A FLOWER RECOGNITION SYSTEM BASED ON IMAGE PROCESSING

AND NEURAL NETWORK

Guided By

Mr.S. Aravind AP/ECE

.

BATCH MEMBERS:

K.AMUTHAPRIYA, 921818106001

Final year ECE

 ABSTRACT

 In this paper we are recognised the flowers based on edge and color characterization

This paper tries to introduce convolution neural networks to efficiently identify a flower by

just feeding an image of the flower to be recognized.

In this system taking an image in your mobile camera, uploading it and just clicking the

predict button is all that is needed to know more about a beautiful flower that you have just

seen.
INTRODUCTION

 In this paper ,I will introduce to a machine learning project on

flower recognition with python.
 Flower recognition uses the edge and colour characteristics of
flower images to classify flowers
 We are using the neural network is CNN.That is
Convolutional neural network is a class of artificial neural
network
 The dataset I am using here for 103 datasets
 Data collection is based on Kaggle dataset
 LITERATURE SURVEY
TITLE METHOD
Flower Identification System by The flower is identified based on
Image Processing color , shape, texture, petals and
features.
Automated Flower Species In the proposed to have a strategy
Detection and Recognition using for characterization of blossoms
Neural Network utilizing Neural Network (NN)
classifier.
A bloom picture is divided utilizing
an edge based technique.
Image Based Recognition of plants First, a new semi-automatic method
for conifers identification based on
images of was proposed.
The method’s inputs are the
coordinates of two branch-points.
DRAWBACK
We found that for better
performance in segmentation, the
user should draw a rectangular
frame to fit with the flower and
try not to overlap the frame with
bigger part of background
because the algorithm would
consider the background as the
same type.
It cannot present recognition of
flower type it’s only recognise
the flower type.
The challenge is a result of the
poor detection and accuracy is
very low.
DATA FLOW DIAGRAM
 PROPOSED SYSTEM
Image acquisition: This step involves collecting images that can be used to train the model so
that later when it comes across an unknown image, it can identify the flower based on the

knowledge acquired during the training phase.

Image Preprocessing: Here the images collected in the previous step were resized and
augmented to increase the efficiency of the model. During augmentation, the size of the dataset

would be increased by performing operations such as rotation, shear etc. Then the image will

be split into 75% training and 25% testing sets.

Training Phase: This is the step where the actual training of the model takes place. In this phase
the model extracts features such as color and shape of the flower used for training. Each of the
 PROPOSED SYSTEM Contd..
Validation phase: Once the model completes its training from the training set it tries to improve
itself by tuning its weight values. The loss function used is categorical cross entropy and the

optimizer used is stochastic gradient descent.

Output prediction: Once the validation phase is over, the model is ready to take an unknown
image of a flower and predict its name from the knowledge it gained during training and

validation phases. Once the classification is done by the model, it displays the common name

as well as the family name of that flower.

Benefits Module: Once the identity of the flower is found out, a previously created CSV file is
imported and the benefits of the corresponding flower will be found out and displayed to the
ALGORITHM
 START
 Import the necessary python libraries to get started with the
task of flower recognition with python
 Next step is to read each image in the data and
 Create a label for each with the name of the folder
 Convert the data into numerical values
 Let use the label encoder and normalize the data
 Next step is to split the dataset into 80% training and 20% test
sets
 Build a neural network model for the task
 Compile the neural network
 The model if it recognize the flower
 STOP
OUTPUT
 REFERENCE
Avishiktha Lodh, Ranjan Parekh,”Flower Recognition System based on Color and Gist Features”,

IEEE 2017

Busra Rumeysa Mete, Tolga Ensari,”Flower Classification with Deep CNN and Machine Learning

Algorithms, IEEE 3 rd International Symposium on Multidisciplinary Studies and Innovative

Technologies, 2019

TanakornTiay, Pipimphorn Benyaphaichit, Panomkhawn Riyamongkol,”Flower Recognition

System Based ON Image Processing, IEEE Third ICT international Student Project Conference,
THANK YOU