K Kondo, M Iguchi, H Ishigaki, Y Konishi, K Mabuchi
JOINT 9TH IFSA WORLD CONGRESS AND 20TH NAFIPS INTERNATIONAL CONFERENCE, PROCEEDINGS, VOLS. 1-5 Vol.3, pp.1642 1646 1642-1646 2001年
In this paper, we present a new enhancement technique using cellular neural network(CNN) filters with complex weighting factors, applicable to medical images. Since the CNN-type filters have only spatially local interconnections and the number of connections between neurons is relatively few, the required computation in the learning phase is a reasonable amount. Instead, the output/input behavior is restrictive. The proposed CNN filters are designed as complex coefficient filters which can improve the output S/N ratio, and process the 2D analytic signals of input images. The filter parameters are determined by applying complex domain backpropagation algorithm. Through several simulations, it is shown that the proposed filters are robust and noise tolerant for medical images.