An API wrapper to Clarifai's image recognition demo | Hacker News Reader

An API wrapper to Clarifai's image recognition demo

api.blockspring.com

47 pointshackerews27 comments

Open articleView on HN

Adam from Clarifai here.

As tommoor pointed out, this is just a thin wrapper around our demo at http://www.clarifai.com/

(we're very flattered...)

A real API will be out soon. It won't be throttled as heavily as the demo, and will be more developer friendly.

you can sign up for early beta access at clarifai.com.

We've changed the title (from "Identifying Images With an API that Actually Works") in an attempt to share the credit fairly.

Really well done Clarifai. From playing around, it works just as well, if not better, than google's reverse image search: https://api.blockspring.com/users/pkpp1233/blocks/5a1b66ef20....

Can you roughly share when the developer API will be ready?

Wow. The classifier is really impressive. Will it be possible to train your own classifier on your service? I have a lot of clothing items that it would be useful to classify. I tried building my own with opencv, but I haven't had too much luck so far.

I signed up for the api access - would be very interested in playing a bit more with this.

Thanks!

Training custom classifiers isn't in the roadmap for v1, but there will be a mechanism for providing feedback (suggesting new tags and marking errors), and we'll continue to improve our models based on that.

If you have a very large (100k+ images) well-labeled repository to train from, send us a note at info@clarifai.com, we'll tawk.

I mean, it's not wrong... But I think the analyzer is missing a detail in this picture...

http://i.imgur.com/MLt4BsX.jpg

we're still working on our bear detector. maybe it's a v2 thing.

I put in the link to my profile picture on twitter -> https://pbs.twimg.com/profile_images/488579015507050497/QvG1...

["black", "american", "woman", "man", "pitt", "brad", "senior", "worker", "group", "cuba"]

Brad Pitt! Great work guys!

I don't know why this link doesn't go directly to the source: http://www.clarifai.com/index.html

Wow! This is really neat, I tried to find images that I didn't think it could process, the results are interesting.

http://upload.wikimedia.org/wikipedia/commons/1/1e/Blown_up_...

["piranha", "fish", "food", "water", "gold", "dish", "crab", "kitchen", "glass", "silver"]

https://www.flippers.com/images/See-SHFA1_Caps&Mods-PCB.JPG

["panel", "retro", "wine", "background", "design", "old", "tool", "letter", "art", "robot"]

http://history.nasa.gov/alsj/a11/a11_lpi_trvrsmap.gif

["background", "metal", "water", "man", "wall", "old", "abstract", "paper", "hand", "paint"]

Very impressive! Some cool ones it recognized:

milk jug http://cdn-jpg.allyou.com/sites/default/files/image/2014/01/...

["milk", "gallon", "jug", "product", "detergent", "plastic", "water", "soap", "canteen", "white"]

mushroom cloud: http://www.atomicarchive.com/Effects/Images/WE12.jpg

["fire", "bomb", "mushroom", "flame", "letter", "font", "hell", "volcano", "smoke", "burn"]

Very optimistic. Got a picture of a Hyundai. Reckons it's a BMW or Audi.

http://www.airnorth.com.au/sites/default/files/Car%20hire%20...

["car", "bmw", "auto", "sport", "3d", "vector", "white", "blue", "front", "audi"]

Tried a Pokémon card and got "semi relevant" results

http://sixprizes.com/wp-content/uploads/pikachu-next-destini...

["background", "card", "kid", "vector", "design", "school", "book", "frame", "cartoon", "dog"]

Facebook Logo: https://www.facebook.com/images/fb_icon_325x325.png

["cross", "sign", "plus", "pound", "medic", "first", "icon", "jesus", "christian", "aid"]

Nice! Got some interesting results from a photos of iPhones and iPads.

Curious to know how this compares head-to-head with the CamFind API at https://www.mashape.com/imagesearcher/camfind which I've been thinking of using for a project.

Well this went better than I expected :) EDIT: context- I'm the one that made the wrapper for clarifai's API, loved the service since I heard of it, great to see people appreciate (from the number of API calls you guys have made so far) both the service and the small wrapper to the API!

Only car was recognised here: http://www.highsnobiety.com/files/2014/05/lamborghini-aventa...

I tried a few images, for all of them "woman" was the first result (only one image had a woman in it).

Combine this with a Markov Chain and you get a nice story teller.

Try typing in

A python stacktrace about JSON

what the hell, i tried a few images from unplash and it worked flawlessly. how does this magic work?

i've tried maybe 30 images now. All of them it nailed. i did find one that made me laugh. it doesnt know what a goat is.

http://picjumbo.com/wp-content/uploads/IMG_9454-1300x866.jpg

["dog", "australia", "deer", "bear", "cow", "mouflon", "lemur", "wild", "safari", "zoo"]

or a horse apparently. Did figure the jockey though...

http://plocp.com/user/Aram%20Comjean//The%20Belmont%202007/i...

["race", "beach", "camel", "rodeo", "jockey", "polo", "toreador", "torero", "donkey", "dog"]

They must have an army of trolls who are typing in tags.

wow this is really cool! how is this done?! what kind of sorcery is this?!

pretty impressive!

Reply on news.ycombinator.com