Failed with this :(
http://i.dailymail.co.uk/i/pix/2012/11/06/article-2228752-15...
Show HN: API for detecting people, cars, and everyday objects in images
51–60 of 74 posts
Re: Show HN: API for detecting people, cars, and everyday objects in images
#52shamelessly plug: libccv supports REST-ful API in 0.4 version, it is open-source, and free: http://libccv.org/doc/doc-http/. Trained pedestrian / car / face detectors are included.
Re: Show HN: API for detecting people, cars, and everyday objects in images
#53Are you willing to pay for this service but need higher accuracy? I'd love to hear from you.
Re: Show HN: API for detecting people, cars, and everyday objects in images
#54This is not Pedro Felzenszwalb's discriminative part-model algorithm. This is simple AdaBoost. The authors have labeled a bunch of datasets (1000s of them) and are able to detect whatever object. AdaBoost (Viola/Jones) is the most popular Yes/No detector, there is an OpenCV api for it. It used for detecting faces and license plates in commercial applications. Full person detector is nothing but a SVM+HOG descriptor.…
It got zero of six airplanes for the link below, even though the images are not overlapping and are against a blue sky background:
http://www.keithcarter.com/wp-content/uploads/2009/10/blue-a...
Re: Show HN: API for detecting people, cars, and everyday objects in images
#55Failed completely for me across a half dozen tries. I wonder how cheaply you could get results via Mechanical Turk. I bet you could get much more accurate results for a very low price but with some added latency.
I agree, crowdsourcing is the way to go if you need to understand images. Image recognition is a very tough problem, especially if you're trying to detect anything nuanced.
We've developed RTFM at CrowdFlower to handle the similar task of moderating images and providing detailed reasons for why they are flagged. It's a common problem that the computers can't solve well enough yet.
Re: Show HN: API for detecting people, cars, and everyday objects in images
#56Over a dozen experiments, the recognition rate for faces seems to be about 70%. Example of failure: only 2 faces detected here (in particular NOT the one in focus) http://iamdaveknockles.files.wordpress.com/2011/03/meeting_j... This is worse than OpenCV (I thought you were using OpenCV but apparently aren't?)
Similar result with the image below. It got four of six faces, missing the most important of the faces.
http://www.bostonglobe.com/rw//Boston/2011-2020/WebGraphics/...
Re: Show HN: API for detecting people, cars, and everyday objects in images
#57Looks like this is using training data from the PASCAL VOC object detection challenge [1], which is the standard benchmark for evaluating object detection performance in computer vision. Object detection is an extremely tough problem (some would say it is the computer vision problem ;-)), and while we've made a lot of progress in the past decade, the best methods are still terrible [2] -- average detection precision…
Isn't the 30-50% only applicable to doing object recognition? I.e. multi-classification.
In this case, you have to tell it which object you're looking for.
Re: Show HN: API for detecting people, cars, and everyday objects in images
#58This is not Pedro Felzenszwalb's discriminative part-model algorithm. This is simple AdaBoost. The authors have labeled a bunch of datasets (1000s of them) and are able to detect whatever object. AdaBoost (Viola/Jones) is the most popular Yes/No detector, there is an OpenCV api for it. It used for detecting faces and license plates in commercial applications. Full person detector is nothing but a SVM+HOG descriptor.…
It got zero of six airplanes for the link below, even though the images are not overlapping and are against a blue sky background: http://www.keithcarter.com/wp-content/uploads/2009/10/blue-a...
But it did find one potted plant for that image. I could not see it (bottom left hand corner).
Re: Show HN: API for detecting people, cars, and everyday objects in images
#59This reminds me of how my visual psychology professor was attempting to help those with poor vision 15 years ago, but didn't appear to get anywhere with at the time. The idea was a simple (but clever) one - use virtual reality to segment the world into solid blocks of identified objects. The solid blocks are identifiable to those with poor vision in a way that the real world is not. Essentially this meant processing…
However, attempt this today According to http://news.ycombinator.com/item?id=4985100 it won't be today, perhaps tomorrow.
I'm guessing that many severely sight-impaired people would be willing to take the latency to have vision that is significantly more useful.
Re: Show HN: API for detecting people, cars, and everyday objects in images
#60Failed completely for me across a half dozen tries. I wonder how cheaply you could get results via Mechanical Turk. I bet you could get much more accurate results for a very low price but with some added latency.
http://www.acstede-test.co.uk/blackhill/images/stories/Lleyn...
Sheeps were detected as horses, faces but not as cats or cars. This seems to be the current state of the art for a general purpose classification. I haven't seen anything better yet (unless you'd specialize in sheep detection)