Produce recognition system

A system for recognizing objects comprising:

• a. a light source for illuminating a scene, the light source having a non-monochromatic light frequency distribution that is constant over a period of time, the light source controlled to illuminate the scene at a first illumination level and at a second illumination level lower than the first illumination level, the scene comprising one or more of the objects, being a target object, and a background;
• b. a computer system having a memory storage, a visual input device for creating a scene image including a target object image of the target object and a background image, and an algorithm that produces a segmented target object image by segmenting the target object image from the background image in the scene image, the algorithm segmenting the target object image by comparing a first scene image taken at the first illumination level with a second scene image taken at a second illumination level;
• c. a plurality of reference normalized histograms, each of the reference normalized histograms being a histogram of a feature associated with an associated segmented reference object, the reference normalized histograms being stored in the computer memory storage;
• and
• d. a normalizer that produces one or more target normalized histograms, each of the target normalized histograms being a histogram of a feature of the segmented target object image, the normalizer normalizing each of the target normalized histograms the same way as the reference normalized histograms are normalized,
• whereby one or more of the target normalized histograms, is compared with one or more of the reference normalized histograms and the target object is recognized as the associated segmented reference object if the target and reference normalized histograms of a feature match.

A system for recognizing objects comprising:

• a. a light source for illuminating a scene, the light source having a non-monochromatic light frequency distribution that is constant over a period of time, the light source controlled to illuminate the scene at a first illumination level and at a second illumination level lower than the first illumination level, the scene comprising one or more of the objects, being a target object, and a background;
• b. a computer system having a memory storage, a visual input device for creating a scene image including a target object image and a background image, and an algorithm that produces a segmented target object image by segmenting the target object image from the background image in the scene image, the algorithm segmenting the target object image by comparing a first scene image taken at the first illumination level with a second scene image taken at the second illumination level;
• c. a plurality of reference normalized histograms, each reference normalized histogram being a histogram of a feature associated with a segmented reference object, the reference normalized histograms being stored in the computer memory storage;
• and
• d. a normalizer that produces one or more target normalized histograms, each of the target normalized histograms being a histogram of a feature of the segmented target object image, the the normalizer normalizing the target normalized histograms the same way as the reference normalized histograms are normalized;
• and
• e. a means for determining if an unrecognized target object image meets a set of storage criteria,
• whereby one or more of the target normalized histograms is compared with one or more of the reference normalized histograms and the target object is not recognized as the associated segmented reference object because the target and reference histograms of a feature do not match and the target normalized histogram is stored in memory storage if it meets the set of storage criteria.

A method for recognizing objects comprising the steps of:

• a. illuminating the one or more of the objects, the illuminated objects being a target object, with a light source, the light source having a non-monochromatic light frequency distribution that is constant over a period of time;
• b. creating a scene image with a computer system having a visual input device, the scene image comprising a target object image and a background image, the computer system having a memory storage an algorithm for producing a segmented target object image by segmenting the target object image from the background image of the scene;
• c. producing one or more target normalized characterizations, each target normalized characterization being a characterization of a feature of the segmented target object image
• d. comparing one or more of the target normalized characterizations to one or more reference normalized characterization in memory storage, each reference characterization of a feature associated with a segmented reference object;
• and
• e. recognizing the target object as a reference object when one or more or the target normalized characterizations matches one or more of the reference normalized characterizations.