Back to results
US 12,614,264 B2Granted
Non-destructive method to predict shelf life and maturity of perishable commodities
OwnerShubham Chandrainventor
Life of this patent
Estimating the term…
Abstract
A non-destructive method to predict the shelf life and maturity of perishable commodities using an intelligent vision system is presented here. The system includes a conventional camera and a vision processor (including shelf-life matrix, defect matrix and maturity matrix specific to each perishable commodity) which automatically determines ready for harvest condition, and the remaining shelf life of the perishable commodity.
Claims1
A computer-implemented method for predicting a remaining shelf life of a fruit or vegetable, wherein at least one processor and at least one memory are configured to perform the method comprising:
- capturing, using an image capture device, an image of said fruit or vegetable;
- cropping and resizing the image to isolate an area of interest;
- separating Red, Green, and Blue (RGB) channels of pixel values corresponding to the cropped image,
- and dissecting the cropped image into a plurality of CIELAB color space values using the separated RGB channels;
- comparing the dissected CIELAB color space values with predefined CIELAB color space values corresponding to the type of said fruit or vegetable, the predefined CIELAB color space values being organized into separate predefined shelf-life, defect, and maturity matrices;
- wherein comparing the dissected CIELAB color space values comprises:
- matching at least a Hue-max pixel value of the dissected CIELAB color space values with a known Hue-max pixel value of the predefined maturity matrix;
- and
- matching at least a Hue-avg pixel value of the dissected CIELAB color space values with a known Hue-avg pixel value of the predefined maturity matrix;
- wherein the predefined maturity matrix correlates a plurality of maturity stages of the type of said fruit or vegetable with a plurality of ranges of predefined CIELAB color space values;
- predicting a remaining shelf life of said fruit or vegetable based on the comparison of the dissected CIELAB color space values with the predefined shelf-life, defect, and maturity matrices;
- and transmitting the predicted remaining shelf life to an automated system comprising at least one of a drone-based monitoring system or a robotic arm.
9 more elements
Dependencies are inferred from the claim text.