Weed Detection Using SVMs
Journal Title: Engineering, Technology & Applied Science Research - Year 2018, Vol 8, Issue 1
Abstract
The major concern in Pakistani agriculture is the reduction of growing weed. This research aims to provide a weed detection tool for future agri-robots. The weed detection tool incorporates the use of machine-learning procedure explicitly implementing Support Vector Machines (SVMs) and blob analysis for the effective classification of crop and weed. Weed revealing is based on characteristic features i.e. red green blue (RGB) components which differentiate soil and plant. Morphological features—centroidand length aid to distinguish shape of crop and weed leaves. Following feature extraction, the positive and negative margins are separated by a hyper-plane. The separating hyper-plane acts as the decision surface. Sample input consists of multiple digital field images of carrot crops. Training samples of seventy two images are taken. Accuracy of the outcomes discloses that SVM and blob analysis attain above 50-95% accuracy.
Authors and Affiliations
S. Murawwat, A. Qureshi, S. Ahmad, Y. Shahid
Keywords
Related Articles
- EP ID EP155841
- DOI -
- Views 219
- Downloads 0
Evaluation of E-Commerce Website Functionality Using a Mamdani Fuzzy System
The majority of leader companies are running their businesses using online E-commerce websites. These E-commerce websites are becoming significant revenue drivers and major retailers. Hence, it is critical to evaluate th...
Considering FACTS in Optimal Transmission Expansion Planning
The expansion of power transmission systems is an important part of the expansion of power systems that requires enormous investment costs. Since the construction of new transmission lines is very expensive, it is necess...
The “Stick-Slip” Phenomenon During the Active Earth Pressure Failure of a Granular Soil of Analogical Material
The aim of this paper is to highlight the "stick-slip" phenomenon in the mechanisms of failure related to active earth pressure of an analogical material simulating a granular medium. For this, a two-dimensional small-s...
Color Channel Characteristics (CCC) for Efficient Digital Image Forensics
Digital image forgery has become extremely easy as low-cost image processing programs are readily available. Digital image forensics is a science of classifying images as authentic or manipulated. This paper aims at impl...
Optimal Allocation of DSTATCOM in Distribution Network Using Whale Optimization Algorithm
This paper deals with a new approach implemented to decrease power losses and improve voltage profile in distribution networks using Distribution STATic COMpensator (DSTATCOM). DSTATCOM location can be determined by the...