Google takes a visual search
Subject image search already raised in these pages, when the company considered Photodate, Developers who have And Idee Piximilar. Now come to the heavyweights.
Google will face Yushi Jing and Shumeet Baluja conference WWW2008, held April 21-25, 2008 in Beijing has demonstrated its development (link to PDF, 3,4 Mb), able to analyze the images not only by name, as it was before, but the quality, relevance and most importantly - content.
Now search for images in Google images work on the basis of the text, as well as searches on file names. And as the name can be assigned arbitrarily, depressing picture of the issue and fun. Try entering the query . You will find on the first page of photos of fat giraffes, fat women and fat children, which, of course, has no direct relation to the request.
Our approach relies on the analysis of the distribution of visual similarity among images.
The premise is simple: by a Web page is likely to choose the images that, with his or her opinion, are relevant to your topic. Instead of assuming that every user who has a web page, a relevant request, will provide a link to an image on the page of another user, our approach relies on the analysis of the combined preferences of many of the creators of the content network.
The new image search on Google will work on the basis of the so-called "visual themes", which can be explained as meaning the image center.
For example, to illustrate many of the images contain a familiar character «M». Some emblem - the main center of the image, while in others it occupies only a small part. Nevertheless, its recurrence in a large fraction of images - an important signal that can be used to deduce the overall "visual theme" throughout the set. The discovery of multiple visual themes and their relative strength in a large set of images - image based ranking system proposed in this study.
Like the Page Rank (PR), introduces the concept of Image Rank, IR. Formula Image Rank is defined as:
where S - the normalized matrix of similarity (normalized, symmetrical adjacency ma -
trix) images, such as S u, v denotes the visual similarity between images u and v.
Google has already demonstrated the operation of its graphical search engine as an example in 2000 the most popular queries in Google images.
The company is close to the submission of the first beta version of a graphical search engine.
Link: (English)
Cross-blog survey: Do you know what a cloud of blogs?
May 4, 2008 at 22:18
Actually it is another hype that up as soon as Google sneeze. If you read this publication, as well as his own statement of the company, it becomes clear that this is only research, and they are still very far from realization. By the way, in contrast to systems that were previously covered in this blog and who have active version of this engine. Likely as a result of Google or Microsoft will buy one of these companies (or all:)), and that's when something goes.
May 4, 2008 at 23:45
Alexis, you are not from Picollator'a?
In my piercing gaze:) engines-publicized earlier in a company blog at the moment far from the ideal of human search.
Ie they look all right (with t.zr. robot): the color match, and shape, but is all wrong.
Just from Google, you can expect something more serious.
All the prerequisites are. In addition, the formula for ranking all prechislennyh systems were not observed, as far as I know, but this is for Google - a priority.
Well, wait and see.