The Prague texture segmentation data-generator and benchmark (mosaic.utia.cas.cz) is a web-based service designed to mutually compare and rank (recently nearly 200) different static and dynamic texture and image segmenters, to find optimal parametrization of a segmenter and support the development of new segmentation and classification methods. The benchmark verifies segmenter performance characteristics on potentially unlimited monospectral, multispectral, satellite, and bidirectional texture function (BTF) data using an extensive set of over forty prevalent criteria. It also enables us to test for noise robustness and scale, rotation, or illumination invariance. It can be used in other applications, such as feature selection, image compression, query by pictorial example, etc. The benchmark's functionalities are demonstrated in evaluating several examples of leading previously published unsupervised and supervised image segmentation algorithms. However, they are used to illustrate the benchmark functionality and not review the recent image segmentation state-of-the-art.

The unsupervised color image segmentation competition is taking place in conjunction with the ICPR 2014 conference. It aims to promote evaluation of unsupervised color image segmentation algorithms using publicly available data sets. The results evaluation is based on the standard performance assessment methodology using the online web verification server. We present in this paper the top six preliminary results submitted to this contest till the ICPR paper submission deadline.

A novel illumination invariant unsupervised multispectral texture segmentation method with unknown number of classes is presented. Multispectral texture mosaics are locally represented by illumination invariants derived from four directional causal multispectral Markovian models recursively evaluated for each pixel. Resulted parametric space is segmented using a Gaussian mixture model based unsupervised segmenter. The segmentation algorithm starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached. The performance of the presented method is extensively tested on the large illumination invariant benchmark from the Prague Segmentation Benchmark using 21 segmentation criteria and compares favourably with an alternative segmentation method.

We present a multiscale unsupervised segmenter for automatic detection of potentially cancerous regions of interest containing fibroglandular tissue in digital screening mammography. The mammogram tissue textures are locally represented by four causal multispectral random field models recursively evaluated for each pixel and several scales. The segmentation part of the algorithm is based on the underlying Gaussian mixture model and starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous mammogram segments is reached. The performance of the presented method is verified on the Digital Database for Screening Mammography (DDSM) from the University of South Florida as well as extensively tested on the Prague Texture Segmentation Benchmark and compares favourably with several alternative unsupervised texture segmentation methods.

The Prague texture segmentation data-generator and benchmark is a web based (http://mosaic.utia.cas.cz) service designed to mutually compare and rank different texture segmenters, and to support new segmentation and classification methods development. The benchmark verifies their performance characteristics on monospectral, multispectral, bidirectional texture function (BTF) data and enables to test their noise robustness, scale, and rotation or illumination invariance. It can easily be used for other applications such as feature selection, image compression, and query by pictorial example, etc. The benchmark functionalities are demonstrated on five previously published image segmentation algorithms evaluation.

Visualization of large urban complexes on the Web is a highly demanding task both from the networking and computational point of view. The whole three-dimensional model of a city is mostly too big to be downloaded in a reasonable time and to be stored in a memory of commonly used computers. This paper presents a scalable approach for subdividing an urban model into smaller parts. Dynamic loading and unloading data allows theoretically unlimited extension of a model with constant network and computation load. Further requirements specific to presentation of virtual cities are also discussed. Theoretical considerations are followed by a practical implementation utilizing the VRML language for modeling the historical city of Prague.