Invariant Image Recognition by Zernike Moments
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Z: specification, refinement, and proof
Using Z: specification, refinement, and proof
Image Analysis in Histology: Conventional and Confocal Microscopy
Image Analysis in Histology: Conventional and Confocal Microscopy
RETRACTED: Invariance image analysis using modified Zernike moments
Pattern Recognition Letters
A computerized cellular imaging system for high content analysis in Monastrol suppressor screens
Journal of Biomedical Informatics
A novel approach to the fast computation of Zernike moments
Pattern Recognition
Exploiting the Self-Organizing Map for Medical Image Segmentation
CBMS '07 Proceedings of the Twentieth IEEE International Symposium on Computer-Based Medical Systems
Hierarchical SOMs: Segmentation of Cell-Migration Images
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Corpus-based thesaurus construction for image retrieval in specialist domains
ECIR'03 Proceedings of the 25th European conference on IR research
Combining multiple modes of information using unsupervised neural classifiers
MCS'03 Proceedings of the 4th international conference on Multiple classifier systems
Hi-index | 0.00 |
A multi-net neural computing system is described that can be used for classifying images based on intrinsic image features and extrinsic collateral linguistic description of the contents. A novel representation scheme based on wavelet analysis of images and a subsequent Zernike moment computation helps in a systematic extraction of image features; collateral linguistic description are obtained by the automatic extraction of single and compound keywords. We give a formal description of the system using the Z formal specification notation. An image data set comprising 480 fluorescent stained images of lymphocytes was used in the test of a 3-component unsupervised multi-net neural computing system. The classification accuracy of this system was found to be just over 85%.