Friday, April 27, 2012

ACM International Conference on Multimedia Retrieval (ICMR) 2012

ACM International Conference on Multimedia Retrieval (ICMR) 2012
June 5-8, 2012, Hong Kong
Kowloon Shangri-La Hotel &
Run Run Shaw Creative Media Centre, City University of Hong Kong
Multimedia computing, indexing and retrieval continue to be one of the most exciting and fastest-growing research areas in the field of multimedia technology. ICMR is the premier conference in the area of multimedia retrieval, offering opportunities for the exchange of ideas between researchers, practitioners and potential users of multimedia retrieval systems. The conference, puts together the long-lasting experience of former ACM CIVR and ACM MIR series, was set up to illuminate the state of the art in multimedia (including image, video and audio) retrieval.
ICMR 2012 offers the following highlights:

Three keynote speeches
- Cortically-coupled computing for media retrieval, by Paul Sajda from Columbia University, USA
- Aggregating local image descriptors for large-scale image retrieval and classification, by Cordelia Schmid from INRIA LEAR, France
- The road to pervasive multimedia search and multimodal interaction, by Hsiao-Wuen Hon from Microsoft Research Asia, China.

Three tutorial sessions
- Foundations of large-scale multimedia information management & retrieval, by Edward Y. Chang from Google Research, and Chih-Jen Lin from National Taiwan University
- Music information retrieval, by Markus Schedl from Johannes Kepler University, and Masataka Goto National Institute of Advanced Industrial Science and Technology.
- 3D Video Segmentation, Recognition, and Retrieval, by B. Prabhakaran from University of Texas at Dallas

Five regular oral sessions
- Annotation and classification
- Fresh views on multimedia retrieval
- Near-duplicate and copy detection
- Machine learning and hashing for multimedia retrieval
- Best paper session

Two special sessions
- Social events in Web multimedia
- Socio-Video Semantics

Practitioner Day including a keynote, project demonstrations, industrial sessions, panel discussion

ICMR 2012 Website:
Technical Program:

Friday, April 20, 2012

Study on Distortion of Image and Video Thumbnails

Due to the highly diverse availability of digital cameras and camcorders with different input resolutions computer systems need to manage images and videos with different aspect ratios (e.g., 4:3, 16:9, 16:10, etc.). Therefore, developers of large-scale image and video browsing and retrieval tools need to find a way of either presenting all thumbnails with their correct aspect ratio, which often conflicts with a harmonic visualization, or to crop or distort thumbnails to one specific aspect ratio. In the paper "A Visual Search User Study on the Influences of Aspect Ratio Distortion of Preview Thumbnails" (to be presented at the International Workshop on Advances in Large-Scale Multimedia Data Collection, Mining and Retrieval at ICME 2012), the authors (David Ahlström and Klaus Schoeffmann) present results from a user study on the influence of aspect ratio distortion on visual search performance. The results show that even heavily distorted thumbnails do not notably influence visual search time or error rate. A preprint of the paper is available here.

Monday, April 16, 2012

BMVA Computer Vision Summer School

The British Machine Vision Association (BMVA) runs an annual Summer School in Computer Vision aimed principally at PhD students in their first year, but which is potentially beneficial to other researchers at an early stage in their careers, or those who need to find out about Computer Vision very quickly.

The 2012 Summer School will take place at the University of Manchester between the 25th and 29th June.  It will consist of an intensive week of lectures and lab sessions covering a wide range of topics in Computer Vision and Digital Image Computing.  Lecturers are researchers from the most active Computer Vision research groups in the UK.  Participants from outside the UK are welcome.

**The registration site for the Summer School is now open.**

To find out more, go to the Summer School web site at or follow the link to the Summer
School pages from the BMVA website:

Monday, April 9, 2012


Article from Congeo

Saturday, April 7, 2012

Image Abstraction in Crossmedia Retrieval for Text Illustration

Image Abstraction in Crossmedia Retrieval for Text Illustration (Filipe Coelho, Cristina Ribeiro) Accepted for the 34th European Conference on Information Retrieval (ECIR 2012).


Text illustration is a multimedia retrieval task that consists in finding suitable images to illustrate text fragments such as blog entries, news reports or children stories. In this paper we describe a crossmedia retrieval system which, given a textual input, selects a short list of candidate images from a large media collection. This approach makes use of a recently proposed method to map metadata and visual features into a common textual representation that can be handled by traditional information retrieval engines. Content-based analysis is enhanced by visual abstraction, namely the Anisotropic Kuwahara Filter, which impacts feature information captured by the Joint Composite and Speeded Up Robust Features visual descriptors. For evaluation purposes, we used the well established MIRFlickr photo collection, with 25,000 photos and user tags collected from Flickr as well as manual annotations provided as image retrieval groundtruth. Results show that image abstraction can improve visual retrieval as well as significantly reduce processing and storage requirements, even more when paired with Google's WebP image format.
We conclude that applying a visual rerank after an initial text retrieval step improves the quality of results, and that the adopted text mapping method for visual descriptors provides an effective crossmedia approach for text illustration.

Read more


Thursday, April 5, 2012

Image Processing and Computer Vision Updates in MATLAB R2012a

MathWorks shipped R2012a right on schedule earlier this month. (Normally, the "a" release ships in March and the "b" release ships in September.) There's a lot to look at in the new release. Today I'll summarize the enhancements in the Image Processing Toolbox, the Computer Vision System Toolbox, and the Image Acquisition Toolbox.

Image Processing Toolbox Enhancements

Version 8.0 includes these enhancements.

Intensity-Based Image Registration

The new imregister function lets you automatically align two images using intensity values, even when the images were created by two different devices (multimodal). With intensity-based registration, you do not need to specify control points.

You use the new imregconfig function to create the optimizer and the metric that imregister uses to specify the desired registration parameters.

Two New Functions to Visually Compare Images

The toolbox includes two new functions for visually comparing images: imshowpair and imfuse.

imshowpair creates a composite of two images and displays them in a figure.

imfuse creates a composite of two images and returns a third image that is a numeric matrix containing a fused version of the original images.

Circle Detection Using the Circular Hough Transform

The new imfindcircles function uses the Hough transform to find circular elements in grayscale, RGB, or binary images. To view the circles that have been detected, overlaid on the original image, use the viscirclesfunction.

Performance Improvements

The performance of the imlincomb function has improved by taking advantage of multicore capabilities.

New and Updated Demos

The toolbox includes these new and updated demos.

  • Registering Multimodal MRI Images (ipexknee)
  • Finding the Rotation and Scale of a Distorted Image (ipexrotate)
  • Measuring the Radius of a Roll of Tape (ipexradius) – Updated to use the new imfindcircles function

Computer Vision System Toolbox

First, I want to note that, as R2012a, the Computer Vision System Toolbox no longer requires the DSP System Toolbox or the Signal Processing Toolbox.

Version 5.0 includes these enhancements.

Audio Output Sampling Mode Added to the From Multimedia File Block

The From Multimedia File block now includes a new parameter, which allows you to select frame- or sample-based audio output. If you do not have a DSP System Toolbox license and you set this parameter for frame-based processing, your model will return an error. The Computer Vision System Toolbox software uses only sample-based processing.

New Viola-Jones Cascade Object Detector

The vision.CascadeObjectDetector System object uses the Viola-Jones algorithm to detect objects in an image. This detector includes Haar-like features and a cascade of classifiers. The cascade object detector is pretrained to detect faces, noses and other objects.

New MSER Feature Detector

The detectMSERFeatures function detects maximally stable extremal regions (MSER) features in a grayscale image. You can use the MSERRegions object, returned by the function, to manipulate and plot MSER features.

New CAMShift Histogram-Based Tracker

The vision.HistogramBasedTracker System object uses the continuously adaptive mean shift (CAMShift) algorithm for tracking objects. It uses the histogram of pixel values to identify the object.

New Integral Image Computation and Box Filtering

The integralKernel object with the integralImage and integralFilter functions use integral images for filtering an image with box filters. The speed of the filtering operation is independent of the filter size, making it ideally suited for fast analysis of images at different scales.

New Demo to Detect and Track a Face

This release provides a new demo, Face Detection and Tracking. This example shows you how to develop a simple face tracking system by detecting a face, identifying its facial features, and tracking it.

Improved MATLAB Compiler Support

MATLAB Compiler™ now supports detectSURFFeatures and disparity functions.

Code Generation Support

The vision.HistogramBasedTracker and vision.CornerDetector System objects now support code generation. See About MATLAB Coder for more information about code generation.

Image Acquisition Toolbox Enhancements

Version 4.2 includes these enhancements.

GenTL Support for GigE Vision, USB, and FireWire Devices

A new adaptor type, GenTL, is now available for GigE Vision, USB, and FireWire cameras.

Windows 64 Support on DCAM

The DCAM adaptor support is now extended to 64-bit Windows®.

VideoDevice System Object

The Image Acquisition Toolbox™ introduces the VideoDevice System Object, which allows single-frame image acquisition and code generation from MATLAB.

You use the imaq.VideoDevice function to create the System Object. It supports the same adaptors and hardware that the videoinput object supports; however, it has different functions and properties associated with it. For example, the System Object uses the step function to acquire single frames.

For more information on using the System Object, use this command in MATLAB:

help imaq.VideoDevice

From Video Device Block Enhancements

Several enhancements have been added to the From Video Device block for doing image acquisition in Simulink. Options for setting color space and Bayer Sensor Alignment are now included in the block properties.

New Hardware Support – National Instruments

Support has been added for additional National Instruments® hardware.

  • PCI-1433
  • PXI-1435
Test Suite for Third-Party Adaptor Developers and Camera Vendors

As part of the Image Acquisition Toolbox Adaptor Kit, we now offer a test suite for third-party adaptor developers and camera vendors to test adaptors and hardware against the toolbox.

DCAM Adaptor Improvement

Support has been added for strobe outputs to the DCAM adaptor on Windows.

Linuxvideo Adaptor Improvement

Improved support has been added for V4L1 cameras with the linuxvideo adaptor when using the V4L1 compatibility library provided by the libv4l project.

Original Article

Instagram for Android Downloaded More Than 1 Million Times in 24 Hours

As expected, the long-awaited Instagram for Android has proved to be a big hit, netting more than 1 million downloads before the app had been out for 24 hours.

Stats from Google Play peg the number of downloads between 1 million and 5 million, a wide target. By the time the app went live on Tuesday, some 430,000 people had preregistered for the app via a signup page that Instagram had created on March 25.

There had been a huge pent-up demand for the Android version of Instagram. Though Android now has more than 50% market share of the smartphone market in the U.S., Instagram had only been available to iOS since October 2010.

Since that time, Instagram has topped more than 25 million users according to estimates, making it the largest mobile-based social network in the world.

Despite the enthusiasm for the Android version, we found some notable differences between it and the iPhone iteration. For instance, the app lacks some of the iPhone version’s image editing features — most importantly tilt shift, which allows you to focus on one area of the photo while distorting the rest of the image.

However, the Android version does have one feature its iPhone counterpart lacks: “Advanced Camera.” When you turn this on, it will automatically resize your photo, so you don’t have to recrop the image in Instagram’s interface. In the iPhone version, you can only resize or crop if you select a photo from your photo library

Original Article

Monday, April 2, 2012

Google Maps 8-bit for NES and Google Fiber Bar

Google Maps is now available for 8-bit Nintendo Entertainment Systems (NES). Availability in Google Store is TBD but you can try it on your browser by going to and clicking "Quest" in the upper right hand corner of the map.

Google Fiber Bar

Google Fiber starts with 100 times more fiber than any source of fiber available today. Tested in labs across our Mountain View campus, we found that in just the right synthesis, psyllium and vitamins C and D morph into a byproduct we have coded as Fiberlicious. This smarter fiber delivers just what the body needs to sustain activity, energy and productivity up to 100 times more than you have experienced before.


PhotoScanner converts a simple camera to a scanner. This program is applied mainly to text documents, where the text is more visible. For better performance locate the sheet or book for scanning over a dark surface. Any suggestions, feedback and comments are welcome and helpful for further project development.