New Ranking Methodology for Google Image Search
The New York Times is reporting on a new research paper about Google’s new image ranking algo which apparently associates an inferred linking relationship between images and uses the PageRank method of iterating ranking values across the graph to come up with final ranking values. This “VisualRank” method was presented in a paper at the International World Wide Web Conference in Beijing this past Thursday, and the process was also reported at Techcrunch.
Google’s advancements in Image Search
could help keep high-value image results
like this coastal pic stay high in the SERPs
for apropos keywords, while making less-
important images rank far lower.
The new methodology is apparently very adept at weeding out less-important and less-useful images from the search results.
I have earlier reported on Google’s research into Supervised Multiclass Labeling (”SML”) which can assist with associating keywords with the actual content found within digital images. See also Search Engine Land’s article on Google’s VisualRank Paper.
Popularity: 8% [?]
Posted by Chris Silver Smith of Netconcepts on 04/28/2008 | Permalink | 
Email
| 
Print
Possible Related Posts
Trackback | Comments (0) | Comments RSS |
Filed under: Google, Image OptimizationGoogle, image-search, Image-Search-Optimization, VisualRank
New Results Filtering Parameter for Google Image Search
The Google Operating System blog reported this past weekend that Google Image Search introduced a new parameter that can allow you to pull up only images of people’s faces or only images from news sites/stories.
Popularity: 3% [?]
Posted by Chris Silver Smith of Netconcepts on 05/29/2007 | Permalink | Email
| Print
Possible Related Posts
Trackback | Comments (0) | Comments RSS |
Filed under: GoogleGoogle, image-search
New Research Could Improve Google Image Search
New research recently published out of University of California - San Diego could allow Google’s Image Search to easily begin using elements from “true image search” — that is, the ability for software to detect and identify elements appearing within the image itself rather than just relying upon external text metadata to associate keywords with the images. Read on for more details.
Popularity: 4% [?]
Posted by Chris Silver Smith of Netconcepts on 04/05/2007 | Permalink | Email
| Print
Possible Related Posts
Trackback | Comments (0) | Comments RSS |
Filed under: Google, Image Optimization, Research and Development, SearchingGoogle, Google-Image-Labeler, Google-Image-Search, image-search, Supervised-Multiclass-Labeling
Flickr Adds Geotagging Features
In a move that proves that the people behind flickr are still channeling the Web 2.0 mass conscious, flickr announced this week that they’re adding Geotagging features to their already-robust suite of image management products.
As you may recall, I previously blogged a bit about the rise of geotagging, particularly geotagging of photos, and I had said that it seemed to be a really strong idea with a lot of potential uses. It’s gratifying to see that a service like flickr (and a company like Yahoo!) also believes that it will be strategically beneficial.
The number of people who have been geotagging or who even know about it is likely a relatively low percentage of the online populace, I’d guess (partly for the reason that most people don’t have a GPS device to tell them a location’s longitude and latitude). Now that a top-ranked photo site is supporting it expressly, droves of users will become educated about it, and experiment with it. By doing this, flickr is propelling the trend into the mainstream, increasing the likelihood that it’ll be more widely adopted.
Flickr’s new geotagging utilities were built by mashing-up their image management utilities with Yahoo! Maps, allowing users to drag pix onto a mapped location of where the image was taken in order to associate the photo with the geotag. Also, it appears that users could now use a graphic map as a navigational interface to browse geographic locations and then pull up any publicly-available photos associated with that location. Read on for more info.
Popularity: 10% [?]
Posted by Chris Silver Smith of Netconcepts on 09/01/2006 | Permalink | Email
| Print
Possible Related Posts
Trackback | Comments (6) | Comments RSS |
Filed under: Content Optimization, Image Optimization, Local Search, Local Search Optimization, Maps, Yahooflickr, GeoTagging, geotags, image-search, images, Yahoo
