Title :
Craquelure analysis for content-based retrieval
Author :
Abas, F.S. ; Martinez, K.
Author_Institution :
Dept. of Electron. & Comput. Sci., Southampton Univ., UK
Abstract :
In this paper, we describe a method for the extraction of distinguishable features from crack patterns, particularly those in paintings. First, we filter the selected crack image using 8 differently oriented Gabor filters. Then we thin the image to 1 pixel wide using a morphological thinning algorithm. Next we implement a crack following algorithm and generate statistical structure of global and local features from a chain code based representation. We describe an orientation-based feature extraction method to represent a crack network from sets of local orientation features. The resultant features are used as a guide towards classifying crack network patterns into several predefined classes, i.e circular, rectangular, spider-web, unidirectional and random. A simple classification experiment is presented to describe the significance of those extracted features towards classifying craquelure patterns.
Keywords :
art; cracks; digital filters; edge detection; feature extraction; image classification; image representation; image thinning; mathematical morphology; Gabor filters; chain code based representation. orientation-based feature extraction method; circular pattern; classification experiment; crack following algorithm; crack image; crack network; crack network patterns; crack patterns; craquelure patterns; distinguishable features; feature extraction; global features; local features; local orientation features; morphological thinning algorithm; paintings; random pattern; rectangular pattern; spider-web pattern; statistical structure; unidirectional pattern; Computer science; Content based retrieval; Data mining; Feature extraction; Frequency; Gabor filters; Image retrieval; Information retrieval; Painting; Pixel;
Conference_Titel :
Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on
Print_ISBN :
0-7803-7503-3
DOI :
10.1109/ICDSP.2002.1027828