Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

news.ycombinator.com

Post reply on HN
Print view View original

21–30 of 52 posts

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#21

Post by zo1 »

beagle3 wrote: post #13

I'm interested in good OCR, preferably local, but I'm close to giving up and using Google Cloud Vision API --- It works well for text that's not prefectly aligned and laid out - unlike e.g. Tesseract or any other local OCR I've used. As far as I can tell, clarifai.com doesn't have OCR, and neither does anyone else except MS and G.

Have you had a look at the ABBYY offerings? They work very well with auto-skew detection + correction. But of course, it's a very pricey solution and wouldn't recommend it if you don't have the budget for that sort of thing.

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#23

Post by chris_st »

ismdubey wrote: post #22

When I checked last, Google API does not allow to identify specific faces. It can detect faces but that's it. Clarify or Microsoft do. Pricing wise almost all are the same. In my view, Watson is a complete no no..

Just curious, what makes you say that about Watson?

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#24

Post by rememberlenny »

JoshTriplett wrote: post #12

OpenCV includes face detection, and given a reasonably limited corpus of faces, it performs quite well and quite reliably. (Whether you want to use that or use a service depends on how close to your core business this is.)

I would add to this comment. I recently thought face detection was a difficult service, but its actually really easy to implement yourself.

I found these really useful: http://www.pyimagesearch.com/

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#26

Post by Negative1 »

wstrange wrote: post #6

Interesting looking at Google's Vision API overview, where they explicitly state that facial recognition is not available. The technology to do this clearly exists, but I gather they are concerned about the potential for abuse. Which makes sense. You could build some very creepy apps with this.

I won't directly speculate but I doubt the Face Detection functionality is absent due to some ethical quandary.

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#27

Post by Eridrus »

malux85 wrote: post #3

Depends on the complexity of what you require. I know I might get down-voted for this, but if your task is relatively simple, then roll your own using deep learning. Message me if you want help with this. I wouldn't rely on either for my own startup, because I dont think these API's will have broad appeal, as a result wont get traction, and will be shutdown with little warning. I could help you if you want - my email…

I've had a surprising amount of success rolling my own deep learning vision system too since the community is so open, but I wanted to learn about the field and I've sunk a few weeks of spare time into it at this point so I'm not sure I'd really recommend it to a startup unless the API offerings just don't work for them for performance or cost reasons.

Re: Ask HN: Microsoft Computer Vision API or Google Cloud Vision API?

#28

Post by kevinSuttle »

IshKebab wrote: post #15
kevinSuttle wrote: post #8

What about Watson? http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl...

I don't know about face recognition but I've quantatively analysed their speech recognition and it came dead last after the 5 or so others that I tested.

Yeah, this would be good to share with the team if you have it documented.
Post reply on HN