Brand recognition system

• US 7,593,856 B2
• Filed: 01/10/2005
• Issued: 09/22/2009
• Est. Priority Date: 01/09/2004
• Status: Expired due to Fees

• Current Assignee: Nickel Brand Software Incorporated
• Original Assignee: Nickel Brand Software Incorporated
• Inventors: Martinez, Loretta A.
• Primary Examiner(s): Weiss; John G.
• Assistant Examiner(s): Brooks; Matthew L
• Application Number:
  US11/032,638
• Publication Number:
  US 20050217590A1
• Time in Patent Office: 1,716 Days
• Field of Search: None
• US Class Current: 705/1.1
• CPC Class Codes: A01K 11/005 Branding or tattooing devices for animals
• CPC Class Codes: A01K 11/006 Automatic identification systems for animals, e.g. electronic devices, transponders for animals identification systems for access to feeding pens A01K1/0209; ear tags with electronic identification means A01K11/004
• CPC Class Codes: Y10T 428/14 Layer or component removable to expose adhesive
• CPC Class Codes: Y10T 428/1419 Wax containing
• CPC Class Codes: Y10T 428/24802 Discontinuous or differential coating, impregnation or bond [e.g., artwork, printing, retouched photograph, etc.]

Abstract

Computer software for and method of determining livestock ownership comprising inputting an image of a livestock brand whose ownership is to be determined, automatically determining one or more computed closest fits to the image from a database of livestock brands, and outputting owner information from the database of livestock brands concerning one or more of the one or more computed closest fits.

Claims

1. A method of determining livestock ownership, the method comprising:

inputting a plurality of livestock brands establishing a database;

inputting into a computer by a user drawing with an input device an image of a physical livestock brand whose ownership is to be determined;

automatically determining using a computer processor in communication with said database one or more closest fits to the image from the database of livestock brands; and

outputting owner information from the database of livestock brands concerning one or more of the one or more computed closest fits back to the user.

2. The method of claim 1 wherein inputting comprises a user tracing a photographic image of a physical livestock brand.

3. The method of claim 1 wherein inputting comprises a user inputting by drawing an image of the brand while observing the brand on livestock.

4. The method of claim 1 wherein determining comprises providing the image to one or more of a set of one or more trained neural networks.

5. The method of claim 4 wherein determining additionally comprises performing feature extraction on the image.

6. The method of claim 5 wherein results of the feature extraction determines which of the set of one or more trained neural networks to which the image is provided.

7. The method of claim 1 wherein outputting comprises presenting a plurality of brands from the database to a user and permitting the user to choose one or more of the plurality for ownership information output.