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 »

SIGGRAPH 2009 Papers Unveiled

SIGGRAPH 2009 accepted papers are coming out. Totally 78 papers out of 439 submissions are accepted (acceptance rate: ~18%). Congratulations to the authors. Many researchers can not stand waiting long time to post their works online. Thanks to Ke-Sen Huang, he maintains a very nice website of accepted papers.

There are several interesting observations:

  Read more »

Camera-Assisted Digital Painting with Virtual Brushes


These two pictures were taken on the roadside of the Strip Street in Las Vegas from my recent trip. The first picture was painted with less than 10 minutes by the artist in the second picture. Very impressive! 

Could computer vision technology be used for creating digital arts? 

Read more »

Image Search by Image Similarity by Google

Congratulations to the Computer Vision Team at Google Labs! Google finally releases image search based on image similarities. 

Let’s review the different stages of image search:

  Read more »

Video Analytics Category Award Goes To BRSLabs At ISC West 2009

Winners of the 2009 Security Industry Association New Product Showcases (NPS) were announced yesterday at ISC West 2009. The video analytics category award goes to Behavioral Recognition Systems (BRS)  for AISight.

In contrast to traditional video analytics software, such as ObjectVideo , ioimage , Lenel , BRS does not need users to draw tripwire or region of interest (ROI) and define the rules. It uses a machine learning based approach to adaptively learn what behaviors or activities are "normal" in the scene, and issues alarms when finding some anomalies.  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 »

VeinViewer: Computational Imaging Makes Needlesticks Easier

Have you experienced being poked several times for your nurse to find your vein for an IV insertion?

Blood collection from children is an extremely difficult task because of their thick skin. The VeinViewer by Luminetx® can help. The VeinViewer utilizes near infrared (NIR) imaging and image processing technologies to assist health care professionals to find veins easier. 

The following video is a brief report on VeinViewer from ABC.
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 »

FashionLatte: Visual Search Engine for Clothes

FashionLatte is still brewing. FashionLatte is a clothes search engine based on images. It is “a one-stop shop for your daily cup of fashion”. The Co-Founders are three brilliant Ph.D. candidates from Computer Vision and Robotics Lab at the University of Illinois at Urbana-Champaign, i.e., Sanketh, Bernard, and Esther (that is how the company name SanBernest Inc. comes from). 
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 »