Google and Microsoft Image Search by Content

Image search is going to an era of search-by-content (such as color, shape, texture, style, objects, etc) instead of search-by-text-context, as described in one of our previous posts, Visual Search Engines: The Future Seach Engines. Following Microsoft’s release of image search by content (color, style (illustration or photograph), or face) at the beginning of this month, Google today also announced their image search product by style (Clip art, Line drawings, and Photo content). I am happy to see more and more computer vision technologies are used in leading search engines.  

Read more »

Augmented Reality for Home Furniture Placement

In one of my previous post, Future iPhone Applications on Image Recognition, I talked about one of future computer vision applications, Virtual Shopping, by designer Mac Funamizu


An article today was posted by Joshua Koopferstock from Enlighen3D (blog of Feeling Software) releasing their product of Constructive 3D Furniture. It requires users to input two pictures of a room, and some parameters (such as three corresponding points and height of ceiling). Their algorithm will then automatically compute the pseudo-3D model (plane perspectives) of the scene. User can place 3D models of any furniture into the scene to see the effects.

 

Read more »

Adobe and Microsoft Competing on Next Generation Home Video Editing

Video editing for special visual effects will no longer be the privileges of video professionals. Recently, Adobe Research and Microsoft Research released their own advanced video editing features. Computer vision technologies have been extensively exploited in the two works. 

As more and more people have digital camcorders at home, easy-to-use “Videoshop” is expected to become a useful tool, as people rely on Adobe Photoshop for editing photos nowadays. Home video editing software has a huge potential market that Adobe and Microsoft are targeting.

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 »

Future iPhone Applications on Image Recognition

What are the future iPhone applications on computer vision?  Mac Funamizu, a graphic designer, came up with a set of new concept of using computer vision and image recognition techniques for Future Mobile Search. This is a perfect add-in to our previous post: Mobile Vision: iPhone Apps Employ Computer Vision and Image Processing Techs.

The future mobile search exploits advanced human computer interaction using build-in camera, fingers and touch screen, powerful capabilities of google search and google map, and the cutting-edge technologies in computer vision and image recognition, and brings engineers great inspiration and opportunities as well. 

Read more »

Mobile Vision: iPhone Apps Employ Computer Vision and Image Processing Techs

There are around 10,000 applications from third-party developers for Apple iPhones by the end of 2008. Among them, there are a number of camera/photo-related applications for you to play with. You will be amazed by how computer vision and image processing technologies could deliver you astonishing visual effects and fun, even with a 2MP mobile camera. Some of them offers a set of image editing functionalities like Adobe Photoshop,  such as image enhancement, image filtering, image/video editing, etc. Others use more advanced and complex computer vision technologies, such as object detection/recognition and image retrieval. Here we will review some of the top computer vision apps for iPhone and their core technologies.

 

 

Read more »

Holiday Season Gift Ideas (1): 3D Greeting Cards

It is holiday season. Have you got a good idea to send a surprise gift to your love or your friends? Have you thought about computer vision and graphics technologies could help?

Snapily recently came up with a brilliant idea for your holiday gifts by using computer vision and graphics technologies. Users can upload your pictures, choose one of the special effects (3D, Morph or Flip) and have moderate user interaction, a customized card will be ready for you. Here is an overview of this technology.

Read more »

Best Visual Search Engines Review: (3) GazoPa

GazoPa is another image based visual serch engine (still in Beta). It is owned by Hitachi, Japan. Users can search similar images on the web based on image color, shape or faces. Similiar to Like.com, but GazoPa has interest of general objects rather than only commercial products. Different from TinEye, GazoPa does not focus on finding the same images.

Let’s first watch an overview video of GazoPa.

Read more »

LA Wildfire Could be Prevented by Video Fire Detection

The Los Angeles wildfire these days has destroyed about 200 multi-million-dollar celebrities’ homes along with 600 mobile homes, and is continuously sweeping the area near the Los Angeles National Forest.

In such a wide open area, the traditional fire and smoke detector used in a building usually do not apply here because it requires the smoke particles reaching to the detector before an alarm, resulting a significant latency. It is also not practical to install huge amount of detectors in a large open space.

Thanks to the recent computer vision technology in video fire detection, it enables large area monitoring with instant alarming system, with the help of volumetric sensors (cameras) and intelligent video analytics software. Mostly importantly, existing video surveillance infrastructure (cameras and network) can be leveraged for this application. 

Read more »

Best Visual Search Engines Review: (2) Like.com


Like.com is one of the earliest visual search engines. It starts from another visual search engine called Riya, which was originally used to search celebrity people, objects in the pictures, and faces in the photos. From the profitability point of view, like.com now changes its business model to high-end online shopping based on visual search. 

The first thing I would like to talk about is like.com’s business model. There are always cool computer vision technologies. However, how to leverage the technology to make profit is a different thing. Like.com is undoubtedly a good model for visual technology entrepreneurs. Visual search is high-tech, and online shopping is something popular and something you can make profit from. The marriage of high-tech search engine with online shopping will undoubtedly bring you venture capital and eventually gain profit for you. 

Read more »