Towards Better Apartment Management and Apartment Accounting. A copy of Maharashtra Apartment Ownership Act 1970.
ApartmentADDA is India's #1 Apartment Management and Apartment Accounting Software. All the best practices of State Bye-Laws are inbuilt in the product.
It depicts the basic information about GPS technology and its various uses in engineering and other fields. May be useful for students of engineering and for presentation.
Towards Better Apartment Management and Apartment Accounting. A copy of Maharashtra Apartment Ownership Act 1970.
ApartmentADDA is India's #1 Apartment Management and Apartment Accounting Software. All the best practices of State Bye-Laws are inbuilt in the product.
It depicts the basic information about GPS technology and its various uses in engineering and other fields. May be useful for students of engineering and for presentation.
Steel ppt ,
History of Steel
What is Steel?
What is Reinforced Steel?
Need for Reinforced Steel
Types of Reinforced Steel
Why Steel?
Properties of Reinforced Steel
Uses of Reinforced Steel
Whats New?
Conclusion
Notes 2D-Transformation Unit 2 Computer graphicsNANDINI SHARMA
Notes of 2D Transformation including Translation, Rotation, Scaling, Reflection, Shearing with solved problem.
Clipping algorithm like cohen-sutherland-hodgeman, midpoint-subdivision with solved problem.
This presentation will introduce you to Raster details in computer graphics.
---------------------------------------------------------------------------
Do Not just learn computer graphics an close your computer tab and go away..
APPLY them in real business,
Visit Daroko blog for real IT skills applications,androind, Computer graphics,Networking,Programming,IT jobs Types, IT news and applications,blogging,Builing a website, IT companies and how you can form yours, Technology news and very many More IT related subject.
-simply google:Daroko blog(professionalbloggertricks.com)
• Daroko blog (www.professionalbloggertricks.com)
• Presentation by Daroko blog, to see More tutorials more than this one here, Daroko blog has all tutorials related with IT course, simply visit the site by simply Entering the phrase Daroko blog (www.professionalbloggertricks.com) to search engines such as Google or yahoo!, learn some Blogging, affiliate marketing ,and ways of making Money with the computer graphic Applications(it is useless to learn all these tutorials when you can apply them as a student you know),also learn where you can apply all IT skills in a real Business Environment after learning Graphics another computer realate courses.ly
• Be practically real, not just academic reader
GSM Based Device Controlling and Fault DetectionIJCERT
The mobile communication has expanded to a great extent such that it can be applied for controlling of electrical devices. These projects make use of this capability of mobile phone to control three electrical devices with some use of embedded technology which can be extended up to eight devices. Apart from controlling it also does the sensing of the devices. Thus a user can be able to know of the status of the devices and in addition to that the user get notified if any fault is detected. Here in the project controlling and sensing is done for three electrical devices only. According to the user need both of this can be expanded.
Steel ppt ,
History of Steel
What is Steel?
What is Reinforced Steel?
Need for Reinforced Steel
Types of Reinforced Steel
Why Steel?
Properties of Reinforced Steel
Uses of Reinforced Steel
Whats New?
Conclusion
Notes 2D-Transformation Unit 2 Computer graphicsNANDINI SHARMA
Notes of 2D Transformation including Translation, Rotation, Scaling, Reflection, Shearing with solved problem.
Clipping algorithm like cohen-sutherland-hodgeman, midpoint-subdivision with solved problem.
This presentation will introduce you to Raster details in computer graphics.
---------------------------------------------------------------------------
Do Not just learn computer graphics an close your computer tab and go away..
APPLY them in real business,
Visit Daroko blog for real IT skills applications,androind, Computer graphics,Networking,Programming,IT jobs Types, IT news and applications,blogging,Builing a website, IT companies and how you can form yours, Technology news and very many More IT related subject.
-simply google:Daroko blog(professionalbloggertricks.com)
• Daroko blog (www.professionalbloggertricks.com)
• Presentation by Daroko blog, to see More tutorials more than this one here, Daroko blog has all tutorials related with IT course, simply visit the site by simply Entering the phrase Daroko blog (www.professionalbloggertricks.com) to search engines such as Google or yahoo!, learn some Blogging, affiliate marketing ,and ways of making Money with the computer graphic Applications(it is useless to learn all these tutorials when you can apply them as a student you know),also learn where you can apply all IT skills in a real Business Environment after learning Graphics another computer realate courses.ly
• Be practically real, not just academic reader
GSM Based Device Controlling and Fault DetectionIJCERT
The mobile communication has expanded to a great extent such that it can be applied for controlling of electrical devices. These projects make use of this capability of mobile phone to control three electrical devices with some use of embedded technology which can be extended up to eight devices. Apart from controlling it also does the sensing of the devices. Thus a user can be able to know of the status of the devices and in addition to that the user get notified if any fault is detected. Here in the project controlling and sensing is done for three electrical devices only. According to the user need both of this can be expanded.
Flower Classification Using Neural Network Based Image ProcessingIOSR Journals
Abstract: In this paper, it is proposed to have a method for classification of flowers using Artificial Neural Network (ANN) classifier. The proposed method is based on textural features such as Gray level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT). A flower image is segmented using a threshold based method. The data set has different flower images with similar appearance .The database of flower images is a mixture of images taken from World Wide Web and the images taken by us. The ANN has been trained by 50 samples to classify 5 classes of flowers and achieved classification accuracy more than 85% using GLCM features only. Keywords: Artificial Neural Network, DWT, GLCM, Segmentation.
Indian Cricket Team Poem prescribed for Class VI by APSCERT and TGSCERT syllabus. PPT prepared by M Padma Lalitha Sharada of GHS Malakpet under guidance of Smt. C B Nirmala Madam.
Note: I did not have minimum knowledge about cricket and cricketers. Any mistakes in this PPT brought to my notice I will definitely rectify them.
http://imatge-upc.github.io/telecombcn-2016-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.
http://imatge-upc.github.io/telecombcn-2016-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.
Apple iPhone 7 Plus: Rear-Facing Dual Camera Module 2016 teardown reverse cos...Yole Developpement
With its choice of a dual camera, Apple’s innovations include new objectives lens assemblies, new bonding processes and a new type of autofocus
In the iPhone 7 Plus, Apple introduced a new rear camera module. Like its competitors LG and Huawei, they have chosen to integrate a dual camera. The module features two sensors, one closed to the sensor in the previous flagship, and another with a totally new structure.
Competition for the best camera phone was revived by Huawei with its flagship, the P9, using a dual camera. Like the other main players except Samsung, Apple has now introduced a dual camera module. This module integrates two 12 megapixel resolution CMOS Image Sensors (CISs) from Sony, using Exmor-RS Technology. The wide-angle objective lens assembly features an aperture of f/1.8 and a pixel size of 1.22 µm. The telephoto has a pixel size of 1 µm but a smaller aperture of f/2.8.
The iPhone 7 Plus dual camera module, with dimensions of 20.6 x 10.0 x 5.9 mm, is equipped with two sub-modules each including a Sony CIS. The wide-angle module is equipped with an optical image stabilization (OIS) voice coil motor (VCM), while the telephoto only comes with a general VCM. The CISs are assembled using a flip-chip process on a ceramic substrate with a gold stud bumping process.
With this new dual camera module and Sony’s Exmor-RS technology, Apple has innovated its offering in areas including phase detection autofocus (PDAF), its objective lens assembly structure, its sensor, and adopts a second generation of through-silicon vias (TSVs). Surprisingly both logic circuit sensors for controlling PDAF are very similar.
The report includes technology and cost analysis of the iPhone 7 Plus dual camera module. Also, comparisons with the Huawei P9, Samsung Galaxy S7 and iPhone 6S rear camera modules are provided. These comparisons highlight differences in structures, technical choices and manufacturing cost.
More information on that report at http://www.i-micronews.com/reports.html
Traffic sign detection via graph based ranking and segmentationPREMSAI CHEEDELLA
The majority of the existing traffic sign detection system use shape information, but the methods of remain limited in regard to detecting and segmenting traffic signs from a complex background.
Performance analysis of transformation and bogdonov chaotic substitution base...IJECEIAES
In this article, a combined Pseudo Hadamard transformation and modified Bogdonav chaotic generator based image encryption technique is proposed. Pixel position transformation is performed using Pseudo Hadamard transformation and pixel value variation is made using Bogdonav chaotic substitution. Bogdonav chaotic generator produces random sequences and it is observed that very less correlation between the adjacent elements in the sequence. The cipher image obtained from the transformation stage is subjected for substitution using Bogdonav chaotic sequence to break correlation between adjacent pixels. The cipher image is subjected for various security tests under noisy conditions and very high degree of similarity is observed after deciphering process between original and decrypted images.
This tutor introduces the basic idea of machine learning with a very simple example. Machine learning teaches machines (and me too) to learn to carry out tasks and concepts by themselves. It is that simple, so here is an overview:
http://www.softwareschule.ch/examples/machinelearning.jpg
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdffxintegritypublishin
Advancements in technology unveil a myriad of electrical and electronic breakthroughs geared towards efficiently harnessing limited resources to meet human energy demands. The optimization of hybrid solar PV panels and pumped hydro energy supply systems plays a pivotal role in utilizing natural resources effectively. This initiative not only benefits humanity but also fosters environmental sustainability. The study investigated the design optimization of these hybrid systems, focusing on understanding solar radiation patterns, identifying geographical influences on solar radiation, formulating a mathematical model for system optimization, and determining the optimal configuration of PV panels and pumped hydro storage. Through a comparative analysis approach and eight weeks of data collection, the study addressed key research questions related to solar radiation patterns and optimal system design. The findings highlighted regions with heightened solar radiation levels, showcasing substantial potential for power generation and emphasizing the system's efficiency. Optimizing system design significantly boosted power generation, promoted renewable energy utilization, and enhanced energy storage capacity. The study underscored the benefits of optimizing hybrid solar PV panels and pumped hydro energy supply systems for sustainable energy usage. Optimizing the design of solar PV panels and pumped hydro energy supply systems as examined across diverse climatic conditions in a developing country, not only enhances power generation but also improves the integration of renewable energy sources and boosts energy storage capacities, particularly beneficial for less economically prosperous regions. Additionally, the study provides valuable insights for advancing energy research in economically viable areas. Recommendations included conducting site-specific assessments, utilizing advanced modeling tools, implementing regular maintenance protocols, and enhancing communication among system components.
Overview of the fundamental roles in Hydropower generation and the components involved in wider Electrical Engineering.
This paper presents the design and construction of hydroelectric dams from the hydrologist’s survey of the valley before construction, all aspects and involved disciplines, fluid dynamics, structural engineering, generation and mains frequency regulation to the very transmission of power through the network in the United Kingdom.
Author: Robbie Edward Sayers
Collaborators and co editors: Charlie Sims and Connor Healey.
(C) 2024 Robbie E. Sayers
Student information management system project report ii.pdfKamal Acharya
Our project explains about the student management. This project mainly explains the various actions related to student details. This project shows some ease in adding, editing and deleting the student details. It also provides a less time consuming process for viewing, adding, editing and deleting the marks of the students.
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
CFD analysis is incredibly effective at solving mysteries and improving the performance of complex systems!
Here's a great example: At a large natural gas-fired power plant, where they use waste heat to generate steam and energy, they were puzzled that their boiler wasn't producing as much steam as expected.
R&R and Tetra Engineering Group Inc. were asked to solve the issue with reduced steam production.
An inspection had shown that a significant amount of hot flue gas was bypassing the boiler tubes, where the heat was supposed to be transferred.
R&R Consult conducted a CFD analysis, which revealed that 6.3% of the flue gas was bypassing the boiler tubes without transferring heat. The analysis also showed that the flue gas was instead being directed along the sides of the boiler and between the modules that were supposed to capture the heat. This was the cause of the reduced performance.
Based on our results, Tetra Engineering installed covering plates to reduce the bypass flow. This improved the boiler's performance and increased electricity production.
It is always satisfying when we can help solve complex challenges like this. Do your systems also need a check-up or optimization? Give us a call!
Work done in cooperation with James Malloy and David Moelling from Tetra Engineering.
More examples of our work https://www.r-r-consult.dk/en/cases-en/
2. Introduction
The ability to identify the tomatoes based on quality in the food industry which
is the most important technology in the realization of automatic tomato sorting
machine in order to reduce the work of human and also time consuming.
Automation of quality control is highly significant because saving time and
expenses is always a necessity in industrial applications.
An automated system has to be developed which acquires the images of the
tomatoes and various features would be extracted using Image Processing and
these features would be further used to train machine using some Machine
Learning Algorithm and data would be classified and analyzed and accuracy and
quality of the test data will be determined.
3. APPLICATIONS USED
MATLAB :Matlab (MATrix LABoratory) is a multi-
paradigm numerical computing environment and
fourth generation programming language.
R :R is a language and environment for statistical
computing and graphics.
E1071 and RGL libraries are used for SVM
classification and visualization.
WEKA :Waikato Environment for Knowledge
Analysis. Weka is a collection of machine learning
algorithms for data mining tasks.
Libsvm package is used to classify data.
5. ALGORITHM
Images are acquired by camera with precision of 20 cm from the surface above from
standard scale for calibration.
Contrast is adjusted for the acquired image.
Segmentation is performed using Otsu’ segmentation method.
Histogram of Images are bimodal hence pixel set of each histogram are calculated and
subtracted and the obtained pixel set is used for threshold.
Mask is generated from threshold level and median filter is applied.
Morphological erosion and filling operation is performed on the mask to generated finally
binary segmented image.
Region props is used to calculated features such as centroid, major Axis Length for radius
and this will be used to find volume and area.
6. Algorithm Continued…
Gradient weight is used to find the image weight.
RGB to HSV transformation is applied on the acquired image and threshold level is
calculated for each red , green and blue level and these threshold are used to find
maximum number of pixels of different colors.
The maximum value of red pixels represents very good quality of tomato and maximum
value of yellow pixels represents good quality of tomato and maximum value of green
pixels represents poor quality of tomato.
These features data acquired and stored in the database and hence eventually total 145
samples feature data are stored.
These samples are feed into WEKA for classification.
SVM Multi class classification of Sequential Marginal Optimization algorithm is used to
classify data.
70% of the data used for training and 30% is used for testing which generates accuracy of
74%.
7. Algorithm in Code
Clear the Workspace;
clc
clear workspace;
Read and load the image
I=imread('t56.jpg');
figure;
imshow(I)
title('original image')
Adjust Contrast of blue channel of the Original Image
IL = imadjust(I(:,:,3))
8. Algorithm in Code
Get the size and total pixel count of the image
[rows, columns, numberOfColorBands] = size(IL);
[pixelCount, grayLevels] = imhist(IL, 256);
Divide image in two half and get the total pixel count of the left half image
middleColumn = floor(columns/2);
leftHalfImage = IL(:, 1:middleColumn);
[pixelCountL, grayLevelsL] = imhist(leftHalfImage, 256);
Get the pixel count of the another half right image
rightHalfImage = IL(:, middleColumn+1:end);
[pixelCountR, grayLevelsR] = imhist(rightHalfImage, 256);
9. Algorithm in Code
Subtract the two left and right pixelcount and get the subtracted histogram
diffHistogram = int16(pixelCountL - pixelCountR);
Create the threshold level of subtracted histogram value. Find Otsu threshold
level
thresholdLevel = 255 * graythresh(diffHistogram)
Create mask from the threshold level
mask1 = IL > thresholdLevel;
Apply Median Filter to the Mask
mask2 = medfilt2(mask1)
10. Algorithm in Code
Apply Morphological Operation on the mask which will generate segmented Image
SE = strel('disk',2)
mask3 = imerode(mask2,SE)
mask4 = ~imfill(~mask3,'holes')
figure;
imshow(mask4)
title('Segmented Image')
Get the separate Channels of the Original Image
red = I(:, :, 1)
green = I(:, :, 2)
blue = I(:, :, 3)
Get the Gradient Weight of the Image
weight = mean2(gradientweight(IL))
11. Algorithm in Code
Get the Major Axis Length
radii = regionprops(mask3,'MajorAxisLength')
radii2 = mean2(cat(1,radii.MajorAxisLength))
Calculate Volume
volume = (4.0/3.0)*pi*(radii2^3)
Calculate Area
area=4.0*pi*(radii2^2)
%Convert to HSV Image
hsvImage = rgb2hsv(I)weight = mean2(gradientweight(IL))
12. Algorithm in Code
Extract out the H, S, and V images individually
hImage = hsvImage(:,:,1);
sImage = hsvImage(:,:,2);
vImage = hsvImage(:,:,3);
Threshold for Yellow Color
YhueThresholdLow = 0.10;
YhueThresholdHigh = 0.14;
YsaturationThresholdLow = 0.4;
13. Algorithm in Code
YsaturationThresholdHigh = 1;
YvalueThresholdLow = 0.8;
YvalueThresholdHigh = 1.0;
% Now apply each color band's particular thresholds to the color band for
yellow
YhueMask = (hImage >= YhueThresholdLow) & (hImage <= YhueThresholdHigh);
YsaturationMask = (sImage >= YsaturationThresholdLow) & (sImage <=
YsaturationThresholdHigh);
YvalueMask = (vImage >= YvalueThresholdLow) & (vImage <=
YvalueThresholdHigh);
14. Algorithm in Code
Smooth the border using a morphological closing operation, imclose().
YstructuringElement = strel('disk', 4);
YcoloredObjectsMask = imclose(YcoloredObjectsMask, YstructuringElement);
Fill in any holes in the regions, since they are most likely red also.
YcoloredObjectsMask = imfill(logical(YcoloredObjectsMask), 'holes');
YcoloredObjectsMask = cast(YcoloredObjectsMask, 'like', I);
15. Algorithm in Code
Use the colored object mask to mask out the colored-only portions of the rgb
image.
YmaskedImageR = YcoloredObjectsMask .* red;
YmaskedImageG = YcoloredObjectsMask .* green;
YmaskedImageB = YcoloredObjectsMask .* blue;
yellowImage = cat(3, YmaskedImageR, YmaskedImageG, YmaskedImageB);
Yellow Pixel Count
yel = mean2(yellowImage(find(yellowImage)))
16. Algorithm in Code
Threshold for Red Color
RhueThresholdLow = 0.03;
RhueThresholdHigh = 1.5;
RsaturationThresholdLow = 0.18;
RsaturationThresholdHigh = 1.5;
RvalueThresholdLow = 0.05;
RvalueThresholdHigh = 1.8;
17. Algorithm in Code
Now apply each color band's particular thresholds to the color band for Red
RhueMask = (hImage >= RhueThresholdLow) & (hImage <= RhueThresholdHigh);
RsaturationMask = (sImage >= RsaturationThresholdLow) & (sImage <=
RsaturationThresholdHigh);
RvalueMask = (vImage >= RvalueThresholdLow) & (vImage <=
RvalueThresholdHigh);
RcoloredObjectsMask = uint8(RhueMask & RsaturationMask & RvalueMask);
RstructuringElement = strel('disk', 4);
RcoloredObjectsMask = imclose(RcoloredObjectsMask, RstructuringElement);
18. Algorithm in Code
Fill in any holes in the regions, since they are most likely red also.
RcoloredObjectsMask = imfill(logical(RcoloredObjectsMask), 'holes');
RcoloredObjectsMask = cast(RcoloredObjectsMask, 'like', I);
Use the colored object mask to mask out the colored-only portions of the rgb
image.
RmaskedImageR = RcoloredObjectsMask .* red;
RmaskedImageG = RcoloredObjectsMask .* green;
RmaskedImageB = RcoloredObjectsMask .* blue;
redImage = cat(3, RmaskedImageR, RmaskedImageG, RmaskedImageB);
Red Pixel Count
rel = mean2(redImage(find(redImage)))
19. Algorithm in Code
Threshold for Green Color
GhueThresholdLow = 0.15;
GhueThresholdHigh = 0.60;
GsaturationThresholdLow = 0.36;
GsaturationThresholdHigh = 1;
GvalueThresholdLow = 0;
GvalueThresholdHigh = 0.8;
20. Algorithm in Code
Now apply each color band's particular thresholds to the color band for Green
GhueMask = (hImage >= GhueThresholdLow) & (hImage <= GhueThresholdHigh);
GsaturationMask = (sImage >= GsaturationThresholdLow) & (sImage <=
GsaturationThresholdHigh);
GvalueMask = (vImage >= GvalueThresholdLow) & (vImage <=
GvalueThresholdHigh);
GcoloredObjectsMask = uint8(GhueMask & GsaturationMask & GvalueMask);
GstructuringElement = strel('disk', 4);
GcoloredObjectsMask = imclose(GcoloredObjectsMask, GstructuringElement);
21. Algorithm in Code
Fill in any holes in the regions, since they are most likely red also.
GcoloredObjectsMask = imfill(logical(GcoloredObjectsMask), 'holes');
GcoloredObjectsMask = cast(GcoloredObjectsMask, 'like', I);
Use the colored object mask to mask out the colored-only portions of the rgb
image.
GmaskedImageR = GcoloredObjectsMask .* red;
GmaskedImageG = GcoloredObjectsMask .* green;
GmaskedImageB = GcoloredObjectsMask .* blue;
greenImage = cat(3, GmaskedImageR, GmaskedImageG, GmaskedImageB);
Green Pixel Count
gel = mean2(greenImage(find(greenImage)))
22. Algorithm in Code
Find the Maximum Number of Pixels to determine the ripeness
ripe = max([yel rel gel])
if ripe == yel
ripeVal = 'Yellow'
else if ripe == rel
ripeVal = 'Red'
else if ripe == gel
ripeVal = 'Green'
else
ripeVal = 'Undefined'
end
end
end
% Store Values in Local Database
data = [radii2,area,volume,weight,centroidxavg,centroidyavg,rel,gel,yel,ripeVal]
dlmwrite('test.csv',data,'delimiter',',','-append');
23. R Code
Load Required Library
require(e1071) #For SVM
require(rgl) #For 3 D Plotting
Load Data Set
FeaturesTrainingData <- read.csv("G:/8th sem/BTP Tomato Complete
Sample/FinalBTPGUI/FeaturesTrainingData.csv")
View(FeaturesTrainingData)
Create Data Frame from Training Data
ftd <-
data.frame(R=FeaturesTrainingData$Radius,A=FeaturesTrainingData$Area,V=FeaturesT
rainingData$Volume,W=FeaturesTrainingData$Weight,C=FeaturesTrainingData$Class)
View(ftd)
24. R Code
Create SVM Model
svm_model <- svm(C~., ftd, type='C-classification', kernel='linear',scale=FALSE)
w <- t(svm_model$coefs) %*% svm_model$SV
Visualizing the Hyperplane and Support Vectors
detalization <- 100
grid <- expand.grid(seq(from=min(ftd$R),to=max(ftd$R),length.out=detalization),
+ +
seq(from=min(ftd$A),to=max(ftd$A),length.out=detalization))
z <- (svm_model$rho- w[1,1]*grid[,1] - w[1,2]*grid[,2]) / w[1,3]
plot3d(grid[,1],grid[,2],z, xlab="PC1 (72%)", ylab="PC2 (19%)", zlab="PC3 (7%)", col="pink")
spheres3d(ftd$R[which(ftd$C=='A')], ftd$A[which(ftd$C=='A')], ftd$V[which(ftd$C == 'A')],
col='red',type="s",radius=0.01)
spheres3d(ftd$R[which(ftd$C=='B')], ftd$A[which(ftd$C=='B')], ftd$V[which(ftd$C == 'B')],
col='blue',type="s",radius=0.01)
25. Result
A B C
14 0 2
5 0 0
4 0 18
Accuracy %age : 74.42%
Confusion Matrix
35. CONCLUSION AND RESULTS
In this automated system, we have developed a methodology which identifies
and detect tomato ripeness and its quality based on an image processing
algorithm followed by classification process. In the algorithm, tomatoes
images are acquired via different perspectives and preprocessed and
segmented.And after segmentation process, five features are extracted such
as area,volume,weight,radius,perimeter and ripeness.The real value of
features of tomatoes are calculated such as volume using Archimedes
Principle and weight using weighing machine.
In classification process, SVM is used with multi-class classification in
WEKA.We provided the training data in WEKA and Weka calculated SVM
accuracy of 74.41% and classified into three classes named A, B and C which
represent quality class of very good, good and poor respectively.
36. Future Scope
The future scope of this Automated Application is in the industry of harvest
engineering and Automated Agriculture.
This Automated Application will be helpful for easing of Supply Chain Management.
This Application is used to detection of bad quality tomatotes using Computer
Vision.
It is also used to analyzed remote sensing data for farming purpose and large scale
control production.
Image processing technique has been proved as effective machine vision
system for agriculture domain. we can conclude that image processing was
the non invasive and effective tool that can be applied for the
agriculture domain with great accuracy for analysis of agronomic
parameters.
37. References
Rafael C.Gonzalez and Richard E. woods, “Digital Image Processing”, Pearson
Education, Second Edition,2005
A simple method for removing reflection and distortion from a single
image.[IJEIT]
Recognition and localization of ripen tomato based on machine vision.[AICS]
Noise removal and enhancement of binary images using morphological
operations.
Tomato classification and sorting with machine vision using SVM,MLP and
LVQ.[IJACS]