Plant Leaf Recognition Using Machine Learning: A Review

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 355
Plant Leaf Recognition Using Machine Learning: A Review
Dinesh Suresh Bhadane1, Suvarna Patil2, Abhay Bhandari3, Danish Mahajan4, Ajay Katoch5,
Naman Abrol6
1,2 Assistant Professor, Dept. of Computer Engineering, Dr. D.Y. Patil Institute of Technology, Pimpri, Pune,
Maharashtra, India
3,4,5,6 B.E. student (Computer Engineering), Dr. D.Y. Patil Institute of Technology, Pimpri, Pune, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Plants classification through leaves is an
innovating and fascinating area of research that can provide
helpful information regarding plants. Plant identification
using their leaves is important in agriculture for weed
identification, plant growth assessment and classification of
diseases in plants. In addition to this, leaves can prove tobean
important factor in identification of plant species in
comparison to other parts of plants including flowers, stems,
and seeds. Although recent advancements in the field of
machine learning have made leaf classification much easier.
Identifying plant species using their leaf images proves to bea
challenge due to the vast variation among species and
variations in their shape, size, and color. This review paper
gives a detailed literature review of numerous tools and
algorithms used in plant classification, providing their
potential results and high accuracy. Some of the most
commonly used leaf classification methods include support
vector machines, convolutional neural networks, and decision
trees. These algorithms have many applications, including
estimating carbon uptake, predicting yields, and monitoring
plant health and biodiversity. Plant classification through
leaves can have applications in various areaofinterestsuch as
agriculture, botanical research, medicine (Ayurveda) etc. In
Ayurveda, plants are used as medicines providing solutions to
diabetes, digestive problems, diseases related to the heart,
liver disorder, etc. As machine learning and imagerecognition
evolve, plant classification will have an even more significant
impact in these fields.
Key Words: Machine Learning, Deep Learning, Plant
Recognition, Pre-processing, Feature Extraction
1. INTRODUCTION
Plants play a crucial role in the ecosystem and have been
used for various purposes throughout history. From
agriculture to medicine, plants have been a source of
sustenance and healing for humans. Identifying plants is
important in agriculture for weed detection, plant growth
estimation, and disease detection. Manual identification of
plants through their leaves is a time-consuming and tedious
job, which can be counteracted by the development of a
plant identification system. In recent years, technology has
made plant identification more accessible, and variousplant
identification systems have been developed. Leaves are the
most important part of a plant for classification as they
provide important information about the species. Leaf
characteristics such as the shape, size, and colour, as well as
the pattern of veins, hairs, or glands, can be used to
differentiate between different plant species. The
arrangement of leaves on the stem can also be used as a
distinguishing feature. Moreover, leaves remain on the
plants for most of the year, making them an ideal part to use
for plant identification. Machine learning algorithms have
become a popular method for plant identification. These
algorithms can recognize patterns and features in plant
leaves and use them to identify unknown plants accurately
and quickly. Various machine learning algorithmshavebeen
used in the development of plant identification models,such
as support vector machines,randomforests,anddeepneural
networks. Additionally, image processing techniques have
been used to extract features from plant leaves that can be
used for plant identification. This paper reviews various
studies conducted to develop plant identification systems
based on leaf characteristics. The paper discusses the
different machine learning algorithms used and the image
processing techniques applied to extract featuresfromplant
leaves. The paper also explores the different applications of
plant identification systems in agriculture and horticulture,
such as weed detection,plantgrowthestimation,anddisease
detection. The development of plant identification systems
has opened new opportunities in the identification of plants
with medicinal properties. Plants have been used as
medicines for centuries, and the identification of plantswith
medicinal properties can lead to the development of new
drugs and treatments for various health disorders. The
identification of plants with medicinal properties can be
done through their leaves, and the use of plant identification
systems can hasten the process. In conclusion, the
development of plant identification systems based on leaf
characteristics has numerous applications in agriculture,
horticulture, and medicine. The identification of plants
through their leaves has become more accessible, thanks to
technology and the development of machine learning
algorithms. The use of plant identification systems can help
in the detection of plant diseases, weed control, and plant
growth estimation, making it an essential tool in agriculture
and horticulture. The identification of plants with medicinal
properties can also be done through their leaves, leading to
the development of new drugs and treatments for various
health disorders. The paper aims to provide an overview of

various studies conducted on plant identification systems
and the different applicationsofplantidentificationsystems.
2. MOTIVATION
Plant leaf recognition is very interesting and essential field
with remarkable potential that impactsinvariousnumber of
fields such as agriculture, medicine, forestry, and
environmental protection.Byaccuratelyidentifyingdifferent
plant species based from their unique leaf features, we can
gain insight into their growth patterns, their response to
environmental factors, and their overall health. This
knowledge can help us develop more efficient and
sustainable agricultural practices,manage natural resources
better, and even discover new plant species. Additionally,
with rapid advances in machine learning and computer
vision, the development of automated leaf recognition
systems can greatly increase the speed andaccuracyofplant
identification, making it an essential tool for researchers,
farmers, and ecologists. Therefore, there is a great need for
motivated individuals to join the field and contribute their
skills and knowledge to advance our understanding of plant
biology and the natural world.
3. LITERATURE REVIEW
I. Leaf Analysis for Plant Recognition:
In this study, [1], a weighted K closest neighbor
search algorithm is used to propose a leaf analysis
system for plant identification. The system consists of
noise reduction preprocessing processes, feature
extraction for computing scale invariant feature
descriptors, and algorithmic matching of plant species.
The Leafsnap dataset is used by the authors to test the
system before it is put into use as a Windows phone
app.
II. A Mobile Application for Plant Recognition through
Deep Learning:
The paper [2] outlines a method for deep learning-
based automated plant and flower recognition. This
method makes use of video data to make up for any
information loss that can occur when comparing static
photographs of plants and flowers, in contrast to
conventional methods that only employ static images.
The approach's deep learning algorithms as well as the
procedure for gathering, scrubbing, and purging data
are described in the study. Also, a mobile iOS app is
provided, and the approach's results demonstrate that
122/125 plants and 47/50 genera may be identified
with a degree of confidence up to 95%. The utilization
of cloud-based resources to increase performance
speed is also covered in the study.
III. Tree Species Identification Based on Convolutional
Neural Networks:
This paper [3] suggests an efficient convolutional
neural network-based method for automatically
classifying tree species (CNNs). The examination of
numerous multi-dimensional characteristics of tree
leaves, such as color, shape, and veinsignatures,isdone
to carry out the identification. Since it can be difficult to
accurately identify a single leaf trait for a given tree
species, CNNs are used to combine the multi-
dimensional information.Preprocessingproceduresare
also used to increase the identification results'
reliability. The Leafsnap database is used to test the
proposed approach, and the results are good.
IV. A Leaf Recognition Approach to Plant Classification
Using Machine Learning:
The paper [4] introduces an automated method for
identifying plants through leaf recognition, which is an
important part of plant ecological research workflows.
The proposed methodology is simple as well as
efficient, which uses a combination of two texture
features (BOF and LBP) as inputs to a multiclass SVM
classifier. The method is evaluated using a leaf image
database and shows extremely effective results. Their
proposed method has great potential for practical
applications in plant recognition due to its
computational efficiency and ease of implementation
using computer vision techniques. Overall, this paper
provides a significant contribution to the field of plant
identification.
V. Plant identification using deep neural networks via
optimization of transfer learning parameters:
In this paper [5], deep convolutional neural
networks were utilized for the purpose of identifying
plant species captured in photographs. The
performance of different factorsthataffecttheaccuracy
of these networks was evaluated. Three popular and
significant deep learning architectures,suchasAlexNet,
GoogleNet, and VGGNet, were implemented for the
purpose of this study. Transfer learning was employed
using LifeCLEF 2015 planttask datasetsinordertofine-
tune the pre-trained models. Data augmentation
techniques based on image transforms such as
reflection, rotation, scaling, and translation were
applied to minimize the risk of overfitting. In addition,
the network parameters were adjusted and different
classifiers were combined to enhance overall
performance. The best combined system achieved an
accuracy of 80% approximately using the validationset
and an approximate inverse rank score of 0.752 using
official test set. Comparing these results with those of
the LifeCLEF 2015 plant identification campaign, the
top system's overall validation accuracy was improved

by 15% points and its overall inverse rank score on the
test set by 0.1. The top three competition participants
were also outperformed in all categories and their
system obtained second place in PlantCLEF 2016.
VI. Leaf Classification Project:
Using a shared dataset of leaf attributes, this paper
[6] analyses alternative machine learning methods for
classifying leaves. To analyze among effective and
ineffective categorization models, the authorscompare
and analyze the model outputs.
VII. Plant Recognition System based on Leaf Image:
The paper [7] suggests an image-based automatic
identification method based on leaf structure. To
identify plants from photographs of leaves, the system
makes use of attributes like shape, texture, vein
structure, and color. For the purpose of storing image
data and related information, the authors additionally
create a cloud-based database.
VIII. Leaf shape extraction for plant classification:
In order to classify plants, this paper [8] focuses on
leaf form extraction from photos. In order to extract
biometric properties of leaves for categorization, the
authors suggest employing a variety of operators and
image processing approaches. This paper states the
necessity for automated methods and shows howtime-
consuming manual classification is.
IX. A study on plant recognitionusingconventionalimage
processing and deep learning approaches:
The paper [9] proposes two approaches,traditional
and deep learning, to address this issue. In the
traditional approach, shape, texture, and color features
are extracted, and various classifiers are used for
classification. The deep learning approach involves
testing different deep learning architectures for plant
species recognition. Four datasets, including three
standard datasets and one real-time dataset, are used
for evaluation. The results demonstratethattheVGG16
CNN models outperformed traditional methods in
terms of accuracy. The combination of color channel
statistics, LBP, Hu, and Haralick featureswitha Random
Forest classifier achieveda plantidentificationaccuracy
of 82.38% for the Leaf12 dataset using the traditional
method. VGG 16 CNN architecture with logistic
regression achieved a greater accuracy of 97.14% for
the Leaf12 dataset, while VGG 19CNN architecturewith
logistic regression achieved an accuracy of 96.53% for
Folio, 96.25% for Flavia and 99.41% for Swedish
datasets, respectively.
X. Plant Identification Methodologies using Machine
Learning Algorithms:
The methods used are what determine how a plant
is identified, it is a process that has evolved over ages.
Identification of plants is important because it enables
the retrieval of necessary data related to various
species, which is necessaryforcertainapplications.This
paper [10] offers numerous methods and strategies
from various writers for identifying plants.
XI. Identification of Plants using Deeplearning:AReview:
Traditional methods ofplant identificationbasedon
physical characteristics can be time-consuming and
challenging. To address this issue, researchers have
explored the use of advanced technologiessuchasdeep
learning and image recognition to develop more
efficient plant identification methods. In a review of
academic literature published between 2015and2020,
it has been observed that convolutional neural
networks (CNNs), a type of deep learning algorithm,
have shown promising results in the area of plant
identification. This has led to the development of
various techniques and methods for leaf recognition
using CNNs. This paper [11] aims to contribute to the
existing body of literature on plant identification by
discussing the concepts of deep learning and different
leaf recognition methods. By analyzing the latest
research in this field, the paper provides an academic
database of knowledge that can be used to improve
plant identification and further advance the field of
ecology.
4. CONCLUSION
Manually identifying plants can be a really tiresomeprocess.
So, to make this task easy automated methods such as
machine learning and deep learning models can be
implemented. In this paper, different machine learning and
deep learning a0lgorithms for the purpose of plant
recognition through their leaves have been reviewed.
Authors of these papers have suggested various techniques
in order to achieve highest accuracy possible. These
techniques include algorithms such as Random Forest, K-
Nearest Neighbors, SVM classifier, Logistic Regression, etc.,
and popular deep learning architectures such as GoogleNet,
AlexNet, VGGNet and these techniques give different
accuracies if used on a single dataset.
5. REFERENCES
[1] Aparajita Sahay, Min Chen, “Leaf Analysis for Plant
Recognition”, 2016 7th IEEE International Conference
on Software Engineering and Service Science (ICSESS)
[2] Min Gao, Lang Lin, Richard O. Sinnott, “A Mobile
Application for Plant Recognition through Deep

Learning”, 2017 IEEE 13th International Conference on
eScience
[3] Hong Zhou, Chenjun Yan, Huahong Huang,“TreeSpecies
IdentificationBasedonConvolutional Neural Networks”,
2016 8th International Conference on Intelligent
Human-Machine Systems and Cybernetics
[4] Redha Ali, Russell Hardie, Almabrok Essa, “A Leaf
Recognition Approach to Plant Classification Using
Machine Learning”, 2018 IEEE
[5] Ghazi, M.M., “Neurocomputing” (2017),
http://dx.doi.org/10.1016/j.neucom.2017.01.018
[6] Jiacheng Hu, Yitao Liu, Jia Liu, “Leaf Classification
Project”, 2020 ECE228
[7] Swati P. Raut, Dr. A.S. Bhalchandra, “Plant Recognition
System based on Leaf Image”, ProceedingsoftheSecond
International Conference on Intelligent Computing and
Control Systems (ICICCS 2018)
[8] M.M. Amlekar, A.T. Gaikwad, R.R. Manza, P.L. Yannawar,
“Leaf Shape Extraction for Plant Classification”, 2015
International Conference on Pervasive Computing
(ICPC)
[9] S. Anubha Pearline, V. Sathiesh Kumar, S. Harini, “A
study on plant recognition using conventional image
processing and deep learning approaches”, Journal of
Intelligent & Fuzzy Systems 36 (2019)
[10] Skanda H N, Smitha S Karanth, Suvijith S, Swathi K S,
Pragati P, “Plant Identification Methodologies using
Machine Learning Algorithms”, International Journal of
Engineering Research & Technology (IJERT)Vol.8Issue
03, March-2019
[11] Rakibul Sk, Ankita Wadhawan, “Identification of Plants
Using Deep Learning: A Review”, International
Symposium on Intelligent Control (ISIC) 2021

Plant Leaf Recognition Using Machine Learning: A Review

More Related Content

Similar to Plant Leaf Recognition Using Machine Learning: A Review (20)

More from IRJET Journal (20)

Recently uploaded (20)

Plant Leaf Recognition Using Machine Learning: A Review