Dextro
AI
computer vision api
SHOW HN2013
179points
72comments
#86of 1,739 in 2013
Top 5%of 2013 by points
How HN took it
RoastedHalf or more of the comments are critical
6 positive, 14 neutral or asking, 6 mixed, 27 critical, out of 53 comments about the project. Thread score -0.34.
Performance: 1 for, 23 againstIdea: 3 for, 0 againstDocs: 0 for, 2 againstExecution: 0 for, 1 againstPricing: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Works well on some images and is easy to use
From 2 comments
Did a few tests and it works pretty well! No false positives at least. Any plans to increase the number of objects you can search for at once? Very interested in using this but…
makeee on HNWorks well! Found a few it didn't work on. For example, it didn't detect an airplane in this image (but it's a fighter jet, so maybe not part of the training set):…
yesimahuman on HN
Free tier is appealing
From 1 comment
That's great! I like that you guys are offering a small free usage tier!
IceyEC on HN
Objections
Misses many objects such as airplanes and cats
From 4 comments
Tried detecting Airplanes on this image with 18 airplanes, but it only detected 4 of them.…
limejuice on HNTried to detect Cats in a whole room full of cats, and it detected zero cats. http://englishrussia.com/wp-content/uploads/2007/08/130-cats-1.jpg
limejuice on HNdetected 2 planes, there are 7 http://iskin.co.uk/wallpapers/imagecache/1280x800/jet_plane_formation.jpg seems too buggy to pay just yet
mephi5t0 on HNIt didn't recognise the cat in this picture (http://i.imgur.com/TgFaJh.jpg) so I'm doubtful of it's practicality.
cabalamat on HN
Reports false positives and wrong counts
From 3 comments
http://rumors.automobilemag.com/files/2012/11/2013-VW-Eos-front-three-quarter-with-plane.jpg detected 3 planes... there is only 1 plane and a car
mephi5t0 on HNIt detects a false positive in this picture for "full-body person": http://farm9.staticflickr.com/8232/8366217251_972624d84b_b.jpg The man is detected, but also a shape above the…
mrtbld on HNWow, I just tried this image of faces: http://3rdarm.biz/images/2010/02/faces.jpg It got almost all of them but so many errors. It can't detect sheeps either. I was really…
zopticity on HN
Video pricing too high
From 1 comment
As a long time CV enthusiast, I applaude the tech and the way you guys make it "just work". However for any serious application I feel a few things are missing: - your pricing…
steeve on HN
Face detection stops at four faces
From 1 comment
If you read the description on the site, you'd know that the face detection stops after finding 4 faces.
bsenftner on HN
Requests
Detect more than four objects at once
From 2 comments
Did a few tests and it works pretty well! No false positives at least. Any plans to increase the number of objects you can search for at once? Very interested in using this but…
makeee on HNYes! Scanning for more than 4 objects at once (which is currently supported) is something that we definitely want to enable in the future. The only constraint is the number of…
jluan on HN
Confidence scores on detections
From 2 comments
As a long time CV enthusiast, I applaude the tech and the way you guys make it "just work". However for any serious application I feel a few things are missing: - your pricing…
steeve on HNHey steeve, thanks for the really kind feedback! We're aware of the video pricing issue, and it's something that we're thinking hard to come up with a solution to for makers and…
jluan on HN
Video support at lower cost
From 2 comments
As a long time CV enthusiast, I applaude the tech and the way you guys make it "just work". However for any serious application I feel a few things are missing: - your pricing…
steeve on HNHey steeve, thanks for the really kind feedback! We're aware of the video pricing issue, and it's something that we're thinking hard to come up with a solution to for makers and…
jluan on HN
Questions
Is it built on the Felzenszwalb part-model code
From 2 comments
It is probably based on "Object Detection with Discriminatively Trained Part Based Models"; Pedro F. Felzenszwalb"... Somebody took http://people.cs.uchicago.edu/~rbg/latent/…
dchichkov on HNThis 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…
ank286 on HN
Is the Mechanical Turk approach cheaper for accuracy
From 2 comments
Failed 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…
forrestthewoods on HNOne to two cents a task. Anytime you have a language agnostic task (identifying/classifying objects, etc), the tasks can be done very cheaply. Just make sure you do triplicate…
aantix on HN
Alternatives named
OpenCV
From 3 comments
Can you give me bit more technical background. Tell me how this is better than for eg. out of the box openCV filters.
bluishgreen on HNOver 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)…
fchollet on HNTry OpenCV: http://opencv.willowgarage.com/wiki/
thechut on HN
libccv
From 1 comment
shamelessly 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.
liuliu on HN
Mechanical Turk
From 1 comment
Failed 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…
forrestthewoods on HN