Method of combining spectral data with non-spectral data in a produce recognition system

• US 6,606,579 B1
• Filed: 08/16/2000
• Issued: 08/12/2003
• Est. Priority Date: 08/16/2000
• Status: Expired due to Term

• Current Assignee: NCR Voyix Corporation
• Original Assignee: NCR Corporation
• Inventors: Gu, Yeming
• Primary Examiner(s): WACHSMAN, HAL D
• Application Number:
  US09/640,033
• Time in Patent Office: 1,091 Days
• Field of Search: 702/180, 702/181, 702/81, 702/82, 702/83, 702/84, 702/27, 702/28, 702/30, 702/76, 702/127, 702/179, 702/183, 702/FOR-115, 702/FOR-131, 702/FOR.137, 702/FOR.139, 702/FOR.141, 235/383, 235/462.06, 235/462.11, 235/462.14, 235/385, 382/110, 382/190, 382/181, 356/326, 356/328, 356/302, 356/303, 356/306, 356/419, 356/402, 356/408, 705/20, 705/23, 250/226
• US Class Current: 702/181
• CPC Class Codes: G01G 19/4144 for controlling weight of goods in commercial establishments, e.g. supermarket, P.O.S. systems
• CPC Class Codes: G01N 21/85 Investigating moving fluids or granular solids
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 20/68 Food, e.g. fruit or vegetables
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles

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.

Claims

1. A method of identifying a produce item comprising the steps of:

(a) collecting produce data from the produce item;

(b) determining Distance Measure of Likeness (DML) values between the produce data and reference produce data for a plurality of types of produce items;

(c) determining conditional probability densities for all of the types of produce items using the DML values;

(d) combining the conditional probability densities together to form a combined conditional probability density;

(e) determining probabilities for the types of produce items from the combined conditional probability density;

(f) determining a number of candidate identifications from the probabilities; and

(g) identifying the produce item from the number of candidate identifications.

2. The method as recited in claim 1, wherein step (e) comprises the substeps of:

(e-1) determining an a priori probability for the types of produce items; and

(e-2) determining the probabilities for the types of produce items from the combined conditional probability density and the a priori probability.

3. The method as recited in claim 1, wherein step (g) comprises the substeps of:

(g-1) displaying the number of candidate identifications; and

(g-2) recording an operator selection of one of the number of candidate identifications.

4. The method as recited in claim 1, wherein step (a) comprises the substep of:

collecting spectral data.

5. The method as recited in claim 1, wherein step (a) comprises the substep of:

collecting non-spectral data.

6. The method as recited in claim 1, wherein step (a) comprises the substeps of:

collecting spectral data from a spectrometer; and

collecting non-spectral data.

7. A method of identifying a produce item comprising the steps of:

(a) collecting produce data from the produce item;

(b) determining Distance Measure of Likeness (DML) values between the produce data and reference produce data for a plurality of types of produce items;

(c) determining conditional probability densities for all of the types of produce items using the DML values;

(d) combining the conditional probability densities together to form a combined conditional probability density;

(e) determining an a priori probability for the types of produce items;

(f) determining probabilities for the types of produce items from the combined conditional probability density and the a priori probability;

(g) determining a number of candidate identifications from the probabilities;

(h) displaying the number of candidate identifications; and

(i) recording an operator selection of one of the number of candidate identifications.

8. A method of combining spectral data with non-spectral data for recognizing a produce item comprising the steps of:

(a) collecting the spectral and non-spectral data for the produce item;

(b) determining Distance Measure of Likeness (DML) values between the spectral and the non-spectral data and reference produce data for a plurality of types of produce items;

(c) determining conditional probability densities for all of the types of produce items using the DML values;

(d) combining the conditional probability densities to form a combined conditional probability density; and

(e) determining probabilities for the types of produce items from the combined conditional probability density.

9. The method as recited in claim 8, wherein step (e) comprises the substeps of:

(e-1) determining an a priori probability for the types of produce items; and

(e-2) determining the probabilities for the types of produce items from the combined conditional probability density and the a priori probability.

10. A produce recognition system comprising:

a number of sources of produce data for a produce item; and

a computer system which determines Distance Measure of Likeness (DML) values between the produce data and reference produce data for a plurality of types of produce items, determines conditional probability densities for all of the types of produce items using the DML values, combines the conditional probability densities together to form a combined conditional probability density, determines probabilities for the types of produce items from the combined conditional probability density, determines a number of candidate identifications from the probabilities, and identifies the produce item from the number of candidate identifications.

11. A produce recognition system comprising:

a number of sources of produce data for a produce item; and

a computer system which determines Distance Measure of Likeness (DML) values between the produce data and reference produce data for a plurality of types of produce items, determines conditional probability densities for all of the types of produce items using the DML values, combines the conditional probability densities together to form a combined conditional probability density, determines an a priori probability for the types of produce items, determines probabilities for the types of produce items from the combined conditional probability density and the a priori probability, determines a number of candidate identifications from the probabilities, displays the number of candidate identifications, and records an operator selection of one of the number of candidate identifications.

12. The system as recited in claim 11, wherein one of the sources comprises a spectrometer.