jul 2008 13:57:47 +0000 http://inperc.com/blog2/2008/06/15/what-is-image-segmentation/#comment-383 That’s a fair question. The main reason is that all I’ve got right now is a critique. I don’t have something to offer that wouldn’t be just as flawed. I do plan to right something up in the coming weeks but only as a very first draft. It will take a while for it to develop into something serious. But even if I had something perfect ready, I’d hesitate to offer it for Wikipedia. I find the idea that what I wrote can be sliced and diced by other people very unappealing. Not that I have anything against Wikipedia... That’s a fair question. The main reason is that all I’ve got right now is a critique. I don’t have something to offer that wouldn’t be just as flawed. I do plan to right something up in the coming weeks but only as a very first draft. It will take a while for it to develop into something serious. But even if I had something perfect ready, I’d hesitate to offer it for Wikipedia. I find the idea that what I wrote can be sliced and diced by other people very unappealing. Not that I have anything against Wikipedia…

]]> Comment on What is image segmentation? by Régis B. http://inperc.com/blog2/2008/06/15/what-is-image-segmentation/#comment-381 Mon, 14 Jul 2008 01:47:18 +0000 http://inperc.com/blog2/2008/06/15/what-is-image-segmentation/#comment-381 Your critics of the wikipedia article are well argued, why don't you modify it? Your critics of the wikipedia article are well argued, why don’t you modify it?

]]> Comment on A quick review of TinEye by Peter http://inperc.com/blog2/2008/05/27/a-quick-review-of-tineye/#comment-298 Sun, 01 Jun 2008 13:12:25 +0000 http://inperc.com/blog2/2008/05/27/a-quick-review-of-tineye/#comment-298 I can see that for TinEye’s purposes rotation isn’t very important. But it would definitely not hurt. I care about this because my interest is mostly image analysis and search in science applications. BTW, in case it didn’t come across in the post, my impression of TinEye is quite positive. It works! I can see that for TinEye’s purposes rotation isn’t very important. But it would definitely not hurt. I care about this because my interest is mostly image analysis and search in science applications. BTW, in case it didn’t come across in the post, my impression of TinEye is quite positive. It works!

]]> Comment on A quick review of TinEye by Leila Boujnane http://inperc.com/blog2/2008/05/27/a-quick-review-of-tineye/#comment-291 Sat, 31 May 2008 13:24:59 +0000 http://inperc.com/blog2/2008/05/27/a-quick-review-of-tineye/#comment-291 Peter, Thanks for giving TinEye a try. A small correction: our image identification algorithms can handle rotation exceptionally well. We have not rolled that out in TinEye because it would add some computational overhead and is not a critical feature for most of our users. I hope you realize that the current TinEye index is 487 million images and that we are working on growing that into the tens of billions of images. While it would be a nice feature, rotation invariance is not as significant as many of the goals and features we have in the works for TinEye. Thanks for the link to Lincoln from MS Research but I have never seen it work on a large scale collection (1/2 a billion images would be a good start!). Keep up the good work! Cheers, Leila Peter,

Thanks for giving TinEye a try.

A small correction: our image identification algorithms can handle rotation exceptionally well. We have not rolled that out in TinEye because it would add some computational overhead and is not a critical feature for most of our users. I hope you realize that the current TinEye index is 487 million images and that we are working on growing that into the tens of billions of images. While it would be a nice feature, rotation invariance is not as significant as many of the goals and features we have in the works for TinEye. Thanks for the link to Lincoln from MS Research but I have never seen it work on a large scale collection (1/2 a billion images would be a good start!).

Keep up the good work!

Cheers,

Leila

]]> Comment on “Brain-inspired” and “nature-inspired”, a rant. by Peter http://inperc.com/blog2/2007/10/12/%e2%80%9cbrain-inspired%e2%80%9d-and-%e2%80%9cnature-inspired%e2%80%9d-a-rant/#comment-252 Tue, 20 May 2008 22:13:34 +0000 http://inperc.com/blog2/2007/10/12/%e2%80%9cbrain-inspired%e2%80%9d-and-%e2%80%9cnature-inspired%e2%80%9d-a-rant/#comment-252 David>> Computer vision is a science. Just like any science it tries to understand the world around us. What is suggested is that we should instead try to understand -- how we understand the world. It’s a roundabout, at best. David>> Computer vision is a science. Just like any science it tries to understand the world around us. What is suggested is that we should instead try to understand — how we understand the world. It’s a roundabout, at best.

]]> Comment on “Brain-inspired” and “nature-inspired”, a rant. by David Marr is turning in his grave http://inperc.com/blog2/2007/10/12/%e2%80%9cbrain-inspired%e2%80%9d-and-%e2%80%9cnature-inspired%e2%80%9d-a-rant/#comment-251 Tue, 20 May 2008 15:20:50 +0000 http://inperc.com/blog2/2007/10/12/%e2%80%9cbrain-inspired%e2%80%9d-and-%e2%80%9cnature-inspired%e2%80%9d-a-rant/#comment-251 First of all, just because computers and brains operate differently on the implementation (hardware vs. bioware) level doesn't mean that the algorithms and representations used by our brains won't be useful for developing better computer vision systems. Secondly, we do indeed already know a fair amount about how vision works in the brain, and we're learning more all the time. So while we'd probably never want to build a computer vision system that mimics the brain at the synaptic level, we should be ready to take advantage of our expanding knowledge of biological vision rather than saying brains are too different or too complicated and sticking our heads into the sand. First of all, just because computers and brains operate differently on the implementation (hardware vs. bioware) level doesn’t mean that the algorithms and representations used by our brains won’t be useful for developing better computer vision systems. Secondly, we do indeed already know a fair amount about how vision works in the brain, and we’re learning more all the time. So while we’d probably never want to build a computer vision system that mimics the brain at the synaptic level, we should be ready to take advantage of our expanding knowledge of biological vision rather than saying brains are too different or too complicated and sticking our heads into the sand.

]]> Comment on Pattern recognition in computer vision, part 1 by Computer Vision for Dummies » Pattern recognition in computer vision, part 2 http://inperc.com/blog2/2008/05/02/pattern-recognition-in-computer-vision-part-1/#comment-209 Mon, 12 May 2008 18:31:54 +0000 http://inperc.com/blog2/2008/05/02/pattern-recognition-in-computer-vision-part-1/#comment-209 [...] Let’s review part 1 first. If you have a 100×100 gray scale image, it is simply a table of 100×100 = 10,000 numbers. You rearrange the rows of this table into a 10,000-vector and represent the image as a point in the 10,000-dimensional Euclidean space. This enables you to measure distances between images, discover patterns, match images, etc. Now, what is wrong with this approach? [...] […] Let’s review part 1 first. If you have a 100×100 gray scale image, it is simply a table of 100×100 = 10,000 numbers. You rearrange the rows of this table into a 10,000-vector and represent the image as a point in the 10,000-dimensional Euclidean space. This enables you to measure distances between images, discover patterns, match images, etc. Now, what is wrong with this approach? […]

]]> Comment on Google’s new image search by Computer Vision for Dummies » Image search engines keep launching http://inperc.com/blog2/2008/04/29/googles-new-image-search/#comment-200 Wed, 07 May 2008 22:25:18 +0000 http://inperc.com/blog2/2008/04/29/googles-new-image-search/#comment-200 [...] After Google “launched” its ImageRank - by presenting a paper about it, now there are two more. [...] […] After Google “launched” its ImageRank - by presenting a paper about it, now there are two more. […]

]]> Comment on Fields related to Computer Vision, part 3 by Computer Vision for Dummies » Google’s new image search http://inperc.com/blog2/2008/03/28/fields-related-to-computer-vision-part-3/#comment-198 Tue, 29 Apr 2008 19:34:40 +0000 http://inperc.com/blog2/2008/03/28/fields-related-to-computer-vision-part-3/#comment-198 [...] The most important thing to understand here is that the paper isn’t about improving image search in general (especially visual image search and CBIR, see here). It is specifically about Google image search (and indirectly other search engines, MSN, Yahoo, etc). The goal is to improve it (because it sucks). It is currently based on surrounding text and as a result you get a lot of irrelevant images. Essentially, they add to this approach some image analysis. What kind? Not the best kind – “descriptors”. So there will be no analysis of the content of the image (see Fields related to computer vision). Even so, the descriptors will help to evaluate similarity between images - to a certain degree. [...] […] The most important thing to understand here is that the paper isn’t about improving image search in general (especially visual image search and CBIR, see here). It is specifically about Google image search (and indirectly other search engines, MSN, Yahoo, etc). The goal is to improve it (because it sucks). It is currently based on surrounding text and as a result you get a lot of irrelevant images. Essentially, they add to this approach some image analysis. What kind? Not the best kind – “descriptors”. So there will be no analysis of the content of the image (see Fields related to computer vision). Even so, the descriptors will help to evaluate similarity between images - to a certain degree. […]

]]>