Computer Science

An approach for extracting higher-level visual features for art painting classification based on MPEG-7 descriptors is presented in this paper. The MPEG 7 descriptors give a good presentation of different types of visual features, but are complex structures. This prevents their direct use into standard classification algorithms and thus requires specific processing.

A Bulgarian research project funded by the Bulgarian National Science Fund under the thematic priority Information and Communication Technologies, contract D002-308/19.12.2008 is presented in this article. The main goal and tasks are outlined. Some already achieved results are pointed.

Resource discovery is one of the key services in digitised cultural heritage collections. It requires intelligent mining in heterogeneous digital content as well as capabilities in large scale performance; this explains the recent advances in classification methods. Associative classifiers are convenient data mining tools used in the field of cultural heritage, by applying their possibilities to taking into account the specific combinations of the attribute values. Usually, the associative classifiers prioritize the support over the confidence. The proposed classifier PGN questions this common approach and focuses on confidence first by retaining only 100% confidence rules. The classification tasks in the field of cultural heritage usually deal with data sets with many class labels. This variety is caused by the richness of accumulated culture during the centuries. Comparisons of classifier PGN with other classifiers, such as OneR, JRip and J48, show the competitiveness of PGN in recognizing multi-class datasets on collections of masterpieces from different West and East European Fine Art authors and movements.

Abstract. The digitization practice for retro-converting of the mathematical periodicals, published by the Institute of Mathematics and Informatics, Bulgarian Academy of Sciences (IMI-BAS) and the followed benefits for long-term preserving and assuring open access to these materials is discussed in the article. Keywords: Digitization Cycle, Open Access, IMI-BAS

K. Ivanova a,*, M. Dobreva b, P. Stanchev a, c, K. Vanhoofd a Institute of Mathematics and Informatics, BAS, Sofia, Bulgaria–kivanova@ math. bas. bg b Centre for Digital Libraries Research, University of Strathclyde, Glasgow, UK–milena. dobreva@ strath. ac. uk c Kettering University, Flint, MI, 48504, USA–pstanche@ kettering. edu d Hasselt University, Hasselt, Belgium–koen. vanhoof@ uhasselt. be KEY WORDS: Art Images, Repositories, Image Retrieval, Content-Based Indexing, User Expectations, Interoperability, Europeana

From all the senses that connect us to the world–vision, hearing, taste, smell, and touch–vision is the most important. More than 80% of our sensory experiences are visual [Holtschue, 2006]. When the brain receives light stimulus, it first recognizes shapes and objects and separates the objects from their surrounding environment. Figure-ground separation or pattern recognition is the first cognitive step in the process of perception. In this process, colour plays an important but secondary role. Colour responses are tied stronger ...

An approach for extracting higher-level visual features for art painting classification based on MPEG-7 descriptors is presented in this paper. The MPEG 7 descriptors give a good presentation of different types of visual features, but are complex structures. This prevents their direct use into standard classification algorithms and thus requires specific processing. Our approach consists of the following steps:(1) the images are tiled into non-overlapping rectangles to capture more detailed information;(2) the tiles of the images are clustered for ...

Abstract-An approach for extracting higher-level visual features for art painting classification based on MPEG-7 descriptors was implemented in the system “Art Painting Image Colour Aesthetics and Semantics”(APICAS). The approach consists of the following steps:(1) tiling images into non-overlapping rectangles in order to capture more detailed local information;(2) the tiles of the images are clustered for each MPEG-7 descriptor;(3) vector quantization is used to assign a unique value to each tile, which corresponds to the ...

In this paper a new method for image retrieval using high level color semantic features is proposed. It is based on extraction of low level color characteristics and their conversion into high level semantic features using Johannes Itten theory of color, Dempster-Shafer theory of evidence and fuzzy production rules.

This paper presents a comparison of four representative discretization methods from different classes to be used with so called PGN-classifier which deals with categorical data. We examine which of them supplies more convenient discretization for PGN Classification Method. The experiments are provided on the base of UCI repository data sets. The comparison tests were provided using an experimental classification machine learning system "PaGaNe", which realizes Pyramidal Growing Network (PGN) Classification Algorithm. It is found that in general, PGN-classifier trained on data preprocessed by Chi-merge achieve lower classification error than those trained on data preprocessed by the other discretization methods. The comparison of PGN-classifier, trained with Chi-merge-discretizator with other classifiers (realized in WEKA system) shows good results in favor of PGNclassifier.

In this paper we present a classification of color harmonies and contrasts, which is consistent with human perceiving of visual expression. It is conformed to the possibilities of automatic extraction of visual information from digitalized copies of art images. The classification is done on the base of the three main characteristics of the color most closed to the human perception -hue, saturation and lightness. Functions for automatic features extraction from digital images are defined. These functions are realized as part of a virtual laboratory "Art Painting Image Color Aesthetic and Semantic" (APICAS). The system can be used by designers and art students for searching images, having certain harmonies or contrasts in image collections as well as a for examining specifics of artists or movements. In future we will use the system as a Web 2.0 service, which could be included in a virtual learning environment.

In this paper we illustrate several aspects of art databases, such as: the spread of the multimedia art images; the main characteristics of art images; main art images search models; unique characteristics for art image retrieval; the importance of the sensory and semantic gaps. In addition, we present several interesting features of an art image database, such as: image indexing; feature extraction; analysis on various levels of precision; style classification. We stress color features and their base, painting analysis and painting styles. We study also which MPEG-7 descriptors are best for fine painting images retrieval. An experimental system is developed to see how these descriptors work on 900 art images from several remarkable art periods. On the base of our experiments some suggestions for improving the process of searching and analysis of fine art images are given.

In this paper we study some of the characteristics of the art painting image color semantics. We analyze the color features of different artists and art movements. The analysis includes exploration of hue, saturation and luminance. We also use quartile's analysis to obtain the distribution of the dispersion of defined groups of paintings and measure the degree of purity for these groups. A special software system "Art Painting Image Color Semantics" (APICSS) for image analysis and retrieval was created. The obtained result can be used for automatic classification of art paintings in image retrieval systems, where the indexing is based on color characteristics.

In the article it is considered preconditions and main principles of creation of virtual laboratories for computer-aided design, as tools for interdisciplinary researches. Virtual laboratory, what are offered, is worth to be used on the stage of the requirements specification or EFT-stage, because it gives the possibility of fast estimating of the project realization, certain characteristics and, as a result, expected benefit of its applications. Using of these technologies already increase automation level of design stages of new devices for different purposes. Proposed computer technology gives possibility to specialists from such scientific fields, as chemistry, biology, biochemistry, physics etc, to check possibility of device creating on the basis of developed sensors. It lets to reduce terms and costs of designing of computer devices and systems on the early stages of designing, for example on the stage of requirements specification or EFT-stage. An important feature of this project is using the advanced multi-dimensional access method for organizing the information base of the Virtual laboratory.

In this paper, we analyze various methods used for semantic annotation and search in a collection of art and architecture images. We discuss the Art and Architecture Thesaurus, WordNet, ULAN and Iconclass ontology. Systems for searching and retrieval art and architecture image collections are presented. We explore if the MPEG 7 descriptors are useful for art and architecture image annotations. For illustrations we use images from Antoni Gaudi architecture and Claude Monet paintings.

Theoretical and practical aspects of classification systems and classification learning are considered. Analysis of subject area learning sets and analysis of classification schemes raises a number of nonstandard questions, such as relations between categorization/metadata and logic-combinatorial structuring/clustering of the descriptive part of the input table. Several such questions are are treated in this paper. Software environment of testing and evaluation is the extended system PaGaNe, completed by research methodology of well known logic-combinatorial scheme of pattern recognition.

In this paper the semantic and abstraction content of art images is studied. Different techniques for search in art image repositories are analyzed and new ones are proposed. The content-based retrieval process integrates the search on different components, linked in XML structures. Some experiments over 200 paintings of six Israel contemporary artists are done and analyzed.