Optical pattern recognition and clustering: Karhunen-Loève analysis
- 1 June 1976
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 15 (6) , 1584-1590
- https://doi.org/10.1364/ao.15.001584
Abstract
A Fourier transform gives a first dimensionally reduced description of optical data. But it is not sensitive to statistical variations characterizing class properties and allowing clustering and statistical recognition. A Karhunen-Loève transform of Fourier spectra leads to a more classifying space: it is shown, through examples of writings, that clustering of optical data (especially recognition of scriptors) is achieved in a 2-D Karhunen-Loève space. Inner evolution of data belonging to a given class is described in a 3-D KL space, allowing the dating of texts.Keywords
This publication has 6 references indexed in Scilit:
- The estimation of the gradient of a density function, with applications in pattern recognitionIEEE Transactions on Information Theory, 1975
- Application of the Karhunen-Loève Expansion to Feature Selection and OrderingIEEE Transactions on Computers, 1970
- A Generalized Technique for Spectral AnalysisIEEE Transactions on Computers, 1970
- The intrinsic dimensionality of signal collectionsIEEE Transactions on Information Theory, 1969
- Selectivity of hologram filters as a function of pass band characteristicsOptics Technology, 1969
- Minimum Spanning Trees and Single Linkage Cluster AnalysisJournal of the Royal Statistical Society Series C: Applied Statistics, 1969