A Structured Image Processing Operation Library to Automatically Isolate Weeds and Crops

Yaqeen Salatneh Ashqer, Marwan Bikdash, Chyi Lyi Liang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a computer-vision framework that isolate parts of the image pertaining to specific weeds and crops using image processing. We developed a structured Image Processing Operation (IPO) library, implemented in JSON format, for efficient representations of the algorithms needed to isolate the desired parts of the image. For each species, a specialized sequence of IPOs, along with their parameters, are obtained. Emphasis is placed on morphological image processing. The IPOs are mostly standard MATLAB functions, but specific and specialized image processing algorithms can be added as needed. We show preliminary success and discuss various aspects and complications.
Original languageEnglish
Title of host publication2019 IEEE SoutheastCon, SoutheastCon 2019
DOIs
StatePublished - 2019

Fingerprint

Dive into the research topics of 'A Structured Image Processing Operation Library to Automatically Isolate Weeds and Crops'. Together they form a unique fingerprint.

Cite this