Application of Image Processing in Weed Management

Please enable javascript in your browser.

Jahromizadeh, Pardis | 2017

540 Viewed

Type of Document: M.Sc. Thesis
Language: English
Document No: 49836 (55)
University: Sharif University of Technology, International Campus, Kish Island
Department: Science and Engineering
Advisor(s): Haj Sadeghi, Khosrow
Abstract:
Weed management is the important issue in agriculture. Using herbicides is one of the strategies to control weed. But using huge amount of herbicides are destructive for environment. Smart spraying system is an impressive solution for this problem. This system detects weeds and sprays just them instead of spraying overall field. In this thesis a new method for plant detection is presented by using Lab color space. We determine the type of plants (broadleaf/grass) to spray specific herbicides onto specific type of plant. One feature of grass plants (the parallel edges of leaf) is used to detect grass plants. A convolutional neural network with four layers and fuzzy logic are used to separate plants of image, then a pre-trained convolutional neural network, namely VGG-f, and Support Vector Machine (SVM) are used to classify the type of single plant. This structure is also used to classify weed/crop if their types are the same
Keywords:
Fuzzy Logic ; Convolutional Neural Network ; Support Vector Machine (SVM) ; Weed Management ; Smart Spraying System

No TOC