Off-campus South Dakota State University users: To download campus access theses, please use the following link to log into our proxy server with your South Dakota State University ID and password.

Non-South Dakota State University users: Please talk to your librarian about requesting this thesis through interlibrary loan.


Yueming Li

Document Type

Thesis - University Access Only

Award Date


Degree Name

Master of Science (MS)

Department / School

Agricultural Engineering

First Advisor

Daniel Humburg


A necessary first step in the robotic harvest of mushrooms is the identification and location of mushrooms of harvestable size in the growing bed. One way to identify and locate mushrooms is to obtain the edge map for each mushroom. The edge map may be used to abstract the attribute of interest for a particular mushroom. Several previously developed edge detection algorithm were evaluated. A new algorithm was developed to separate mushrooms by using the intensity profile of mushrooms and simple morphological characteristics of the mushroom shapes. A new way of locating the starting point for edge-tracking was developed. A computer program that, given a mushroom image, can compute the diameters of individual mushrooms was developed. Another program was developed by modifying a previously developed algorithm. These two programs and a program that implemented a previously developed algorithm were e valuated by processing real mushroom images taken from a commercial mushroom grower. The two new algorithms developed processed 93 percent of the mushrooms with a relative error in diameter estimation of less than 10 percent. The existing algorithm that was implemented was able to identify 90 percent of the harvestable mushrooms in images with a relative error in diameter estimation of 10 percent.

Library of Congress Subject Headings

Mushrooms -- Selection -- Automation
Mushrooms -- Harvesting -- Automation
Computer vision




South Dakota State University