Pages

img(Anaktisi)

K Zagoris, S. Α. Chatzichristofis, Nikolas Papamarkos and Y. S. Boutalis, “IMG(ANAKTISI): A WEB CONTENT BASED IMAGE RETRIEVAL SYSTEM.”, «2nd International Workshop on Similarity Search and Applications (SISAP)», Proceedings: IEEE Computer Society, pp.154-155, August 29-30 2009, Prague, Czech Republic. [Download]
In this web-site a new set of feature descriptors is presented in a retrieval system. These descriptors have been designed with particular attention to their size and storage requirements, keeping them as small as possible without compromising their discriminating ability. These descriptors incorporate color and texture information into one histogram while keeping their sizes between 23 and 74 bytes per image. Also, in this web-site an Auto Relevance Feedback (ARF) technique is introduced which is based on the proposed descriptors. The goal of the proposed Automatic Relevance Feedback (ARF) algorithm is to optimally readjust the initial retrieval results based on user preferences. During this procedure the user selects from the first round of retrieved images one as being relevant to his/her initial retrieval expectations. Information from these selected images is used to alter the initial query image descriptor.

anaktisi

K Zagoris, S. Α. Chatzichristofis, Nikolas Papamarkos and Y. S. Boutalis, “IMG(ANAKTISI): A WEB CONTENT BASED IMAGE RETRIEVAL SYSTEM.”, «2nd International Workshop on Similarity Search and Applications (SISAP)», Proceedings: IEEE Computer Society, pp.154-155, August 29-30 2009, Prague, Czech Republic. [Download]
Img(Anaktisi) was developed at the Democritus University of Thrace-Greece. This web program is programmed in C# with the help of Visual Studio 2008 and is based on the Microsoft .NET Framework 3.5. It also employs AJAX, HTML and Javascript technologies for user interaction. Finally, Microsoft SQL Server 2005 is the database used by the web platform to store and retrieve the descriptors for each
image.

Updates

31 March 2009

The MIR Flickr Retrieval Evaluation Database is now supported in img(anaktisi). The new MIRFLICKR-25000 collection consists of 25000 images downloaded from the social photography site Flickr through its public API.

M. J. Huiskes, M. S. Lew (2008). The MIR Flickr Retrieval Evaluation. ACM International Conference on Multimedia Information Retrieval (MIR'08), Vancouver, Canada – Read More about MIR Flickr

10 January 2009
IRMA 2005 Medical Image is now supported in img(Anaktisi)



anaktisi2
The IRMA database consists of 10000 annotated radiographs taken randomly from medical routine at the RWTH Aachen University Hospital-Germany. The images are separated into 9000 training images and 1000 test images. The images are sub divided into 57 classes. For CBMIR, the relevance's are defined by the classes, given a query image from a certain class, all database images from the same class are considered relevant. The IRMA database was used in the ImageCLEF 2005 image retrieval evaluation fort he automatic annotation task.

IRMA Database is courtesy of TM Deserno, Dept. of Medical Informatics, RWTH Aachen

14 November 2008
New Features
Two new experimental features are implemented in the on-line image retrieval system img(Anaktisi)
1. Draw a sketch to retrieve similar images from our database. The method is based on a new spatial compact color descriptor.

Img(Anaktisi)#3
2. Automatic keyword annotation. Select a combination of words and retrieve images. The method is based on a fuzzy support vector machine system. The network was trained using a combination of CEDD and FCTH descriptors
Img(Anaktisi)#4
Note that both techniques are still under study.

20 July 2008
New features:
1. Up to 100000 random images from flickR are now implemented in a separate image database. Total number of images: 155000!!!
2. A new descriptor (JCD) added.
3. Speed improvements.
4. Improved layout.
5. All the descriptors and the relevance feedback method are available for download.
6. The user can upload an image for retrieval
NEW!!!
7. Search in more than 155000 images in less than 1 sec!!! Probably the faster image retrieval engine in the web.

The planned future features at this time are:

1. Merge the experimental (for now) img(Paint.Anaktisi) to img(Anaktisi) (At the implementation stage).
2. Create a parallel Word - Annotation Image Retrieval to supplement the descriptors (This is still at research stage).
3. Better support for non-windows OS (Careful selection of the font-names) (done)
4. Auto descriptor selector (done)

Very special thanks to Konstantinos Zagoris