Method and system for recognition and classification of objects in semi-controlled environments

Method and system for recognition and classification of objects in semi-controlled environments

NOVELTY – The method involves extracting descriptive characteristics of a data set e.g. images of the objects. The combination of different types of descriptors and the association of various types of classifiers are specialized and configured for a set of characteristics or types in a confused classification. An intelligent combination of binary classifiers is provided to divide the greater multi-type classification problem into small problems. The information extracted from various types of media is aggregated with a view to solve the problem of classifying objects in internal environments. USE – Method for recognizing and categorizing objects e.g. fruit, legumes, vegetables, flowers and boxes in semi-controlled environments for automating the purchasing process. ADVANTAGE – The method involves extracting descriptive characteristics of a data set e.g. images of the objects, where the combination of different types of descriptors and the association of various types of classifiers are specialized and configured for a set of characteristics, and hence ensures simplified and improved object recognizing and categorizing method. DETAILED DESCRIPTION – An INDEPENDENT CLAIM is also included for a system for recognizing and categorizing objects e.g. fruit, legumes, vegetables, flowers and boxes in semi-controlled environments. DESCRIPTION OF DRAWING(S) – The drawing shows a schematic view of an object recognizing and categorizing system. (Drawing includes non-English language text). Balancing device (1) Objects (2) Display system (3) Camera (5) Camera supporting arm (6)

Main Application Field

T04 (Computer Peripheral Equipment)

INVENTORS:

ANDERSON DE REZENDE ROCHA
DANIEL CABRINI HAUAGGE
JACQUES WAINER
SIOME KLEIN GOLDENSTEIN

416_AMBIENTES

Patent number: WO2011106854-A1;BR112012020417-A2

PATENT STATUS:

For information contact Inova Unicamp

FOR ADDITIONAL INFORMATION:

parcerias@inova.unicamp.br

+55 (19) 3521-5207 / 2607

This technology profile has been automatically generated.

COMPARTILHE:

TECNOLOGIAS RELACIONADAS: