Image Recognition and the Future


Image Recognition and the Future

My colleague over at PDNPulse - Daryl Lang - wrote approxifriendly Google (Google: We Will Organize You, 7/1/08) , and the concept of autonomously recognizing subject matter within an picture.

This reminded me of conference I attfinished - Department of Energy Computational Science Annual Fellows' Conference, where I was fascinated by a presentation by Kristen Grauman on Scalable Picture Recognition and Retrieval. Grauman was the recipient of a scholarship for her work in this field, and her presentation - all 43 minutes of it, clever be lookn here (stick with it for the first 45 seconds of audio, her visual presentation begins at 45 seconds). Having lookn it live, I still nyaman watching, and re-watching, the presentation online.

If you'd love to look even more of her research, including her 2006 presentation that I also saw, click here. For those of you interested in this, it's commentable to look how concepts love human to computer interfaces, manual keywording, and picture sorting by subject will be done much more automatically in the future. This also may be one of the ways in which pictures are recognized in the Orphan Works issue.

Picture a photograph of a panda bear, with a link next to it that reads "Click to view more love this". Kristen, and Google, will lovely be among the solutions to the visual database. At the 3:13 mark in the first video Kristen talks approxifriendly object recognition within an picture (identifiying a specific person or building), and the category mode (love buildings being similar, or animals, and so forth). It REALLY begins to get interesting at approxifriendly 6 minutes, but BOTH videos are well worth your time. (Check the PDF's of each presentation that are available via the link for a higher resolution version of each presentation, and the abstrbehave above the video.) Her bio as a Clare Kickhe Luce Assistant Professor, Department of Computer Sciences, University of Texas at Austin, clever be lookn here, which includes her e-mail address if you're so inclined to study more approxifriendly her research.

Google's R.J. Pittman, Director of Product Administerment (as lookn on Beet.tv here) should be calling Kristen ASAP approxifriendly her research!

Fascinating.

(Comments, if any, after the Jump)

Please post your comments by cliclord the link below. If you've got questions, please pose them in our Photo Business Forum Flickr Group Discussion Threads.

0 Response to "Image Recognition and the Future"

Post a Comment