Plant Identification Via Leaf Classification Using Color and Biometric Features
Journal Title: ISPEC Journal of Agricultural Sciences - Year 2021, Vol 5, Issue 2
Abstract
Plants that are of great importance for humans and other living things are an integral part of our ecosystem. In today's world, where many plant species are at risk of disappearance, the identification of plants helps to protect and survive all natural life. There are many studies presented in the literature for plant identification. The most popular of these identification methods is leaf based classification. The reason for choosing leaves in this classification is that they are easier to obtain than other biometric components such as flowers available for a short period of time. Various biometric properties of the leaf must be determined for leaf classifications. In traditionally it is time consuming and expensive to perform this process visually by experts. In this article, various leaf biometric features obtained by digital image processing methods are used as the feature extraction step for automatic leaf classification. As the classification algorithms, Naive Bayes, Linear Regression, Multilayer Perceptron, Decision Tree and Random Forest are used. According to the experimental results using the training set as the test set, 100% recognition rate is obtained for Random Forest classification algorithm and 96% recognition rate is obtained in 30-fold cross validation for Linear Regression classification algorithm.
Authors and Affiliations
Çiğdem TURHAL
Investigation of The Availability of Children's Playgrounds By Disabled Children In Line With The Universal Design Principles: Van City Example
Games are indispensable in children's lives. Playgrounds are also important for disabled individuals, who are a part of our lives, to hold on to life, socialize and develop. It should be ensured that disabled children ca...
Determination of the Effect of Different Sowing Dates on Growth and Yield Parameters of Some Dry Bean (Phaseolus vulgaris L.) Varieties
The experiment was carried out at Dicle University, Faculty of Agriculture Department of Field Crops in 2018 spring and summer season. The aim of this study was to evaluate the effect of different sowing dates (March 10,...
Germination Characteristics and Seedling Development of Hungarian Vetch (Vicia pannonica Crantz.) in Different Priming Application
In the study, 3 different priming processes at different soaking times were applied in order to promote germination and seedling characteristics of Hungarian vetch (Vicia pannonica Crantz.), which is one of the high qual...
Cultivation Possibilities of Lemon Balm (Melissa officinalis L.) in the Central Anatolia Region of Turkey
This study was carried out to determine yield and quality characteristics of Lemon balm (M. officinalis L.) in in 7 districts (7 locations) under Kayseri ecological conditions for 3 years in 2015-2017. In this research,...
Determination of Some Physical and Physiological Properties of Seeds of Different Grass Pea (Lathyrus sativus L.) Genotypes
Grass pea (Lathyrus sativus) is a naturally growing crop in Turkey and it is considered a valuable fodder resource to improve soil properties and livestock farming. This study was carried out in the laboratories of Bingo...