Google pattern matching

Image Comparison Engines

“CBIR” is the handy acronym for Content based image retrieval. Basically, it means instead of entering text to find images, you provide or click on an existing image to find related ones. This ought to be much more intuitive for certain tasks.

A CBIR research project of Penn State University has now been applied to an aviation images database,Slashdot reports. Click

 on “Show me photos”, and then click on “View similar photos” to get an idea of how well this works. This is not necessary related to actual image recognition (analyzing a picture to find out it contains, say, an elephant), but can be implemented using much more brute force pixel-by-pixel image comparison with some added mirror and scaling fuzzyness.

If Google or Yahoo would add this feature to their image search, they’d have an immediate killer advantage to other image searches – and lawyers hunting down copyright infringements would have a new powerful tool at their hands.

Or... did Google already have this in place? One reader by the nick of Chefmonkey at Slashdot comments:

“Google actually did take this technology and try it. The first version of their image search had a “find similar” link next to every image. These tended to work okay at first (they weren’t great, but you usually got enough photos back that you could visually scan them and find something of interest that was related to the original image). After a few months, for some reason, the “find similar” links started returning increasingly nonsensical results. After it degenerated to the point of near uselessness, they took the “find similar” link away from the image search results. I expected it to turn up again once they got the kinks worked out, but apparently they just decided to stop working on it.”

Google returns the results....

If you search for …	Google won't find …
cheap	inexpensive
tv	television
effects	influences
children	kids
car	automobile
Calif OR CA	California

Note: There are exceptions when Google finds pages that include synonyms of your search terms, which are displayed in a boldface typeface in Google's snippet.

If you search for …	Google finds …
NYC	New York City
SF	San Francisco
GNP	Gross National Product

3. Similar Words Match

Google returns pages that match variants of your search terms.

The query [ child bicycle helmet ] finds pages that contain words that are similar to some or all of your search terms, e.g., “child,” “children,” or “children's,” “bicycle,” “bicycles,” “bicycle's,” “bicycling,” or “bicyclists,” and “helmet” or “helmets.” Google calls this feature word variations or automatic stemming. Stemming is a technique to search on the stem or root of a word that can have multiple endings.

If you only want to search for pages that contain some term(s) exactly, surround each such word or phrase with quotation marks (" "). See Quoted Phrases and Quotation Marks Replace the + Operator.

Google doesn't match variants when your query consists of a single term.

Note: When you want synonyms or variants that Google doesn't find, consider using either the ORor tilde operator.

4. Stop Words

Some common words, called “stop words” (such as the, on, where, how, de, la, as well as certain single digits and single letters) generally don't add meaning to a search.