Review-1

Medicinal Plant Identification Using Machine Learning
TEAM MEMBERS:
KALPANA CHAWLA S – 20CS019
RIDHANYA R – 20CS041
SHAHIN NISHA S - 20CS048
GUIDE:
MR.R.RAJKUMAR
ASSOCIATE PROFESSOR
DEPARTMENT OF CSE
Medicinal Plant
Identification Page 1 1
OBJECTIVE
• Medicinal plant play a very active role in healthcare traditions. Ayurveda

is one of the oldest systems of medicinal science that is used even today.
• This project proposes A fully automated method for the recognition of
medicinal plants using computer vision and machine learning techniques
has been presented.
Medicinal Plant
Identification Page 2
ABSTRACT
• In this world there are thousands of plant species available, and plants
have medicinal values. Medicinal plants play a very active role in health-
care traditions. Ayurveda is one of the oldest of medicinal science that is
used even today.
• So proper identification of the medicinal plants has major benefits for not
only manufacturing medicines but also for forest department peoples, life
scientists, physicians, medication laboratories, government, and the pub-
lic.
• There may be chances to misidentification, which leads to certain side ef-
fects and may lead to serious problems. This chapter focuses on creation of
image dataset by using a mobile-based tool for image acquisition, which
helps to capture the structured images, and reduces the effort of data clean-
ing. This chapter also suggests that by ANN, CNN, or PNN classifier, the
classification can be done accurately.
Medicinal Plant
INTRODUCTION
• The world bears thousands of plant species, many of which have medicinal
values , others are close to extinction, and still others that are harmful to
man.
• Not only are plants an essential resources for human beings , but they form
the base of all food chains.
• To use and protect plant species, it is crucial to study and classify plants
correctly.
Medicinal Plant
EXISTING SYSTEM
• Several studies have been conducted in order to develop tools for the iden-
tification of plants during the last to years.
• One of the most authoritative works in the field of plant classification has
been done by Wu et al.
• From five basic geometric features , and then principle component Analy-
sis(PCA) is used for dimension reduction so that fewer inputs could be
sent to a probabilities neural network(PNN).
• They achieved an average accuracy of 90.3% with the Flavia dataset.
Medicinal Plant
PROBLEM DEFINITION
• Low Accuracy Achieved.

• Less number of plants identified in database which is small database in
real-time.
• Low Light Plant images will not be predicted correctly.
Medicinal Plant
PROPOSED SYSTEM
• The image processing techniques have been established to optimize the

footprints, input image is converted into greyscale, Edge detection on the
image.
• All the images in the dataset are read ,processed, and feature extracted,
raw data is loaded for classification of input image.
• This project proposed a Fuzzy C-means response , for extracting texture
features and preserves texture features of an image in frequencies.
• Selective scale and orientation filter is applied on input image to acquire
texture features.
• And segmentations requires separating the image from the background for
efficient classification.
• Next step is extracting templates of the footprints.
• In template matching process along with template updating is specified.
Medicinal Plant
FLOWCHART
Medicinal Plant
SOLUTION
• The proposed solution for identifying medicinal plants in the wild utilizes a
Convolutional Neural Network (CNN) – an artificial intelligence algorithm
designed to recognize patterns in images.
• To implement this, a diverse dataset of images featuring various medicinal
plants in their natural environments is collected. The CNN is then trained
this dataset, allowing it to learn and distinguish unique visual characteristic
of each plant.
• Subsequently, the trained model undergoes testing and validation on new,
previously unseen images to ensure accurate identification. The ultimate
goal to deploy the CNN in a practical tool or mobile application, enabling
users to capture images of plants in the wild, and have the algorithm
analyze these images to identify whether the plant is of medicinal value.
Medicinal Plant
SOLUTION
• This classification result and the details on the plant will be displayed on an
Interactive user interface. This approach offers a technologically
advanced and accessible means for herbalists, researchers, or enthusiasts to
quickly and accurately recognize medicinal plants during fieldwork. Contin-
uous improvement is achieved by refining The CNN's accuracy
through the incorporation of additional data and periodic model up-
dates, ensuring its effectiveness and relevance over time.
Medicinal Plant
CONCLUSION
• In this work , we addressed the problem of identifying the medicinal plant

species by the analysis of leaf images obtained directly from their habitat
and irrespective of lighting conditions.
• In this project, computer vision techniques have been used to extract sev-
eral shape-based features from the leaves of medicinal plants.
• Machine learning algorithms were then used to classify the leaves from 60
different plant species into their appropriate categories.
• The highest accuracy of 98.1% was obtained from the CNN classifier.
Medicinal Plant
THANK
YOU
MedicinalDetection
Intrusion Plant Sys-
Identification
tem With Enhanced Se- Page 12 11
curity

Review-1

Uploaded by

Copyright:

Available Formats

Review-1

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Review-1

Uploaded by

Copyright:

Available Formats

Medicinal Plant Identification Using Machine Learning

• Medicinal plant play a very active role in healthcare traditions. Ayurveda

• Low Accuracy Achieved.

• The image processing techniques have been established to optimize the

• In this work , we addressed the problem of identifying the medicinal plant

You might also like