gi/go
Suddenly, a leopard print sofa appears
81–90 of 114 posts
Re: Suddenly, a leopard print sofa appears
#82How about detecting vector edge shapes and unifying that result with the existing classifier? Surely a leopard sofa cannot have the same edge vector shape as a real big cat.
That's an idea from 1970-1980s AI, called the "primal sketch" model. The concept was to take an image and try to turn it into a line drawing, then extract the topology and geometry.[1] Further processing might yield a 3D model.
This sort of works on simple situations without too much edge noise. It's been used for industrial robot vision, where what matters are the outside edges of the part. It's not too useful when there's clutter, occlusion, or noisy textures.
More recent thinking is to find surfaces, rather than edges. This works well if you have a 3D imager, such as a Kinect. You can get a 3D model of the scene. Occlusion remains a problem, but texture noise doesn't hurt.
[1] http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/GOME...
Re: Suddenly, a leopard print sofa appears
#83OP here, and thank you kind sirs and ladies for you feedback.
I'd just like to answer the recurring objection: yes, our visual experience contains a lot of frames and that seemingly refutes my MNIST example; however, you do forget about the other part of a supervised dataset, namely labels. Do we have a label provided to each thing we see in our life? Obviously not. How much time do you need to familiarize yourself with a new entity, like an unknown glyph or symbol? Can't provide a concrete example, but I guess a single math class was enough for all of you to recognize all the digits the next day. You can test it right now by looking into some unknown alphabet and then looking into it again upside down - you'll recognize it perfectly, except for mental rotation issues (which occuur even for well-known letters and symbols).
Re: Suddenly, a leopard print sofa appears
#84This is fascinating and well written. I tried the unrotated sofa image on Wolfram's ImageIdentify and it correctly identified a settee [1]. So it presumably gathered that from the shape of the image rather than the pattern. It is peculiar though that it can't see the shape under a simple rotation. Or perhaps the margin of confidence levels between sofa and leopard were so narrow that a rotation was enough to tip it i…
I tried Wolrfram ImageIdentify with a bunch of bicycle photos and it insisted on identifying them as "Bicycle Saddle". I kept trying different ones and it kept identifying as "Bicycle Saddle"...
To be fair that is one of the few things on a bike that isn't a triangle.
Re: Suddenly, a leopard print sofa appears
#85Earlier quoted context omitted.
I tried Wolrfram ImageIdentify with a bunch of bicycle photos and it insisted on identifying them as "Bicycle Saddle". I kept trying different ones and it kept identifying as "Bicycle Saddle"...
To be fair that is one of the few things on a bike that isn't a triangle.
hmmm, good point!
Re: Suddenly, a leopard print sofa appears
#86Thank you for this article; very thought provoking. My nitpick: > When each student was given a heavy book of MNIST database, hundreds of pages filled with endless hand-written digit series, 60000 total, written in different styles, bold or italic, distinctly or sketchy. > ... > So, are you going to say that was not the case? I understand the point the author is making. Human brains are really good at taking limited…
Forget seeing a symbol once, you can recognise and represent a symbol without ever having seen it.
Test your humanness; draw these symbols:
"Like an E but rotated so the prongs point upwards"
"Like a snake but with two heads. Snakes down, up, down, up, down."
"Like a walking stick with the handle pointing left and looping back around."
(answer for A: Russian letter Sha) (answer for B: Kannada letter Uu) (answer for C: Tamil vowel sign I)
Re: Suddenly, a leopard print sofa appears
#87Well, you can try this one, it is open source and based on Caffe : http://imgdetect.alexgirard.com/#
The image link: http://rocknrollnerd.github.io/assets/article_images/2015-05...
It says 'studio couch, day bed' with 97% accuracy. Very likely because it is part of Imagenet.
Re: Suddenly, a leopard print sofa appears
#88Google image search says Best guess for this image: cat bed furniture https://goo.gl/vXwSaj
That's cheating though; you can see the first few results are for the exact same image with a dog pasted on it, and contain those terms.
Re: Suddenly, a leopard print sofa appears
#89OP here, and thank you kind sirs and ladies for you feedback. I'd just like to answer the recurring objection: yes, our visual experience contains a lot of frames and that seemingly refutes my MNIST example; however, you do forget about the other part of a supervised dataset, namely labels. Do we have a label provided to each thing we see in our life? Obviously not. How much time do you need to familiarize yourself w…
What is the upside down experiment meant to prove? Seems to me that the mental rotation issues indicate that mental image processing is not very rotation tolerant, but rather needs a hardwired (and slow) counter-rotation step added to cope with rotated symbols, which you could just as well tack onto a neural network. Am I missing the point?
Also, being able to consciously recognize letters is relatively easy, but the normal reading process, with which people recognize well-known letters and instantly unconsciously convert them to sounds, does require quite a bit of repetition of those letters before it starts to kick in...
Re: Suddenly, a leopard print sofa appears
#90Maybe the algorithm did detect a face in the couch, as we see them in trees (wood sprites!).