Saturday, February 28, 2009


Vision in general and images in particular have always played an important and
essential role in human life. In the past they were, today they are, and in the
future they will continue to be one of our most important information carriers.
Nowadays, image processing and computer vision have numerous commercial,
scientific, industrial and military applications. All these applications result
from the interaction between fundamental scientific research on the one hand,
and the development of new and high-standard technology on the other hand.

In order to cope with the variety of image processing and computer vision
challenges, several techniques have been introduced and developed, quite often
with great success. Among the different techniques that are currently in use,
we also encounter soft computing techniques. Soft Computing is an emerging field
that consists of complementary elements of fuzzy logic, neural computing,
evolutionary computation, machine learning and probabilistic reasoning, and
often offers solutions where conventional approaches fail.

The Workshop on Soft Computing in Image Processing and Computer Vision (SCIPCV)
aims to provide a forum for current state-of-the-art approaches of soft
computing techniques in image processing, computer vision and related

Las Vegas, July 13-16 2009

Tuesday, February 24, 2009

img(Rummager) Update


Change Log

1. Tamura texture feature bug fixed (Thanks to Ben Struss)

Img Retrieval
2. Now you can combine all the data files in an XML file. Select the descriptors you want and create the XML file. (You have to recreate the index files for your databases)
3. Hybrid search. Connect to our server and download the latest available keywords. Then combine the keywords with a visual example images and retrieve images from FlickR. Every week we will update the “available keyword” list. So far 5000 images are available in our server.
4. EHD descriptor bug fixed. (Thanks to Ben Struss)

5. “Lite” and “Normal” Versions are now combined.

Read More And Download

Photo & Video Viewer with Encryption Capability

Article from codeproject


I've tried a few image viewer utilities out there but couldn't find one that really fits my preference, so I've decided to write up one for my own use. I've got all the functionality I need but would like to get input from experts out there on a few issues.

The Problems with Common Image Utilities

  • Load photos as a thumbnail list with no option to switch to simple file name list. This would take forever when the folder contains several hundreds of photos. This is very common when unloading photos taken from a digital camera that has 1GB+ SD card.
  • The thumbnail list would reside in a wide view pane that takes up valuable view space for the main image plus the annoying double click to open a photo in the main view, then close and double click on another.

The Utility Features

There are too many features to list but the general idea is to make the photo list as narrow as possible and the main view as large as possible. Selecting a photo would display it in the main view using the default "Fit to screen" so user can see the whole picture without having to scroll right/down. A photo taken from a 6 mega pixels digital camera is typically 2576 x 1932 resolution. Once a photo is selected, the listview has focus and subsequent photo can be viewed by simply pressing the up/down key to select next/previous file.

Read More

Saturday, February 21, 2009

Moments from Innsbruck

Innsbruck 2009

Saturday, February 14, 2009

Step By Step (15 Years)

FORTRAN code is the same for all platforms (except for the time function and some parallel instructions)
Download a console program for NT (solver of linear system Ax= f) (36KB) or the source (2KB) and compare your CPU's horsepower with the Intel 386, RISC Intel 860 or legendary NeXT station.

Hardware (Software)


AthlonXP 2100+ 1.73GHz (2506MHz) (COMPAQ FORTRAN v6.1)


Intel Pentium 4/2200 (INTEL FORTRAN v6.0 -O3 -QaxW)


Intel Pentium 4/2940 (WATCOM FORTRAN v10.5)


Intel Pentium 4/2200 (COMPAQ FORTRAN v6.6) Windows 98


Intel Pentium 4/2200 (COMPAQ FORTRAN v6.6) Windows XP


AMD Athlon 1200 (COMPAQ FORTRAN v6.1)



Intel 386/20 w 387 (Microsoft FORTRAN 5.0)


View the entire list Here

The Seventh IASTED International Conference on Signal Processing, Pattern Recognition and Applications

This week I will be at Austria (Innsbruck), where the “The Seventh IASTED International Conference on Signal Processing, Pattern Recognition and Applications” takes place. I’ll be there to present 2 papers:

C[1]. S. Α. Chatzichristofis, Y. S. Boutalis and Mathias Lux, “SELECTION OF THE PROPER COMPACT COMPOSIDE DESCRIPTOR FOR IMPROVING CONTENT BASED IMAGE RETRIEVAL.”, «The Sixth IASTED International Conference on Signal Processing, Pattern Recognition and Applications SPPRA 2009» Austria, Accepted for Publication.
C[2]. S. Α. Chatzichristofis and Y. S. Boutalis, “CONTENT BASED MEDICAL IMAGE INDEXING AND RETRIEVAL USING A FUZZY COMPACT COMPOSITE DESCRIPTOR”, «The Sixth IASTED International Conference on Signal Processing, Pattern Recognition and Applications SPPRA 2009» Austria, Accepted for Publication.

Stay tuned for my impressions and the slides.

Image Management is Easier with Image Comparer

Article from

You may have never heard the service of Image Comparer. This is an innovation for use to manipulate a set or a large collection of digital snapshots. You know what, if you have to send to your friends all the large images as they are, they will surely be overwhelmed and consuming a lot of space. Image Comparer helps you find duplicate by automatically functioning as duplicate image finder. It works on content-based image search or known as content based image retrieval.

So, by using Image Comparer, you can refine similar images or pictures you have in your collection. The picture comparison software Image Comparer has, you can easily save the original version of your photos and use the duplicates for publication, sharing and as such. By then, it is going to be very fun for to deal with your photo or image collections because Image Comparer helps you with it.

Wednesday, February 11, 2009 is a stock photo search portal for the creative community. You can quickly browse the way you think – visually - through millions of stock images, vector illustrations, flash files, and videos. Our inventory is from the leading providers, and it’s all searchable in one place.


Article from

Xcavator is a new type of search engine which utilizes visual clues that you provide to identify and extract similar pictures from large groups of digital images. To provide clues you first select a reference image, and then identify within it visual elements that you want to become your visual search query specifications. You do this by clicking one or more individual points on the reference image while excavator samples them and their surrounding are to determine the unique traits, characteristics and visual patterns present in each of the reference points. Then in real-time excavator displays as many "matching" images to your visual specifications as possible.
To note is the fact that you can progressively add new specs and eliminate them while you see corresponding visual matches being displayed on-screen in real-time. This allows the user to quickly learn and understand excavator sensitivity and abilities, making the learning curve rather flat.
Excavator utilizes the enormous and free Flickr/Yahoo digital image library to perform its impressive capabilities.
The one showcased here is only a first release. More advanced functionalities and tools for Excavator will be released in the near future.

Image Processing for Intelligent User Interfaces at IUI’09

Article from eceblogger

Trevor Darrell a distinguished professor from UC Berkeley gave a very interesting invited talk yesterday at IUI’09 on the role of image processing in making user interfaces more intelligent.

He elaborated on the state-of-the-art of image recognition. There are essentially two categories of this field: 1) instance level recognition and 2) category level retrieval. The first category is almost a solved problem, while the second one sill causes headaches to scientists: how could computers recognize that a bar stool and a rocking chair belong to the same category?

Trevor also showed a few new cutting edge technologies that are starting to change our everyday life. For example, the SnapTell application for smartphones can recognize snapshots of book covers, CDs, etc. made with your cameraphone and find the product on the internet. The goal of this program is of course commercial, to sell the items that you are looking for. But such applications can also enable you to find out more about e.g. a new movie, based on a snapshot of its poster or even a TV advertisement.

This idea seems relevant to the work of my colleague, Michael Farrar, at Project54. His photo tagging application could be further improved to enable location, object or even suspect recognition (in the long run) for police officers.

Oszkar Palinko

3rd NISS2009: 2009 International Conference on New Trends in Information and Service Science

NISS stands for INTERNATIONAL CONFERENCE ON NEW TRENDS IN INFORMATION AND SERVICE SCIENCE. It is a premium international conference on all areas related to the Theory, Development, Applications, Experiences, and Evaluation of multidisciplinary and Hybrid/Convergent research with consumer-oriented and service-oriented technologies. In this event, researchers from all around the world can share their experience and knowledge.

Scope and Topics:

Topics of interest are specified on the scope and topics page. High quality submissions are invited for technical papers describing original unpublished results of theoretical, empirical, conceptual or experimental research. Papers should describe a new contribution to NISS and should support claims of novelty with citations to the relevant literature.

Topic1: SC: Service Computing
Topic2: SIS: Service Oriented Information Science
Topic3: CSE: Consumer and Service Oriented Communication, Network and Electronics
Topic4: IMS: Consumer Oriented Information Management and Service
Topic5: ICS: Service Oriented Industry and Convergence Science

Track 1: Research Results

The purpose of the Research Track is to present and discuss the latest, best, most profound, and most important research results in the research field of Multidisciplinary and Hybrid/Convergent researches with consumer oriented and service oriented technologies.

Track 2: Technical Experiences

The purpose of the Technical Experience Track is to establish a meaningful forum between practitioners and researchers with useful solutions in various organizational environments, diverse systems or different cultures. The Technical Experience Track includes all kind of practical applications which are principles, projects, missions, techniques, tools, methods, processes, and etc. We invite original, unpublished submissions in two categories:
*Case studies
*Experience reports

Tuesday, February 10, 2009

Some Thoughts on Compound Video Coding

Article from:

While at Sharp, I worked on compound image coding problem - a compound image consists of the mixture of photographic pictures, graphics and texts. Djvu and PDF have become the standard document images formats. In the past four years, especially due to the increasing popularity of YouTube, more and more video clips are available online. I have noticed that there seems to be a need for the study of compound video coding - the counterpart of compound image coding.

The compound nature of video source is particularly valid in applications related to distance learning (mixture of PPT slides and classroom experience), multimedia presentation (mixture of text slides and graphic/motion pictures) and gaming (screenshot of video games). But the definition of compound source can be generalized to incorportate  more traditional view - e.g., foreman sequence is compound because it contains the mixture of slow and fast camera motion; flower-garden is compound in the sense of mixing objects at varying scene depths (layered representation is the essential idea underlying MRC adopted by djvu image coding algorithm). Of course,  segmentation will likely be the main technical challenge again in compound video coding. But from a system perspective, unifying coding with analysis is desirable because it supports both higher coding efficiency and content-based retrieval.

Image Description and Retrieval (Advances in Computer Vision and Machine Intelligence)

Image Description and Retrieval (Advances in Computer Vision and Machine Intelligence)
Edition: 1
Manufacturer: Springer
Number Of Items: 1
Number Of Pages: 210
With recent advances in multimedia technology, on-line libraries of digital images are assuming an ever increasing relevance within a wide range of information systems. Effective access to these archives requires not only conventional searching techniques based on keywords, but also content-based queries which allow visual features of data to be searched. This new comprehensive reference introduces the intricate science of implementing image modeling and retrieval based on the shape, on the color and texture, or on the spatial arrangement of imaged objects. Building on this introduction, six chapters by major research groups in the field detail and compare different modeling approaches.


More information

WPF Simple ColorPicker Control


This is a simple ColorPicker control. It allows you to pick a color from a specified range. This ColorPicker includes some event wrappers for CurrentColorChanged and LastColorChanged. So when the value changes, the respective event will be thrown.


The ColorPickerUnit is the left square, the ColorSelectorUnit describes the centered square in the image you can see, the ColorBarUnit is at the bottom, and shows the Current and Last selected color. Last but not least is the ColorInfoUnit which shows you the RGB and HEX value of the color. The main idea of this project was to clip the mouse to the ColorPicker or ColorSelectorUnit in the way which one has been clicked. So what I mean is, the mouse gets "jailed", you can't move out of this location. My second idea was to set the mouse to the last position wherever you clicked one of these units.

Using the Code

My project includes the following classes:

  • _ColorPicker.xaml with codefile: This one is the root element. It includes the basic events and the units mentioned above. So I can say this class controls the main user interaction.
  • CopyBox.cs: This class inherits from border, and the border includes a textbox, and one property called value, which sets or gets the current value of the CopyBoxes. That's all.
  • MouseClipping.cs : This is one tricky class. It allows to clip the mouse to any UIElement. This is possible by using an API-Method called ClipCursor which is stored in the user32.dll.
  • MouseControling.cs : This one also includes some API calls -> SetCursorPos, GetCursorPos, GetPixel, GetWindowDC and ReleaseDC.
  • ValueBox.cs : This class has some properties -> Maximum and Value, and some events. When you set the value property, the class calculates the length of a border. So you can see the value stored in a textbox and the position in graphic mode.

Article From Codeproject

Sunday, February 8, 2009

Low-Cost Multi-point Interactive Whiteboards Using the Wiimote

Since the Wiimote can track sources of infrared (IR) light, you can track pens that have an IR led in the tip. By pointing a wiimote at a projection screen or LCD display, you can create very low-cost interactive whiteboards or tablet displays. Since the Wiimote can track upto 4 points, up to 4 pens can be used. It also works great with rear-projected displays.


Read More

Saturday, February 7, 2009

Augmenting Navigation for Collaborative Tagging with Emergent Semantics

Melanie Aurnhammer , Peter Hanappe , and Luc Steels

We propose an approach that unifies browsing by tags and
visual features for intuitive exploration of image databases. In contrast to
traditional image retrieval approaches, we utilise tags provided by users
on collaborative tagging sites, complemented by simple image analysis
and classification. This allows us to find new relations between data elements.
We introduce the concept of a navigation map, that describes
links between users, tags, and data elements for the example of the collaborative
tagging site Flickr.We show that introducing similarity search
based on image features yields additional links on this map. These theoretical
considerations are supported by examples provided by our system,
using data and tags from real Flickr users.

Read More

Computer Vision

Author: George Stockman

Computer Vision presents the necessary theory and techniques for students and practitioners who will work in fields where significant information must be extracted automatically from images. It will be a useful resource automatically from images. It will be a useful resource book for professionals and a core text for both undergraduate and beginning graduate computer vision and imaging courses.

• Topics include image databases an virtual and augmented reality in addition to classical topics.
• Offers a complete view of two real-world systems that use computer vision.
• Contains applications from industry, medicine, land use, multimedia, and computer graphics.
• Includes over 250 exercises and programming projects, 48 separately defined algorithms, and 360 figures.
• The companion website features include image archive, sample

This well-illustrated guide presents the theory and techniques for students and practitioners. Using image databases and applications from many fields as supporting material the topics covered include: imaging and image representation, binary image analysis, pattern recognition, filtering and enhancing, color and shading, texture, content-based image retrieval, motion from 2D image sequences, image segmentation, matching in 2D, perceiving 3D from 2D, 3D sensing and object pose computation, 3D models and matching, virtual reality, and case studies. The authors both teach computer science and engineering, Shapiro at the U. of Washington, Stockman at Michigan State U. Annotation c. Book News, Inc., Portland, OR (

Wednesday, February 4, 2009

Make Your Own Handwriting Fonts is a FREE online font generator that allows you to create your own TrueType fonts within a couple of minutes. Go make your own handwriting as a font!

Your own handwriting turned into your very own font for free

  • Optionally include your signature
  • You'll have your very own font within 15 minutes
  • Make as many fonts as you like
  • Use your fonts on Windows, Mac OS X and Linux
  • Personalize your digital scrapbook pages
  • Make your own "family handwriting history"
  • Use your fonts in Microsoft Word, PowerPoint and every program that you own

Read More

Tuesday, February 3, 2009


A new version (2.3) of the PhotoEnhancer software is now available here.

The new version features a new enhancement algorithm for images captured under low-transmittance conditions (fog, smoke, aerial photos, satellite photos etc). It also features an improved automatic enhancement engine, which improves the enhancement in automatic mode.

Monday, February 2, 2009

5th International Symposium on Visual Computing

ISCV seeks papers describing contributions to the state of the art and state of the practice in the broad field of visual computing. The symposium is structured around four central areas of visual computing: (1) computer vision, (2) computer graphics, (3) virtual reality, and (4) visualization. In particular, we are interested in papers that combine technologies from two or more of these areas. In addition to the main symposium, we are soliciting papers for several special tracks related to ISVC.
All paper submissions will be handled electronically through our online web submission system.
Area 1: Computer Vision
Computer vision, the study of enabling computers to understand and interpret visual information from static images and video sequences, is expanding rapidly throughout the world. During the past ten years, computer vision has grown from a research area to a widely accepted technology, capable of providing dramatic increase in productivity and improving living standard. We are seeking papers covering both the theory and applications of computer vision. Topics of interest include all aspects of computer vision including, but not limited, to the following areas:

* Color and texture
* Segmentation and grouping
* Motion and tracking
* Image-Based Modelling
* 3D reconstruction
* Shape representation and recognition
* Video analysis and event recognition
* Face/gesture analysis and recognition
* Human-computer interfaces
* Biological/Medical image analysis
* Image and Video Retrieval
* Sensors and Systems
* Secure Image/Video Communication
* Image/Video Encoding/Compression
* Applications

Read More

Image Comparer

Bolide Software today announces Image Comparer, a duplicate image finder that lets users find similar or duplicate images automatically and delete redundant files. Until now, most people used to browse through computer folders manually to find dupes and similar photos. Image Comparer puts this process on autopilot. Using a content-based image retrieval technology (CBIR) for image comparison, the program is able to find dupes and similar pictures, regardless of their file name, format, image size, bit depth and orientation of the object.

Taking photos or downloading images from the Web is part of our daily life. Over the years, people collect thousands of them in the computer - photos made with the camera, wallpapers, clipart, images and artwork, the list goes on and on. Unfortunately all these images are hardly ever kept organized. People save them to different folders in different formats and then re-save their copies to other folders and sub folders. Photo duplicates take space on the hard disk, slow browsing through the collection and cause confusion as too many times we wind up not remembering where we put that particular photo we need now. Browsing through folders to compare images can be very daunting and would take ages, so many users don’t do this, planning to sort out pictures later. And never do this.

Read More