%0 Conference Proceedings
%T A Window-Based Self-Organizing Feature Map (SOFM) for Vector Filtering Segmentation of Color Medical Imagery
%+ Hellenic Telecommunication Organization S.A. (OTE)
%+ Technological Educational Institute of Piraeus (TEI of Piraeus)
%+ Medical Informatics Laboratory
%+ Hellenic Open University [Patras]
%+ Democritus University of Thrace (DUTH)
%A Stephanakis, Ioannis, M.
%A Anastassopoulos, George, C.
%A Iliadis, Lazaros
%Z Part 3: Classification - Pattern Recognition
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI)
%C Corfu, Greece
%Y Lazaros Iliadis
%Y Chrisina Jayne
%I Springer
%3 Engineering Applications of Neural Networks
%V AICT-363
%N Part I
%P 90-100
%8 2011-09-15
%D 2011
%R 10.1007/978-3-642-23957-1_11
%K Vector Filtering
%K Color Segmentation
%K Self-Organizing Feature Maps (SOFM)
%K Medical Imaging
%Z Computer Science [cs]Conference papers
%X Color image processing systems are used for a variety of purposes including medical imaging. Basic image processing algorithms for enhancement, restoration, segmentation and classification are modified since color is represented as a vector instead of a scalar gray level variable. Color images are regarded as two-dimensional (2-D) vector fields defined on some color space (like for example the RGB space). In bibliography, operators utilizing several distance and similarity measures are adopted in order to quantify the common content of multidimensional color vectors. Self-Organizing Feature Maps (SOFMs) are extensively used for dimensionality reduction and rendering of inherent data structures. The proposed window-based SOFM uses as multidimensional inputs color vectors defined upon spatial windows in order to capture the correlation between color vectors in adjacent pixels. A 3x3 window is used for capturing color components in uniform color space (L*u*v*). The neuron featuring the smallest distance is activated during training. Neighboring nodes of the SOFM are clustered according to their statistical similarity (using the Mahalanobis distance). Segmentation results suggest that clustered nodes represent populations of pixels in rather compact segments of the images featuring similar texture.
%G English
%Z TC 12
%Z WG 12.5
%2 https://inria.hal.science/hal-01571348/document
%2 https://inria.hal.science/hal-01571348/file/978-3-642-23957-1_11_Chapter.pdf
%L hal-01571348
%U https://inria.hal.science/hal-01571348
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-AIAI
%~ IFIP-WG12-5
%~ IFIP-AICT-363
%~ IFIP-EANN