What's Happening in This Picture?
It’s a question that human minds can answer instantly in most cases. Show me a photo of nine uniformed men standing on a diamond-shaped field and I’ll tell you, “It’s a baseball game.” Computers have a much harder time answering such questions. But this new technology just might be a breakthrough. Read on to learn more and try it for yourself...
What is Wolfram Image ID?
First, Stephen Wolfram gave us , a “computational knowledge engine” that provides computed answers to natural-language questions instead of merely Web pages that contain some of the words in the questions. Then he developed the Wolfram Language, a programming language that draws much of its power from the algorithms and databases underpinning Wolfram|Alpha.
Now, Stephen has added a simple function to his language, ImageIdentify, that answers the question, “What’s going on in this picture?”
Let's go back to that example of a baseball game. Make it nine little kids instead of grown men, and I’ll refine my answer to, “Little League game.” Such instant identifications are second nature to humans; few of us realize what vast stores of facts and billions of lightning-fast computations are required to pull of this simple feat.
Artificial-intelligence experts know that image-recognition is incredibly complex, and it’s going to be utterly necessary in the future of self-driving vehicles, self-piloting drones, and other autonomous machines. Image-recognition is a problem that people like Stephen Wolfram are very keen to solve.
The ImageIdentify function is a simple way for a programmer to invoke a very complex program that operates on Wolfram|Alpha’s database of several trillion facts. This program has been exposed to over 10,000 “training images” and their associated identities or tags, e. g., “coffee mug.” Given an image as input via the ImageIdentify function, the program returns the tag of the image that is the closest fit to the input image.
You can try the ImageIdentify function on any image you like, at the Wolfram Language Image Identification Project Web site. You’ll also be helping the function expand and refine its knowledge base.
You can drag an image into the project’s input area, or upload an image file from your hard drive. The project will take just a few seconds to analyze the image and return a tag. Then you’ll be asked to rate the project’s performance on a scale labeled “Great,” “Could be better,” “Missed the point,” or “What the heck?!” If your rating is less than “great,” the project will offer second guesses and ask you to tell it what you think the tag should be.
...and All I Got Was This Lousy T-Shirt
Finally, you can leave your email address to be notified when ImageIdentify learns more about “your kind of image” and, more importantly, to be entered in a daily random drawing for an “I taught ImageIdentify” T-shirt. That ought to get you a few “What the hecks?” of your own!
My own tests produced very uneven but not unamusing results. ImageIdentify correctly recognized a flower and even gave me its genus. It deemed me a “person.” An origami fish was a “vertebrate.” ImageIdentify guessed correctly that one photo of a baseball stadium was a "ballpark" but thought that another one was a casino.
The FAQ attributes some bloopers to “training errors.” For example, ImageIdentify may have been trained to associate the word “Chihuahua” with several examples of the dog, one of which was wearing a party hat. So if you upload a picture of a party hat, it may be identified as a “Chihuahua.” Wolfram and company are working on such things.
There are other image-recognition Web sites to which you can compare Wolfram’s ImageIdentify. Their results are generally similar but can be amusing in their own ways. Examples include CamFind, Clarifai, MetaMind, Orbeus, and AlchemyAPI.
I expect this technology to become rapidly better. It has to… we don't want the robotic maid to throw all the chihuahuas in the trash after your kid's birthday party. Your thoughts on this topic are welcome. Post your comment or question below...
This article was posted by Bob Rankin on 26 May 2015
|For Fun: Buy Bob a Snickers.|
Really, a $9 Computer?
The Top Twenty
Geekly Update - 27 May 2015
Post your Comments, Questions or Suggestions
Free Tech Support -- Ask Bob Rankin
Subscribe to AskBobRankin Updates: Free Newsletter
Copyright © 2005
- Bob Rankin - All Rights Reserved
Article information: AskBobRankin -- What's Happening in This Picture? (Posted: 26 May 2015)
Copyright © 2005 - Bob Rankin - All Rights Reserved