UC Berkeley Researchers Create Tool To Average Images

The amount of visual data is growing and it is growing fast. How fast? See for yourself:
Now all that data needs sorting, storage, metadata and other things the Big Data guys know better about. The scientists at UC Berkeley may have found a solution to tame this monster. Their solution is simple: Average the data. Scientists Alexei Effros, Jun-Yan Zhu and Yong Jae Lee developed a software tool to develop an image representing an average of a cluster of images. This tool, named AverageExplorer was presented as a part of paper at SIGGRAPH 2014 conference in Vancouver, Canada.

AverageExplorer makes it easier to analyse 'chains of related images' such as that of brides and grooms at weddings or that of a graduation ceremony. Specific features in images could be given more 'weight' by the user to create subcategories and make sorting easier. The researchers said that potential applications include online shopping, media analysis, sports analysis, etc.

image_average_1
The tool lets users focus on images in which President Obama appears over Stephen Colbert’s shoulder. Users can also observe Colbert’s typical body posture among those results.
Yong Jae Lee further stated that the efficiency of Computer Vision systems in deducing key features from images could be improved using this technique. For example, a face recognition system needs to be trained using lot of data which requires a considerable manual effort. Instead, if the average image is annotated for features (such as eyes, nose and mouth), the effect could propagate down the collection to each individual image.

It is worth to note here that an artist, Jason Salavon has created average images from hundreds of photos of kids with Santa, newlyweds or baseball players to illustrate this concept of 'image averaging'. Check out his amalgamation work on Chicago city's photos taken from the city's typical tourist points #-Link-Snipped-#. But unlike Salavon, the scientists automated the process of aligning and sorting the images.

On a parting note, if we could create an average of a number of averages, we could have an 'image within an image' or an "Inception"-styled image. We could call it 'Im'ception.

Nevertheless, share your views in the comments. Also feel free to bash the author if you thought the 'Im'ception joke was a bad one.

Source: #-Link-Snipped-#

Replies

You are reading an archived discussion.

Related Posts

Quote: The phenomenon of 3-D printing is allowing medical device makers to do amazing things, as showcased by the recent FDA approval of the first 3-D printed facial implant. But...
WhatsApp has been showing the nasty "Failed. Out of memory. Please try again later." error message whenever I send multiple photos to a group or any of my content. After...
Story of a roadside corn roaster and his passion towards technology. ^ Shot by Subhash G.
I am Priya Tanwar pursuing my graduation in IT. Programming skill: Android,Java, C#, vb.net, Haskell, C++, C. Other skill: web development,Photoshop,sketching portraits. Location: India. Work Experience: worked as an intern...
The role of percentage criteria/cutoffs in getting a job and building a successful career. My marks are as follows: SSC 84% HSC 78% B.Tech. aggregate of 8 semesters 57% B.Tech....