|Sanders, Timothy - Tim|
Submitted to: American Peanut Research and Education Society Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 7/10/1998
Publication Date: N/A
Citation: Interpretive Summary:
Technical Abstract: The hull-scrape method is the tool of choice for determination of peanut pod maturity distribution and harvest recommendations for certain peanut cultivars and growing regions. The method currently employs manual color sorting of a representative pod population sample into pre-determined color classes. General-use hardware and software components are commercially available for implementation of color image analysis to hull-scrape color sorting for harvest prediction. Customization and integration of these components is necessary to establish procedures and protocols for individual image analysis applications. The objective of this study was to design and test a color image acquisition and analysis system and establish and test a procedure for color classification of peanut pods based on the established hull-scrape methodology. A system prototype was assembled, using a CCD-based color video camera with RGB output coupled to a personal computer equipped with an RGB video input/output card for image acquisition. Commercial color classification software was used to build color reference classes based on manually generated color classes (yellow, orange A, orange B, brown and black). Generated color distributions were used to sort the test pods in sets of 50 by class comparison for a variety of pod arrangements and distributions. Resulting classification was generally within 1 color class relative to manually sorted samples when one visible surface of each pod was sampled. Image sampling and classification for a 50-pod sample were performed in under 1 second using an Intel 486 CPU based system. This objective color image analysis and classification methodology could significantly improve the accuracy, repeatability, and efficiency of hull-scrape methodology to determine peanut pod maturity.