Using Color and Texture Indexing to improve Collaborative Filtering of Art Paintings.

Bibliographic reference :

KOHRS Arnd and MERIALDO Bernard. Using Color and Texture Indexing to improve Collaborative Filtering of Art Paintings.

Available at : www.eurecom.fr/util/publidownload.en.htm?id=261




Extract :

"3 Content-Based Filtering
It is reasonable to expect that images with similar content will be almost equally interesting to users.
The problem is that de ning image content and image similarity is still an open problem. Ongoing research in multimedia indexing is focusing on two directions: { either each image is described by a textual caption, and captions are compared using techniques derived from document retrieval, { or analysis and recognition techniques are applied to the image pixels to extract automatically features which are compared using some distance measure in the feature space.
We focus on the second approach, because it can be entirely automated. In our prototype, we have currently implemented two feature extraction components, derived from the work described in [10, 11]: Color histograms and texture coe cients."



Dublin Core Metadata :

Title : Using Color and Texture Indexing to improve Collaborative Filtering of Art Paintings.
Creator : KOHRSArnd, MERIALDO Bernard
Subject : content analysis/ art paintings/ filtering/ indexing system
Description : « Information ltering is a key technology for the creation of Web sites, which are adapted to the user's needs. In this paper we identify collaborative ltering and content-based ltering as independent technologies for information ltering. We apply both technologies in our prototype user-adapting Web site, the Active WebMuseum, a recommender system for art paintings. Our new approach extends existing user pro les with content-based information gained through automatic image indexing. These extensions lead to a better performing collaborative ltering system. We validate our approach in o -line experiments. »
Publisher : Institut EURECOM { Department of Multimedia Communications
Date : None
Type : Text
Format : Pdf
Identifier : www.eurecom.fr/util/publidownload.en.htm?id=261
Source : None
Language : En
Coverage : International
Rights : Institut EURECOM { Department of Multimedia Communications

ARTISTE: An integrated Art Analysis and Navigation Environment

Bibliographic reference :

ALLEN Paul, VACCARO Roberto and PRESUTTI Gert. ARTISTE: An integrated Art Analysis and Navigation Environment.

Available at : http://www.cultivate-int.org/issue1/artiste/



Extract :

Introduction

The possibility of an easy and effective management of large data repository is a strategic objective for many enterprises. This field of research is of particular interest to the market, as the availability of large repositories of electronic data is increasing and the industrial interest to solve the problem of automated content-based indexing and retrieval of images is high [1].

European museums and galleries are rich in cultural treasures but public access to masterpieces for education, leisure or work purposes has not reached its full potential. Automation of the indexing, retrieval and delivery of such assets over the web would help to address these issues and expand the accessibility of collections, broadening public awareness of the European cultural heritage, which lies behind them. To date, however, there has been a lack of systems and techniques to provide effective remote access to these collections [2],[3],[4].

New technology is now being developed that will transform that situation. A European consortium, partly funded by the EU under the fifth R&D framework, is working to produce a new management system for visual information. (…)



Dublin Core Metadata :

Title : ARTISTE: An integrated Art Analysis and Navigation Environment.
Creator : ALLEN Paul, VACCARO Roberto and PRESUTTI Gert
Subject : content analysis/ indexing system/ ARTISTE/ databases
Description : Presents the objectives of the ARTISTE project then describes differents applications of this tool as image content analysis or image retrieval.
Publisher : Cultivate interactive
Date : 2000
Type : Text
Format : Html
Identifier : http://www.cultivate-int.org/issue1/artiste/
Source : http://www.cultivate-int.org
Language : En
Coverage : International
Rights : Cultivate interactive

Computer analysis of Van Gogh's complementary colours.

Bibliographic reference:

Igor Berezhnoy, Eric Postma and Jaap van den Herik, Computer analysis of Van Gogh's complementary colours.

Available at: http://www.ai.rug.nl/conf/bnaic2004/ap/a39.pdf

Extract:

3.3. Opponent-colour Analysis

Application of the opponent-colour transform yields three images (one for the luminance channel and one for each chrominance channel). Since our analysis focusses on opponent-colour transitions, the two chromatic-channel images are convolved with odd and even Gabor filters in four orientations (horizontal, vertical and along both diagonals) and at four scales. For the four scales, the support for the Gabor filters measured 82, 162, 322, and 642 pixels. The opponency for each channel is defined as the total energy averaged over the orientations and scales and divided by the number of pixels in the image. The opponency value for a painting equals the summed opponencies of the red-green and blue-yellow channels.

Dublin Core Metadata:

Title: Digital analysis of Van Gogh’s complementary colours
Creator: Igor Berezhnoy, Eric Postma, Jaap van den Herik
Subject: art paintings/ Vincent van Gogh/ digital analysis/ complementary colours

Description: "Traditionally, the analysis of visual arts is performed by human art experts only. The availability of advanced artificial intelligence techniques makes it possible to support art experts in their judgement of visual art. In this paper image-analysis techniques are applied to measure the complementary colours in the oeuvre of Vincent van Gogh. It is commonly acknowledged that, especially in his French period, Van Gogh started employed complementary colours to emphasize contours of objects or parts of scenes. We propose a method to measure complementary-colour usage in a painting by combing an opponent-colour space representation with Gabor filtering. Using this method, the analysis of a dataset of 617 digitised oil-on-canvas paintings confirms artexpert’s knowledge about the global pattern of complementary-colour usage in Van Gogh’s paintings. In addition, it provides an objective and quantifiable way to support the analysis of colours in individual paintings. Our results show that art experts can be supported by artificial-intelligence techniques."

Publisher: IKAT/Computer Science, Maastricht University
Date: None
Type: Text
Format: Pdf

Identifier: http://www.ai.rug.nl/conf/bnaic2004/ap/a39.pdf
Source: None
Language: En
Coverage: International
Rights: IKAT/Computer Science, Maastricht University

Classification of painting cracks for content-based analysis

Bibliographic reference:

F.S. Abas and K. Martinez, Classification of painting cracks for content-based analysis.

Available at: http://eprints.ecs.soton.ac.uk/7294/1/spie_cracks.pdf

Extract:

2. APPLICATION SCENARIO

The capabilities of image analysis and processing can aid conservators if the process can provide them with the functionalities that manual processes fail to do. Among the common problems of manual defect screening are time consumption and the risk of further damage. Required information should be retrieved correctly (i.e as close as possible to the users’ individual perception) and consumes considerably less time and effort. The following sections briefly outline potential application scenarios from a user point of view.

Dublin Core Metadata:

Title : Classification of painting cracks for content-based analysis
Creator : F.S. Abas and K. Martinez

Subject : cracks/ classification/ content analysis/ clustering
Description : "In this paper we present steps taken to implement a content-based analysis of crack patterns in paintings. Cracks are first detected using a morphological top-hat operator and grid-based automatic thresholding. From a 1-pixel wide representation of crack patterns, we generate a statistical structure of global and local features from a chain-code based representation. A well structured model of the crack patterns allows post-processing to be performed such as pruning and high-level feature extraction. High-level features are extracted from the structured model utilising information mainly based on orientation and length of line segments. Our strategy for classifying the crack patterns makes use of an unsupervised approach which incorporates fuzzy clustering of the patterns. We present results using the fuzzy k-means technique."

Publisher : Intelligence, Agents, Multimedia Group, Department of Electronics and Computer Science, University of Southampton, United Kingdom, S017 1BJ.
Date : None
Type : Text
Format : pdf

Identifier : http://eprints.ecs.soton.ac.uk/7294/1/spie_cracks.pdf
Source: None
Language : En
Relation : -
Coverage : United Kingdom
Rights : Intelligence, Agents, Multimedia Group, Department of Electronics and Computer Science, University of Southampton, United Kingdom, S017 1BJ.