It appears you have not yet registered with our community. To register please click here...

 
Go Back [M] > Madshrimps > WebNews
Google improves machine vision Google improves machine vision
FAQ Members List Calendar Search Today's Posts Mark Forums Read


Google improves machine vision
Reply
 
Thread Tools
Old 25th July 2013, 06:33   #1
[M] Reviewer
 
Stefan Mileschin's Avatar
 
Join Date: May 2010
Location: Romania
Posts: 124,716
Stefan Mileschin Freshly Registered
Default Google improves machine vision

Researchers at Google have come up with a machine vision technique which could bring high power visual recognition to simple desktop and even mobile computers.

IProgrammer said that the system can recognise 100,000 different types of object within a photo in a few minutes.

Google appears to have made improvements to the fairly standard technique of applying convolutional filters to an image to pick out objects of interest.

This is tricky because the filters needs a sample of at least one per object type. If you are scanning Facebook for cats you need a filter which finds cats, so the method is limited to a small number of categories - otherwise you need a huge database.

A report, co-authored by Googlers Tom Dean, Mark Ruzon, Mark Segal, Jonathon Shlens, Sudheendra Vijayanarasimhan and Jay Yagnik, describes technology that speeds things up by using hashing.

Locality sensitive hashing looks up the results of each step. Instead of applying a mask to the pixels and summing the result, the pixels are hashed and then used as a lookup in a table of results.

They also use a rank ordering method which indicates which filter is likely to be the best match for further evaluation.

The result of the change to the basic algorithm is a speed up of roughly 20,000 times faster. Using 100,000 object detectors, which required over a million filters to be applied to multiple resolution scalings of the target image, the set up recognised an object in less than 20 seconds. The hardware involved was a single multi-core machine with 20GB of RAM.

http://news.techeye.net/science/goog...machine-vision
Stefan Mileschin is offline   Reply With Quote
Reply


Similar Threads
Thread Thread Starter Forum Replies Last Post
Google uses computer vision and machine learning to index your photos Stefan Mileschin WebNews 0 24th May 2013 07:41
Google Glass' vision of the future runs on a 2011 smartphone chip Stefan Mileschin WebNews 0 29th April 2013 09:05
Samsung improves DRAM Stefan Mileschin WebNews 0 6th July 2012 06:56
Dell improves bid for Quest Stefan Mileschin WebNews 0 27th June 2012 07:45
iOS 6 Improves Call Handling Stefan Mileschin WebNews 0 12th June 2012 06:55
Google MapsGL updates 3D buildings, improves virtual tourism Stefan Mileschin WebNews 0 30th April 2012 08:18
Microsoft removes VM hardware requirements, improves XP mode jmke WebNews 0 19th March 2010 07:14
IntelBurnTest v1.9 Further Improves PC Stability Testing jmke WebNews 6 11th March 2009 07:06
AMD Improves Price-Performance Ratio of Its Chips jmke WebNews 0 9th April 2007 20:56
Sony Improves Recording Accuracy And Compatibility For DVD Media jmke WebNews 0 22nd December 2004 09:17

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are On
Pingbacks are On
Refbacks are Off


All times are GMT +1. The time now is 13:01.


Powered by vBulletin® - Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO