PLANT LEAF IDENTIFICATION

2020UIN3314 DIVANGI CHAUDHARY

2020UIN3318 ROHIT PATHAK
2020UIN3349 SAHIL

Under the Guidance of Dr. Nisha Kandhoul

BTP-II Final Presentation
INITC23 B. Tech Project - II
PLANT LEAF
IDENTIFICATION
Identification of plants through plant leaves on the
basis of their shape, color and texture features
using digital image processing techniques
 CONTENT
● Introduction
● Project Objective
● Motivation Behind Project
● Literature Survey
● Gaps Identified
● Proposed Model
● Methodology
● Implementation
● Results
● Conclusion
● Future work
● References
INTRODUCTION

Plant leaf identification is a new and fascinating area of

research currently adopted and explored by various ML works
for improved industry applications. Traditional knowledge of
plants can be utilized in a framework able to detect leaves of
different species in real time with maximum precision.
As Agriculture and Medicinal industries are technologically
booming, new innovations like these play a role in easing the
traditional requirements and bondages of time and effort.
Plant leaf identification is a system which is able to classify
different species of plants on the basis of their leaves using
digital image processing techniques.
PROJECT OBJECTIVE

● The main objective of this research was to compare the performance of different machine
learning algorithms and select the best algorithm to be used for further development of a
mobile application to identify herbal, fruits, and vegetable plants.

● To develop an accurate and efficient placement prediction model using Machine Learning (ML).
Objective of the Project Identification of plants through plant leaves on the basis of their shape,
color and texture features using digital image processing techniques

● Primary focus: Support Vector Machine (SVM) algorithm.

● Secondary goal: Compare SVM's effectiveness with other ML algorithms.

MOTIVATION BEHIND PROJECT

A project focused on plant identification through machine learning is

driven by diverse motivations, spanning environmental conservation,
biodiversity monitoring, agriculture, and education. It's pivotal for
biodiversity conservation, enabling quick identification and protection
of endangered species. In ecological research, machine learning
analyzes large datasets, deepening our understanding of ecosystems.
Agriculture benefits from rapid plant identification for crop
management, disease detection, and resource optimization. Detecting
invasive species early is crucial for ecosystem health. Machine
learning aids in educational tools, fostering biodiversity appreciation.
Citizen science engagement supports data collection and raises
awareness. Accurate plant identification informs conservation policies
and contributes to global environmental monitoring, making the
project a comprehensive solution for ecological challenges
LITERATURE SURVEY
● The main objective of this research was to compare the performance of different machine
learning algorithms and select the best algorithm to be used for further development of a
mobile application to identify herbal, fruits, and vegetable plants. In this regard, this article
focuses on pre-processing and effective classification of manually collected leaves data sets.
Subsequently, five machine learning algorithms were employed on the dataset for
classification after normalizing the data.
● In this study, images from Swedish leaf dataset have been used, which contains 1,125 images
of 15 different species. This is followed by pre-processing using Gaussian filtering
mechanism and then texture and color features have been extracted. Finally, classification
has been done using Multiclass-support vector machine, which achieved accuracy of nearly
93.26%, which we aim to enhance further.
● 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.

● In this work, a recognition system capable of identifying plants by using the images to f their leaves has
been developed. A mobile application has been developed to allow the user to take pictures and upload
them to server. The server runs pre processing and feature extraction techniques on image before a
pattern matcher compares the information from this image with that on database in order to get
matches. The features being length and width of leaves, area and perimeter, hull area, hull perimeter, a
distance map among vertical and horizontal axes, a colour histogram and centroid based radial distance
map. A kNN classifier was implemented and achieved an accuracy of 87.3 percent.

● This paper presents the extraction of plant leaf gas alongside other features from the camera images or a
dataset of images by applying a convolutional neural network (CNN). The extraction of leaf gas enables
identification of the actual level of chlorophyll (Ch) and nitrogen (N) which may help to interpret future
predictions. This includes the study of texture and geometric features, analyzing ratio of Ch and N in
both healthy and dead leaves, and the study of color-based methods via CNN.
GAPS IDENTIFIED
● Sensitivity to Hyperparameters (KNN, Random Forest): - KNN's performance is sensitive to the
choice of the number of neighbors (k), and selecting an inappropriate k-value can lead to
suboptimal predictions. Similarly, Random Forest performance is impacted by the number of
trees and other hyperparameters, making tuning crucial but challenging.

● Overfitting (KNN, Logistic Regression, Random Forest): - All three algorithms are susceptible to
overfitting, especially when dealing with noisy or complex datasets. Logistic Regression and
Random Forest may overfit if the model is too complex or the dataset is not representative.

● Difficulty in Handling Missing Data (KNN, Logistic Regression): - KNN is sensitive to missing data,
and imputing missing values can introduce bias. Logistic Regression also requires handling
missing data appropriately, which can be challenging and may introduce potential inaccuracies.
PROPOSED MODEL
 METHODOLOGY
PRE - PROCESSING

1. Conversion of RGB to Grayscale image

2. Smoothing image using Gaussian filter
3. Adaptive image thresholding using Otsu's thresholding method
4. Closing of holes using Morphological Transformation
5. Boundary extraction using contours

FEATURE EXTRACTION

Various types of leaf features were extracted from the pre-processed image which are listed as follows:

1. Shape based features : physiological length,physiological width, area, perimeter, aspect ratio,
rectangularity, circularity
2. Color based features : mean and standard deviations of R,G and B channels
3. Texture based features : contrast, correlation, inverse difference moments, entropy
Model building and testing

1. Support Vector Machine Classifier was used as the model to classify the plant species
2. Features were then scaled using StandardScaler
3. Also parameter tuning was done to find the appropriate hyperparameters of the model using
GridSearchCV

Import the dataset and libraries. numpy, pandas, seaborn, matplotlib are used in this implementation. “df”
variable is a pandas dataframe containing the dataset.
 IMPLEMENTATION
● Conversion of RGB to Grayscale image
● Smoothing image using Guassian filter of size (25,25).
● 44Adaptive image thresholding using Otsu's threshold method
● Closing of holes using Morphological Transformation
● Boundary extraction (Using sobel filter and contour)
● Calculation of Shaped based Features (Calculation of Moments ,Rectangularity ,
Aspect Ratio , Circularity)
● Calculation of colour based features ( Mean and Standard deviation).
● Calculation of Texture based features (contrast, correlation, entropy.)
● Import the dataset and libraries. numpy, pandas, seaborn, matplotlib are used in
this implementation. “df” variable is a pandas dataframe containing the dataset.
● Clean the dataset by removing all the rows containing missing values.
● As the dataset was already preprocessed by now and it contained various
attributes such as area ,perimeter, physiological_length, physiological_width,
aspect_ratio etc.
● Train test split of data was then performed which helps to evaluate the ability of
machine learning models to generalize to new, unseen objects. It also prevents
overfitting, where the model performs well on training material but not well in
new situations. Using the validation process, we recalibrate the model to achieve
better performance on unseen data.
● Feature scaling was then performed to prevent overfitting and to normalize the
data that we used,imported via standardScalar.
● Now a model is trained on the Augmented/Preprocessed Dataset to predict the
best classifier for each row. keeping best classifier column as the dependent
variable (Y variable/target variable)
● Finally, the proposed Plant leaf identifier Model is evaluated on the original
cleaned preprocessed test dataset (“X_test_scaled”, “Y_test”)
● 7. Another step is done that is Perfoming parameter tuning of the model by taking
the 4 parameters to fine tune them again, them being parameters = [{'kernel':
['rbf'], 'gamma': [1e-4, 1e-3, 0.01, 0.1, 0.2, 0.5], 'C': [1, 10, 100, 1000]},{'kernel':
['linear'], 'C': [1, 10, 100, 1000]}].
● The result of means was stored in “mean_test_score” , while the standard result
was assigned as “std_test_score”.
● Dimensity Reduction using PCA was done to enhance the performance
furthermore.
 RESULTS

1. We have evaluated our proposed Identification of plants through plant leaves

on four metrics namely accuracy, f1-score, precision and recall. The results are
as follows
Accuracy: 0.91 Precision: 0.90 Recall: 0.89 F1-score: 0.415

2. For comparison we also evaluated traditional, ensemble machine learning

models on the same metrics.
3. It can be observed that SVM performs better than all the machine learning
models given in the above table. It performs better than the rest of the models
giving a better accuracy, better precision, better recall and better f1-score.

4.The algorithm is successful in the classification of plants through plant leaves on

the basis of their features extracted using digital image processing techniques as
the result is shown below too :
 CONCLUSION
1. It was realised on a collection of leaf characteristics that have shown promise in
leaf datasets. 90% greater accuracy was attained. This programme is helpful to
both experts and non-experts interested in learning about plants because of the
accuracy of the identification.
2. We began by Preprocessing the image by using various methodologies and
then jumped on to extract the features be it shaped based or color based
followed by model building and testing it out where the SVM ,KNN and other
models were used to classify the plant species.
3. After that, a large number of features were scaled using standard scalar, and
GridSearchCV was used to tune the model's parameters and determine the
proper hyperparameters.
 FUTURE WORK TO BE DONE
● Adoption of multiclass svm to improve accuracy and range of plant species.
● Scope of deep learning algorithms to improve results upto 99 percent in leave
detection
● Mobile image application includes a broad range of detection and recognition.
● Exploration of techniques to create a background subtraction function to remove
background from mobile camera captured leaf images
● SVM's efficiency in high-dimensional spaces, ability to handle non-linearity,
robustness against overfitting, and effectiveness in handling imbalanced data make it
a favorable choice for placement prediction, especially when dealing with complex
and diverse datasets commonly encountered in educational and career domains.
However, the choice of the most suitable algorithm ultimately depends on the
specific characteristics of the dataset and the particular goals of the prediction task.
REFERENCES
● Dissanayake, Charith & Kumara, W.G.C.W.. (2021). Plant Leaf Identification based on
Machine Learning Algorithms.
● Kaur, Surleen & Kaur, Prabhpreet. (2019). Plant Species Identification based on Plant Leaf
Using Computer Vision and Machine Learning Techniques. Journal of Multimedia Information
System. 6. 49- 60. 10.33851/JMIS.2019.6.2.49.
● Dinesh Suresh Bhadane, Patil S. Et al, Plant Leaf Recognition Using Machine Learning: A
Review .
● Munisami T., Ramsurn M. Et al, Plant leaf recognition using shape features and color
histogram with k-nearest neighbours classifiers.
● Ahmad M., Ashiq S. Et al, Feature Extraction of Plant Leaf Using Deep Learning.
● X. F. Wang, et al. "Recognition of Leaf Images Based on Shape Features Using a Hypersphere
Classifier". International Conference on Intelligent Computing, 2005. Pp87-96
● J.-X. Du, X.-F. Wang, and G.-J. Zhang, "Leaf shape based plant species recognition," Applied
Mathematics and Computation, vol. 185, 2007.
● P. Panchal, V. C. Raman and S. Mantri, "Plant Diseases Detection and Classification using
Machine Learning Models", (CSITSS).
● R. G. de Luna, E. P. Dadios and A. Bandala, "Automated Image Capturing System for Deep
Learning-based Tomato Plant Leaf Disease Detection and Recognition", IEEE Region 10
Conference.
● S. Kumar, K. Prasad, A. Srilekha, T. Suman, B. P. Rao and J. N. Vamshi Krishna, "Leaf Disease
Detection and Classification based on Machine Learning", (ICST CEE).
● J. W. Tan, S. Chang, S. Binti, Abdul Kareem, H. J. Yap and K. Yong, Deep learning for plant
species classification using leaf vein morpho metric, pp. 1-1, 2018.
● I. Motoyoshi, S. Nishida, L. Sharan, and E. H. Adelson, “Image statistics and the perception of
surface qualities,” Nature, vol. 447, May 2007.
● B. C. Heymans, J. P. Onema, and J. O. Kuti, “A neural network for opuntia leaf-form
recognition,” in Proceedings of IEEE International Joint Conference on Neural Networks, 1991
● F. Gouveia, V. Filipe, M. Reis, C. Couto, and J. Bulas-Cruz, “Biometry: the characterisation of
chestnut-tree leaves using computer vision,” in Proceedings of IEEE International
Symposium on Industrial Electronics, Guimar˜aes, Portugal, 1997
2020UIN3314:Rohit Pathak
2020UIN3318:Divangi
Chaudhary
2020UIN3349:Sahil