How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning

The detection of weeds with computer vision without the help of an expert is important for scientific studies and other purposes. The images used for the detection of weeds are recorded under controlled conditions and used in image processing-deep learning methods. In this study, the images of 3-4-l...

Full description

Saved in:
Bibliographic Details
Main Authors: Mustafa Guzel, Bulent Turan, Izzet Kadioglu, Bahadir Sin, Alper Basturk, Khaled R. Ahmed
Format: Article
Language:English
Published: Hasan Eleroğlu 2022-08-01
Series:Turkish Journal of Agriculture: Food Science and Technology
Subjects:
Online Access:http://www.agrifoodscience.com/index.php/TURJAF/article/view/5183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414537243000832
author Mustafa Guzel
Bulent Turan
Izzet Kadioglu
Bahadir Sin
Alper Basturk
Khaled R. Ahmed
author_facet Mustafa Guzel
Bulent Turan
Izzet Kadioglu
Bahadir Sin
Alper Basturk
Khaled R. Ahmed
author_sort Mustafa Guzel
collection DOAJ
description The detection of weeds with computer vision without the help of an expert is important for scientific studies and other purposes. The images used for the detection of weeds are recorded under controlled conditions and used in image processing-deep learning methods. In this study, the images of 3-4-leaf (true-leaf) periods of the wild mustard (Sinapis arvensis) plant, which is the critical process for chemical control, were recorded from its natural environment by a drone. The datasets were included 50-100-250-500 and 1 000 raw images and were augmented by image preprocessing methods. Totally 12 different augmentation methods used and datasets were examined for understand how to affects the numbers of images on training-validation performance. YOLOv5 was used as a deep learning method and results of the datasets were evaluated with the Confusion Matrix, Metrics-Precision, and Train-Object Loss. For results of Confusion Matrix where 1 000 images gave the highest results with TP (True Positive) 80% and FP (False Positive) 20%. The TP-FP ratios of 500, 250, 100 and 50 image numbers were respectively; 65%-35%, 43%-57%, 0%-100% and 0%-100%. With 100 and 50 images, the system did not show any TP success. The highest metrics-precision ratio was found 92.52% for 1 000 images set and for 500 and 250 image sets respectively; 88.34% and 79.87%. The 100 and 50 images datasets did not show any metrics-precision ratio. The minimum object loss ratio was 5% at 50th epochs in the 100 images dataset. This dataset was followed by other 50, 250, 500, and 1 000 images respectively; 5.4%, 6.14%, 6.16%, and 8.07%.
format Article
id doaj-art-7355df97c0c04747a0db4fa8c2f71901
institution Kabale University
issn 2148-127X
language English
publishDate 2022-08-01
publisher Hasan Eleroğlu
record_format Article
series Turkish Journal of Agriculture: Food Science and Technology
spelling doaj-art-7355df97c0c04747a0db4fa8c2f719012025-08-20T03:33:49ZengHasan EleroğluTurkish Journal of Agriculture: Food Science and Technology2148-127X2022-08-011081441144610.24925/turjaf.v10i8.1441-1446.51832557How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep LearningMustafa Guzel0Bulent Turan1Izzet Kadioglu2Bahadir Sin3Alper Basturk4Khaled R. Ahmed5Department of Plant, Soil, and Agricultural Systems, Southern Illinois University, CarbondaleFaculty of Engineering and Natural Science, Tokat Gaziosmanpaşa University, 60250 TokatAnamur/MersinFaculty of Agriculture, Sakarya University of Applied Science, 54050 SakaryaFaculty of Engineering, Erciyes University, 38039 KayseriSchool of Computing, Southern Illinois University, Carbondale, ILThe detection of weeds with computer vision without the help of an expert is important for scientific studies and other purposes. The images used for the detection of weeds are recorded under controlled conditions and used in image processing-deep learning methods. In this study, the images of 3-4-leaf (true-leaf) periods of the wild mustard (Sinapis arvensis) plant, which is the critical process for chemical control, were recorded from its natural environment by a drone. The datasets were included 50-100-250-500 and 1 000 raw images and were augmented by image preprocessing methods. Totally 12 different augmentation methods used and datasets were examined for understand how to affects the numbers of images on training-validation performance. YOLOv5 was used as a deep learning method and results of the datasets were evaluated with the Confusion Matrix, Metrics-Precision, and Train-Object Loss. For results of Confusion Matrix where 1 000 images gave the highest results with TP (True Positive) 80% and FP (False Positive) 20%. The TP-FP ratios of 500, 250, 100 and 50 image numbers were respectively; 65%-35%, 43%-57%, 0%-100% and 0%-100%. With 100 and 50 images, the system did not show any TP success. The highest metrics-precision ratio was found 92.52% for 1 000 images set and for 500 and 250 image sets respectively; 88.34% and 79.87%. The 100 and 50 images datasets did not show any metrics-precision ratio. The minimum object loss ratio was 5% at 50th epochs in the 100 images dataset. This dataset was followed by other 50, 250, 500, and 1 000 images respectively; 5.4%, 6.14%, 6.16%, and 8.07%.http://www.agrifoodscience.com/index.php/TURJAF/article/view/5183weed detectiondeep learningreal time detectionsinapis arvensisconfusion matrix
spellingShingle Mustafa Guzel
Bulent Turan
Izzet Kadioglu
Bahadir Sin
Alper Basturk
Khaled R. Ahmed
How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
Turkish Journal of Agriculture: Food Science and Technology
weed detection
deep learning
real time detection
sinapis arvensis
confusion matrix
title How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
title_full How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
title_fullStr How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
title_full_unstemmed How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
title_short How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning
title_sort how to affect the number of images on the success rate for detection of weeds with deep learning
topic weed detection
deep learning
real time detection
sinapis arvensis
confusion matrix
url http://www.agrifoodscience.com/index.php/TURJAF/article/view/5183
work_keys_str_mv AT mustafaguzel howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning
AT bulentturan howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning
AT izzetkadioglu howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning
AT bahadirsin howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning
AT alperbasturk howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning
AT khaledrahmed howtoaffectthenumberofimagesonthesuccessratefordetectionofweedswithdeeplearning