Applying Principal Component Analysis for Macromolecular Objects Diffraction Images Sorting
Teslyuk A.B., Senin R.A., Ilyin V.A
National Research Centre «Kurchatov Institute», 123082 Moscow Russia
Abstract. In this paper we present a method for fast detection of images containing diffraction patterns of specific macromolecular objects. Our method is based on a principal component analysis, a popular method used in a various areas to analyse multi-dimensional data like image classification, noise reduction, video indexing and etc. In our paper we demonstrate that our method is efficient for diffraction images classification for various macromolecular structures containing collagen. Diffraction data was gathered from Kurchatov synchrotron radiation source.
Key words: images analysis, data clustering, principal component analysis, dimension reduction methods, macromolecular objects diffraction, diffraction images analysis, diffraction images classification.