Method of combining spectral data with non-spectral data in a produce recognition system
US6606579B1 · kind B1 · utility
Assignee
Inventor
Key dates
| Filing date | Aug 16, 2000 |
| Grant date | Aug 12, 2003 |
| Priority date | — |
| Expiry date | Feb 3, 2021 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/68
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
A method of combining spectral data with non-spectral data which uses a defined distance measure of likeness (DML) value and conditional probabilities. The method includes the steps of collecting the spectral and non-spectral data for the produce item, determining DML values between the spectral and the non-spectral data and reference produce data for a plurality of types of produce items, determining conditional probability densities for all of the types of produce items using the DML values, combining the conditional probability densities to form a combined conditional probability density, and determining probabilities for the types of produce items from the combined conditional probability density.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.