Here, the data set represents the collection of elements that give rights to conduct the research. By trying to prove that coconut shell has energy properties and its carbon neutral, various external components have been used to get the extraction of some morphological features of coconut shell and wood, another main stage of this project is color infusing; which consists of the conversion of the image color from RGB to grayscale, which plays an important role in permitting the accusation of a clear and accurate overview of the object. It also reveals and identifies all the pattern presents, then via obtaining the object description, analysis of the data can be conducted.
It is necessary to notice that every step was enshrined in the algorithm by a MATLAB language syntax. The following steps are the main processes used for the analysis:
This step consists of Renaming input data for the software to identify them and then be able to recognize them at any point of time when the data are needed for processing.
After declaring the variables (Images), which do not appear directly on the workspace. Another line of code is written for the image to be displayed and reassure the user of the effectiveness of the data.
Efficiency in image processing attainment requires the image size to be reduced by converting the RGB images into grayscale.
-Image enhancement
Reducing the size of an image makes digital image processing easier but may also affect the quality of the image, this is why we enhance the gray image in order to eliminate all flaws and getting a much clear view of the working area.
Applying thresholding consist of segmenting a grayscale image by changing pixels intensity and applying threshold values. This leads to separating the image into foreground value and background value. This values represents numerous highlighted sections of the images to be analyzed.
S = imread('IMG_5087.jpeg');
imshow (S)
Sgray = rgb2gray (S);
imshow (Sgray)
Sh = histeq (Sgray);
imshow (Sh)
level = 0.5;
Stresh = imbinarize (Sh,level);
imshow (Stresh)
W = imread ('IMG_3710.jpeg');
imshow (W)
Wgray = rgb2gray (W);
imshow (Wgray)
Wtresh = imbinarize(Wh,level);
imshow (Wtresh)
One of the most important steps in the image analysis which is using the operated via the syntax < < Stresh = imbinarize (Sh,level);>> for the coconut shell and the syntax < < Wtresh = imbinarize(Wh,level);>> for the wood is called thresholding which is meant to create a binary image of the enhanced gray pictures. Threshold values will be inputed and varied until the pixel intensity of the images are manipulated enough to separate the wanted regions from the unwanted ones. Then, the Neural network training tool is activated as a section in Matlab that performs Pattern recognition which is the last step in the experiment.
level2 = 0.6;
Wtresh2 = imbinarize (Wh,level2);
imshow (Wtresh2)
Wtresh3 = imbinarize(Wh,level3);
imshow (Wtresh3)
imshowpair(Stresh2,Wtresh3,'montage')
imshowpair(Stresh3,Wtresh4,'montage')
As the images have been inputted, the default of ‘Number of neurons’ is put into memory. This number is 10 to evaluate the threshold coconut shell image and later add ‘1’ to the default number of neurons to evaluate the threshold charcoal wood image.
4.1 Performance of Energy properties
The following graphs represent the performance of energy properties collected right after the thresholding process. It shows the presence of other types of energy and the slight difference between coconut shell and charcoal wood.
Pattern Recognition with Matlab is basically defined as the process whereby; a received pattern is assigned to one of a prescribed number of classes which is operated with the neural network tool. The syntax to have access to that tool is ‘nprtool’.
Once the tool is accessed, the pattern recognition application is selected and then the ‘train’ button is activated to allow the software to evaluate the output of the written algorithm and apply pattern recognition.
In the cases, two sets of patterns from a coconut shell and a charcoal revealed by an algorithm will be evaluated by the software and create different analysis matrixes that will analyse the patterns through machine learning system. The Different Matrixes in the case are:
-
Training confusion matrix; which is a matrix meant to train or apply directly the applied method and different methods that can be used to analyse patterns.
-
Testing confusion matrix; which is a matrix meant to test directly the applied method and different methods that can be used to analyse patterns.
-
Validation confusion matrix; which is the matrix meant to analyse directly the performance of the energy properties in the objects.
-
All confusion matrix; which is the final matrix displaying the result of the patterns recognition.
4.2.1 Threshold comparison
Threshold comparison is one of the results displaying the difference between the Matrixes of the raw image and the processed one. In the case we have different values visible in the matrixes from the gray scale stage to the thresholding stage.
4.3 Results of Pattern Recognition
The confusion Matrixes below are the results of the pattern recognition analysis conducted. The results in the green boxes are called the ‘True positives’ which in this case mean that, the method used to segment patterns for the image is the right one hence delivers the energy property index at the bottom right boxes. The pink boxes are called the ‘True negatives’ which indicates that the other methods directly applied were not appropriate to analyze the patterns. Here, the results of ‘99.4%’ of energy property index in the two confusion matrixes table is the proof that coconut shell is as carbon based as charcoal wood is and a good bioenergy agent.
By using more than one method to conduct the analysis and writing the corresponding algorithms of coconut shell and wood as well abiding by the policies and step involved in this project, provides a solid backing of the research conducted. The positive results obtained in both cases establishes a convincing assessment of the bioenergy properties of coconut shell as expected and so a pronouncement of coconut shell being a sthece of energy is duly made.
4.4 A Proposed Framework of Potentials of Bioenergy (Coconut Shell) For Sustainability
Generally, bioenergy plants increase soil carbon and fix atmospheric carbon for plant growth, making it essential in earth’s carbon cycle. Similarly, Biomass provide hydrogen, which can be chemically extracted to produce green hydrogen fuels for many benefits. Establishing the bioenergy chrematistics of coconut shell, possesses a great potential for the application of benefits of this bioenergy fuels for energy sustainability in sub- Saharan Africa. Figure 27 illustrates a proposed framework of the potentials of coconut shell.