SlideShare a Scribd company logo
1 of 25
Bhoj Reddy Engineering College for Women
(Sponsored by Sangam Laxmibai Vidyapeet, approved by AICTE and affiliated to JNTUH)
Vinaynagar, IS Sadan Crossroads, Saidabad, Hyderabad ā€“ 500 059, Telangana. www.brecw.ac.in
Department of Computer Science and Engineering
Mini Project Design Seminar on
Weed Detection in Agricultural fields
Internal Guide: Mrs B.Pravalika Date : 19 Aug 2023
Assistant Professor Batch No : 20MP32
CSE-B Coordinator: Mrs K.Shireesha T.SaiPriya Reddy 20321A0577
Associate Professor R.Shivani 20321A0591
Ch.Vani 20321A05B5
Dr B Raveendranadh Singh Dr E Madhusudhana Reddy
Professor & Head Professor & Principal
Introduction
The growths of invasive weeds are hard to control as it grows fast and compete with
another crop aggressively. Fungi bacteria and nematodes may be introduced and this is
difficult to control and causing the grower to decrease harvest yield and revenue. It is costly
to destroy the weed with herbicide and reduce the margin of the cultivator. By using deep
learning we can detect the weed and it is a tool used to build intelligent systems as close
to human brain.
Scope
ā€¢ The scope of weed detection in agricultural fields using deep learning is to automate the
process of identifying and removing weeds from crops.
ā€¢ By detecting and removing weeds, farmers can improve their crop yields and reduce the
use of herbicides, which can be harmful to the environment.
Existing System
At present, weeds and crops research at home and abroad generally study and explore
from the following perspectives. On the one hand, the field seedlings are identified based on
image features such as color, texture, shape, and the like. However, factors such as the
similar color of crops and weeds and overlapping leaves may affect the recognition rate. On
the other hand, it is a method of identifying grass and grass based on stereo vision.
Disadvantages:
ļ‚· Low Accuracy
ļ‚· Low FPS
Proposed System
This system introduces a weed identification method based on convolutional neural
network. The proposed method can be applied not only to the data set of , but also to the
type of weed. Combining ground truth images and constructing multiple convolutional neural
networks for identification and comparison, the only regret is that crops and weeds in the
picture are infected to some extent, and the recognition accuracy needs to be
improved.This system proposes a convolutional neural network weed recognition based on
machine vision combined with digital image processing technology.
Advantages of Proposed System
o More Accuracy
o Convent to use
o High FPS
o Automatic Feature Extraction
Requirement Analysis
Functional Requirements:
System:
Image Processing
Annotated Dataset Collection
Feature-Extraction
Classification
User:
Input: User can submit an image for prediction of proper weed.
Output: Process the user input image and views the output.
Non-Functional Requirements:
ļƒ˜Portability:Ability to run and operate seamlessly across different platforms ,
environments.
ļƒ˜ Security:Code and database should be secured so that unauthorized user cannot
access it.
ļƒ˜ Maintainability: Code maintainability and readability for ease of future updates.
ļƒ˜ Scalability:Ability to handle a growing number of users and increasing data volumes.
ļƒ˜ Performance: Real-time disease detection to provide timely results.
Computational Resources:
Hardware Requirements:
Processor : Intel i5 and above
RAM : 8GB and above
Hard Disk : 500GB Minimum
Software Requirements:
Programming Languages /Platform : Python 3.6
IDE : pycharm
Operating System : Windows 10 and above
Data Pre-processing Techniques:
ā€¢ Resize images
ā€¢ Convert images into pixels
ā€¢ Scale pixel
ā€¢ Augmentation
Design
ā€¢ Design represents the number of components we are using as a part of the project and
the flow of request processing i.e., what components in processing the request and in
which order.
ā€¢ An architecture description is a formal description and representation of a system
organized in a way that supports reasoning about the structure of the system.
Software Architecture
Architecture
Software Process Model
Implementation steps and algorithm
ā€¢ A CNN is a kind of network architecture for deep learning algorithms and is specially used
for image recognition and tasks that involve the processing of pixel data.
ā€¢ The architecture of a convolutional neural network is a multi-layered network, made by
stacking many hidden layers on top of each other in sequence.
ā€¢ It is this sequential design that allows convolutional neural networks to learn hierarchical
features.
ā€¢ A general CNN consists of the following layers:
ā€¢ Convolutional layers
ā€¢ Pooling layers
Steps:
1.Input layer:
The input layer receives the raw image data, typically in the form of pixel values.The
size of this layer corresponds to the dimensions of the input image, e.g., 224x224 pixels
for many standard architectures.
2.Convolutional layer:
ā€¢ Convolutional layers are the core building blocks of CNNs. They consist of multiple
learnable filters (kernels) that slide across the input image.
ā€¢ Each filter extracts different features, such as edges, textures, or more complex patterns,
by performing element-wise multiplications and summing the results.
ā€¢ Convolutional layers help the network automatically learn relevant features from the
input data.
Activation Function:
ā€¢ After each convolution operation, an activation function is applied, typically Rectified
Linear Unit (ReLU).
ā€¢ ReLU introduces non-linearity into the model, allowing it to learn complex relationships in
the data.
3.Pooling layer:
ā€¢ Pooling layers reduce the spatial dimensions of the feature maps while retaining the most
essential information.
ā€¢ Max pooling is a common technique where the maximum value in a local region of the
feature map is taken, reducing the feature map's size.
ā€¢ Pooling helps make the model more robust to variations in the input and reduces
computational complexity.
Fully Connected layer:
ā€¢ Fully connected layers come after one or more convolutional and pooling layers.These
layers flatten the output from the previous layers into a 1D vector and connect it to a
dense neural network.
ā€¢ The final fully connected layer often has as many neurons as there are classes in the
problem (two for weed detection: weed or non-weed).
4.Output Layer:
ā€¢ The output layer typically uses a softmax activation function to convert the network's raw
output into class probabilities.
ā€¢ In weed detection, there are two classes: one for weeds and one for non-weeds.
Algorithm:
ļ± VGG Algorithm:
ā€¢ VGG (Visual Geometry Group) is a convolutional neural network (CNN) architecture that
gained popularity for its simplicity and effectiveness in image classification tasks. The VGG
architecture is characterized by its use of small 3x3 convolutional filters and its deep
structure with multiple layers.
ā€¢ The layers in VGG are composed of a combination of convolutional layers, followed by max-
pooling layers for downsampling, and fully connected layers at the end for classification.
VGG networks are known for their deeper architecture, which makes them suitable for
capturing intricate features in images.
ā€¢ However VGG networks are used in making training and deployment more resource-
demanding compared to some later architectures like ResNet or Inception.
CNN Architecture
Expected output
Conclusion
This project concludes that Weed detection is a critical task for agricultural productivity. This
requires improved computational methods that allow faster response.Therefore, the proposed
method has higher accuracy than the existing methods.
Any Queries?
References
ā€¢ G.L.N. Murthy, Baji Baba Shaik, Ch Uday Reddy, V ManikanteswarRao,ā€Multilayered
CNN Architecture for Assistance in Smart Farming", 2023 International Conference
on Inventive Computation Technologies (ICICT), pp.347-351.
ā€¢ Weed Identification Using Deep Learning Techniques",2023 International Conference
on Computer Communication and Informatics (ICCCI), pp.
ā€¢ K. Osorio, A. Puerto, C. Pedraza, D. Jamaica and L. RodrĆ­guez, "A deep learning
approach for weed detection in lettuce crops using multispectral images", Agri Engi-
neering, vol. 2, no. 3, pp. 471-488
weed detecion hhjjjjjhhbnjjjnjffhjjkkjhjjj

More Related Content

Similar to weed detecion hhjjjjjhhbnjjjnjffhjjkkjhjjj

Implementation of Automated Attendance System using Deep Learning
Implementation of Automated Attendance System using Deep LearningImplementation of Automated Attendance System using Deep Learning
Implementation of Automated Attendance System using Deep Learning
Md. Mahfujur Rahman
Ā 

Similar to weed detecion hhjjjjjhhbnjjjnjffhjjkkjhjjj (20)

Makine Ɩğrenmesi ile GƶrĆ¼ntĆ¼ Tanıma | Image Recognition using Machine Learning
Makine Ɩğrenmesi ile GƶrĆ¼ntĆ¼ Tanıma | Image Recognition using Machine LearningMakine Ɩğrenmesi ile GƶrĆ¼ntĆ¼ Tanıma | Image Recognition using Machine Learning
Makine Ɩğrenmesi ile GƶrĆ¼ntĆ¼ Tanıma | Image Recognition using Machine Learning
Ā 
GRID COMPUTING
GRID COMPUTINGGRID COMPUTING
GRID COMPUTING
Ā 
Deep Learning based Multi-class Brain Tumor Classification
Deep Learning based Multi-class Brain Tumor ClassificationDeep Learning based Multi-class Brain Tumor Classification
Deep Learning based Multi-class Brain Tumor Classification
Ā 
IRJET- Automated Studentā€™s Attendance Management using Convolutional Neural N...
IRJET- Automated Studentā€™s Attendance Management using Convolutional Neural N...IRJET- Automated Studentā€™s Attendance Management using Convolutional Neural N...
IRJET- Automated Studentā€™s Attendance Management using Convolutional Neural N...
Ā 
Ku3419461949
Ku3419461949Ku3419461949
Ku3419461949
Ā 
Implementation of Automated Attendance System using Deep Learning
Implementation of Automated Attendance System using Deep LearningImplementation of Automated Attendance System using Deep Learning
Implementation of Automated Attendance System using Deep Learning
Ā 
Pest Classification and Pesticide Recommendation System
Pest Classification and Pesticide Recommendation SystemPest Classification and Pesticide Recommendation System
Pest Classification and Pesticide Recommendation System
Ā 
Visual Cryptography Industrial Training Report
Visual Cryptography Industrial Training ReportVisual Cryptography Industrial Training Report
Visual Cryptography Industrial Training Report
Ā 
A Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep LearningA Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep Learning
Ā 
AUTOMATED WASTE MANAGEMENT SYSTEM
AUTOMATED WASTE MANAGEMENT SYSTEMAUTOMATED WASTE MANAGEMENT SYSTEM
AUTOMATED WASTE MANAGEMENT SYSTEM
Ā 
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry PiIRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
Ā 
A deep learning based stereo matching model for autonomous vehicle
A deep learning based stereo matching model for autonomous vehicleA deep learning based stereo matching model for autonomous vehicle
A deep learning based stereo matching model for autonomous vehicle
Ā 
Efficient mobilenet architecture_as_image_recognit
Efficient mobilenet architecture_as_image_recognitEfficient mobilenet architecture_as_image_recognit
Efficient mobilenet architecture_as_image_recognit
Ā 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image Detection
Ā 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
Ā 
Prototyping of Wireless Sensor Network for Precision Agriculture
Prototyping of Wireless Sensor Network for Precision Agriculture Prototyping of Wireless Sensor Network for Precision Agriculture
Prototyping of Wireless Sensor Network for Precision Agriculture
Ā 
Plant Disease Detection.pptx
Plant Disease Detection.pptxPlant Disease Detection.pptx
Plant Disease Detection.pptx
Ā 
Potato Leaf Disease Detection Using Machine Learning
Potato Leaf Disease Detection Using Machine LearningPotato Leaf Disease Detection Using Machine Learning
Potato Leaf Disease Detection Using Machine Learning
Ā 
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
Ā 
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
Ā 

Recently uploaded

Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
amitlee9823
Ā 
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
ZurliaSoop
Ā 
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdfreStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
Ken Fuller
Ā 
Gabriel_Carter_EXPOLRATIONpp.pptx........
Gabriel_Carter_EXPOLRATIONpp.pptx........Gabriel_Carter_EXPOLRATIONpp.pptx........
Gabriel_Carter_EXPOLRATIONpp.pptx........
deejay178
Ā 
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
amitlee9823
Ā 
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night StandCall Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
amitlee9823
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men šŸ”MirzapuršŸ” Escor...
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men  šŸ”MirzapuršŸ”   Escor...āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men  šŸ”MirzapuršŸ”   Escor...
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men šŸ”MirzapuršŸ” Escor...
amitlee9823
Ā 
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service BangaloreCall Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
amitlee9823
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men šŸ”SatarašŸ” Escorts S...
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men  šŸ”SatarašŸ”   Escorts S...āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men  šŸ”SatarašŸ”   Escorts S...
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men šŸ”SatarašŸ” Escorts S...
amitlee9823
Ā 
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
amitlee9823
Ā 
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
amitlee9823
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men šŸ”TirupatišŸ” Escor...
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men  šŸ”TirupatišŸ”   Escor...āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men  šŸ”TirupatišŸ”   Escor...
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men šŸ”TirupatišŸ” Escor...
amitlee9823
Ā 

Recently uploaded (20)

Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
Call Girls Devanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service B...
Ā 
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
Jual obat aborsi Jakarta ( 085657271886 )Cytote pil telat bulan penggugur kan...
Ā 
Hyderabad šŸ’«āœ…šŸ’ƒ 24Ɨ7 BEST GENUINE PERSON LOW PRICE CALL GIRL SERVICE FULL SATIS...
Hyderabad šŸ’«āœ…šŸ’ƒ 24Ɨ7 BEST GENUINE PERSON LOW PRICE CALL GIRL SERVICE FULL SATIS...Hyderabad šŸ’«āœ…šŸ’ƒ 24Ɨ7 BEST GENUINE PERSON LOW PRICE CALL GIRL SERVICE FULL SATIS...
Hyderabad šŸ’«āœ…šŸ’ƒ 24Ɨ7 BEST GENUINE PERSON LOW PRICE CALL GIRL SERVICE FULL SATIS...
Ā 
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdfreStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
reStartEvents 5:9 DC metro & Beyond V-Career Fair Employer Directory.pdf
Ā 
Joshua Minker Brand Exploration Sports Broadcaster .pptx
Joshua Minker Brand Exploration Sports Broadcaster .pptxJoshua Minker Brand Exploration Sports Broadcaster .pptx
Joshua Minker Brand Exploration Sports Broadcaster .pptx
Ā 
Gabriel_Carter_EXPOLRATIONpp.pptx........
Gabriel_Carter_EXPOLRATIONpp.pptx........Gabriel_Carter_EXPOLRATIONpp.pptx........
Gabriel_Carter_EXPOLRATIONpp.pptx........
Ā 
Rearing technique of lac insect and their management
Rearing technique of lac insect and their managementRearing technique of lac insect and their management
Rearing technique of lac insect and their management
Ā 
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Btm Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Ā 
Resumes, Cover Letters, and Applying Online
Resumes, Cover Letters, and Applying OnlineResumes, Cover Letters, and Applying Online
Resumes, Cover Letters, and Applying Online
Ā 
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night StandCall Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
Call Girls In Devanahalli ā˜Ž 7737669865 šŸ„µ Book Your One night Stand
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men šŸ”MirzapuršŸ” Escor...
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men  šŸ”MirzapuršŸ”   Escor...āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men  šŸ”MirzapuršŸ”   Escor...
āž„šŸ” 7737669865 šŸ”ā–» Mirzapur Call-girls in Women Seeking Men šŸ”MirzapuršŸ” Escor...
Ā 
Personal Brand Exploration ppt.- Ronnie Jones
Personal Brand  Exploration ppt.- Ronnie JonesPersonal Brand  Exploration ppt.- Ronnie Jones
Personal Brand Exploration ppt.- Ronnie Jones
Ā 
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service BangaloreCall Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Hoodi Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Ā 
Toxicokinetics studies.. (toxicokinetics evaluation in preclinical studies)
Toxicokinetics studies.. (toxicokinetics evaluation in preclinical studies)Toxicokinetics studies.. (toxicokinetics evaluation in preclinical studies)
Toxicokinetics studies.. (toxicokinetics evaluation in preclinical studies)
Ā 
Booking open Available Pune Call Girls Ambegaon Khurd 6297143586 Call Hot In...
Booking open Available Pune Call Girls Ambegaon Khurd  6297143586 Call Hot In...Booking open Available Pune Call Girls Ambegaon Khurd  6297143586 Call Hot In...
Booking open Available Pune Call Girls Ambegaon Khurd 6297143586 Call Hot In...
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men šŸ”SatarašŸ” Escorts S...
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men  šŸ”SatarašŸ”   Escorts S...āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men  šŸ”SatarašŸ”   Escorts S...
āž„šŸ” 7737669865 šŸ”ā–» Satara Call-girls in Women Seeking Men šŸ”SatarašŸ” Escorts S...
Ā 
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
Nagavara Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore Es...
Ā 
Dubai Call Girls Kiki O525547819 Call Girls Dubai Koko
Dubai Call Girls Kiki O525547819 Call Girls Dubai KokoDubai Call Girls Kiki O525547819 Call Girls Dubai Koko
Dubai Call Girls Kiki O525547819 Call Girls Dubai Koko
Ā 
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
Call Girls Bommanahalli Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service ...
Ā 
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men šŸ”TirupatišŸ” Escor...
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men  šŸ”TirupatišŸ”   Escor...āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men  šŸ”TirupatišŸ”   Escor...
āž„šŸ” 7737669865 šŸ”ā–» Tirupati Call-girls in Women Seeking Men šŸ”TirupatišŸ” Escor...
Ā 

weed detecion hhjjjjjhhbnjjjnjffhjjkkjhjjj

  • 1. Bhoj Reddy Engineering College for Women (Sponsored by Sangam Laxmibai Vidyapeet, approved by AICTE and affiliated to JNTUH) Vinaynagar, IS Sadan Crossroads, Saidabad, Hyderabad ā€“ 500 059, Telangana. www.brecw.ac.in Department of Computer Science and Engineering Mini Project Design Seminar on Weed Detection in Agricultural fields Internal Guide: Mrs B.Pravalika Date : 19 Aug 2023 Assistant Professor Batch No : 20MP32 CSE-B Coordinator: Mrs K.Shireesha T.SaiPriya Reddy 20321A0577 Associate Professor R.Shivani 20321A0591 Ch.Vani 20321A05B5 Dr B Raveendranadh Singh Dr E Madhusudhana Reddy Professor & Head Professor & Principal
  • 2. Introduction The growths of invasive weeds are hard to control as it grows fast and compete with another crop aggressively. Fungi bacteria and nematodes may be introduced and this is difficult to control and causing the grower to decrease harvest yield and revenue. It is costly to destroy the weed with herbicide and reduce the margin of the cultivator. By using deep learning we can detect the weed and it is a tool used to build intelligent systems as close to human brain.
  • 3. Scope ā€¢ The scope of weed detection in agricultural fields using deep learning is to automate the process of identifying and removing weeds from crops. ā€¢ By detecting and removing weeds, farmers can improve their crop yields and reduce the use of herbicides, which can be harmful to the environment.
  • 4. Existing System At present, weeds and crops research at home and abroad generally study and explore from the following perspectives. On the one hand, the field seedlings are identified based on image features such as color, texture, shape, and the like. However, factors such as the similar color of crops and weeds and overlapping leaves may affect the recognition rate. On the other hand, it is a method of identifying grass and grass based on stereo vision. Disadvantages: ļ‚· Low Accuracy ļ‚· Low FPS
  • 5. Proposed System This system introduces a weed identification method based on convolutional neural network. The proposed method can be applied not only to the data set of , but also to the type of weed. Combining ground truth images and constructing multiple convolutional neural networks for identification and comparison, the only regret is that crops and weeds in the picture are infected to some extent, and the recognition accuracy needs to be improved.This system proposes a convolutional neural network weed recognition based on machine vision combined with digital image processing technology.
  • 6. Advantages of Proposed System o More Accuracy o Convent to use o High FPS o Automatic Feature Extraction
  • 7. Requirement Analysis Functional Requirements: System: Image Processing Annotated Dataset Collection Feature-Extraction Classification User: Input: User can submit an image for prediction of proper weed. Output: Process the user input image and views the output.
  • 8. Non-Functional Requirements: ļƒ˜Portability:Ability to run and operate seamlessly across different platforms , environments. ļƒ˜ Security:Code and database should be secured so that unauthorized user cannot access it. ļƒ˜ Maintainability: Code maintainability and readability for ease of future updates. ļƒ˜ Scalability:Ability to handle a growing number of users and increasing data volumes. ļƒ˜ Performance: Real-time disease detection to provide timely results.
  • 9. Computational Resources: Hardware Requirements: Processor : Intel i5 and above RAM : 8GB and above Hard Disk : 500GB Minimum Software Requirements: Programming Languages /Platform : Python 3.6 IDE : pycharm Operating System : Windows 10 and above
  • 10. Data Pre-processing Techniques: ā€¢ Resize images ā€¢ Convert images into pixels ā€¢ Scale pixel ā€¢ Augmentation
  • 11. Design ā€¢ Design represents the number of components we are using as a part of the project and the flow of request processing i.e., what components in processing the request and in which order. ā€¢ An architecture description is a formal description and representation of a system organized in a way that supports reasoning about the structure of the system.
  • 15. Implementation steps and algorithm ā€¢ A CNN is a kind of network architecture for deep learning algorithms and is specially used for image recognition and tasks that involve the processing of pixel data. ā€¢ The architecture of a convolutional neural network is a multi-layered network, made by stacking many hidden layers on top of each other in sequence. ā€¢ It is this sequential design that allows convolutional neural networks to learn hierarchical features. ā€¢ A general CNN consists of the following layers: ā€¢ Convolutional layers ā€¢ Pooling layers
  • 16. Steps: 1.Input layer: The input layer receives the raw image data, typically in the form of pixel values.The size of this layer corresponds to the dimensions of the input image, e.g., 224x224 pixels for many standard architectures. 2.Convolutional layer: ā€¢ Convolutional layers are the core building blocks of CNNs. They consist of multiple learnable filters (kernels) that slide across the input image. ā€¢ Each filter extracts different features, such as edges, textures, or more complex patterns, by performing element-wise multiplications and summing the results. ā€¢ Convolutional layers help the network automatically learn relevant features from the input data.
  • 17. Activation Function: ā€¢ After each convolution operation, an activation function is applied, typically Rectified Linear Unit (ReLU). ā€¢ ReLU introduces non-linearity into the model, allowing it to learn complex relationships in the data. 3.Pooling layer: ā€¢ Pooling layers reduce the spatial dimensions of the feature maps while retaining the most essential information. ā€¢ Max pooling is a common technique where the maximum value in a local region of the feature map is taken, reducing the feature map's size. ā€¢ Pooling helps make the model more robust to variations in the input and reduces computational complexity.
  • 18. Fully Connected layer: ā€¢ Fully connected layers come after one or more convolutional and pooling layers.These layers flatten the output from the previous layers into a 1D vector and connect it to a dense neural network. ā€¢ The final fully connected layer often has as many neurons as there are classes in the problem (two for weed detection: weed or non-weed). 4.Output Layer: ā€¢ The output layer typically uses a softmax activation function to convert the network's raw output into class probabilities. ā€¢ In weed detection, there are two classes: one for weeds and one for non-weeds.
  • 19. Algorithm: ļ± VGG Algorithm: ā€¢ VGG (Visual Geometry Group) is a convolutional neural network (CNN) architecture that gained popularity for its simplicity and effectiveness in image classification tasks. The VGG architecture is characterized by its use of small 3x3 convolutional filters and its deep structure with multiple layers. ā€¢ The layers in VGG are composed of a combination of convolutional layers, followed by max- pooling layers for downsampling, and fully connected layers at the end for classification. VGG networks are known for their deeper architecture, which makes them suitable for capturing intricate features in images. ā€¢ However VGG networks are used in making training and deployment more resource- demanding compared to some later architectures like ResNet or Inception.
  • 22. Conclusion This project concludes that Weed detection is a critical task for agricultural productivity. This requires improved computational methods that allow faster response.Therefore, the proposed method has higher accuracy than the existing methods.
  • 24. References ā€¢ G.L.N. Murthy, Baji Baba Shaik, Ch Uday Reddy, V ManikanteswarRao,ā€Multilayered CNN Architecture for Assistance in Smart Farming", 2023 International Conference on Inventive Computation Technologies (ICICT), pp.347-351. ā€¢ Weed Identification Using Deep Learning Techniques",2023 International Conference on Computer Communication and Informatics (ICCCI), pp. ā€¢ K. Osorio, A. Puerto, C. Pedraza, D. Jamaica and L. RodrĆ­guez, "A deep learning approach for weed detection in lettuce crops using multispectral images", Agri Engi- neering, vol. 2, no. 3, pp. 471-488