Category: Internet Vision

Pornographic Image Recognition Software Employed by Chinese Government

These days online discussion grows regarding Chinese government’s deployment of Green Dam Censorware System, a piece of software aiming at blocking adult content or political content-sensitive websites. It is mandated that every computer that will be sold in China after July 1st, 2009 needs to install this software.

The part I am interested in is its pornographic image recognition engine, developed by Jinhui Technologies in Zhengzhou. Pornographic image identification is an interest computer vision application. How does this work?  Read more »

Unconstrained Face Recognition with User Interaction

Face recognition in unconstrained environment is very challenging due to the variations in facial expression, face pose, light condition and occlusion (e.g. eye glasses or hair). A recent project led by Dr. Learned-Miller at University of Massachusetts, Amherst, published the test results on 13,000 images of faces collected from web. The results are described in an ROC curve. At 10% false positive rate, the best true position rate (recognition rate) is around 67%. That is, in 100 face images for one person, only 67 faces are correctly recognized as this person; in 100 faces images of other persons, 10 faces are incorrectly recognized as this person. Therefore there is still big gap between this performance and the requirements of security applications, for example, access control. But are these results useful for other practical applications?  

Read more »

Smart Video Thumbnail Comes to YouTube

After you upload a video to YouTube, one thumbnail image will be displayed linking to your video. A thumbnail image is usually small but it is very important. It delivers the first visual impression of your video to audience browsing millions of videos on the web. 

How does YouTube generate thumbnails for videos?

Read more »

Video Analytics Driven Video Advertising by Digitalsmiths

Digitalsmiths is an intelligent video advertising start-up driven by visual and speech analysis of video content. It is different from ZuraVision, which embeds visual advertisements into videos. Digitalsmiths serves as an information extraction procedure by video content analysis. The extracted information is called “metadata”. How the metadata is used for ads dispatch and how the ads are embedded into videos are the tasks of video publishers. 

According to Digitalsmiths, their technology:

  • Indexes video with an unprecedented sense of context, nuance and intelligence
  • Generates powerful metadata based on visual, audio, text and speech recognition
  • Gives video publishers the ability to search, retrieve, publish and monetize content 

Read more »

Pictures about Bush You Haven’t Seen in Public

Celebrity such as George W. Bush always shows smiling face and confident spirit to the public. Are you curious about what he looks like when he is angry or frustrated, or his mask when he attends friends’ Halloween parties?

Here is a collection of Bush’s faces you have no chance to see in public, with different facial expressions, facial makeovers, tattoos, funny expressions, and change of ethnicity, age, attractiveness and even gender. 
Read more »

Apple’s iPhoto vs. Google’s Picasa: Technology and Strategy

With the closure of Macworld’09, Apple unveiled enhanced iPhoto software with facial recognition. iPhoto allows to keep track of your photos by “who, where, and when” with facial recognition and Geo-tagging. It also allows to enhance/edit your photos and share them online or in print. 

Each piece of the software is not new, for example, Google Picasa released their facial recognition feature on early September of 2008. How could Apple’s iPhoto compete with Google’s Picasa, considering Picasa is totally free to end users? Steve Jobs again fully leverages his vision and Apple’s strengths in technology (Human-Computer Interaction – HCI and Computer Vision) and System Integration for business.
Read more »

Video Advertising: More Intelligent With Computer Vision Technology

Online video advertising combines a video and an advertising image/video

Nowadays almost all online ads are based on keywords extracted from text of a page, finding the most relevant ads and putting them up alongside the page, such as AdWords by Google. Can we have “Video AdWords” extracted directly from online videos?

Read more »

Embed Visual Ads into Videos

ZuraVision is a website on embedding pictures or videos into a video using the computer vision technology developed by Stanford students. 

One immediate application of ZuraVision is to embed visual advertisements into the video. As Google AdSense do for text advertisement, ZuraVision may bring you new opportunities to monetize your video (e.g., on YouTube) in the near future.

The image on the left was cropped from a video embedded with our “VisionWang” logo, giving a realistic perspective.  

Read more »