racoolanding

[racoolanding]

NO DSP CLASS.

11.14.17. No dsp class this week..

[racoolanding]

No Class Tuesday!

11.07.17. No DSP Class Again.

[racoolanding]

Holiday!

10.31.17 No DSP Class Today!

[racoolanding]

3rd Major Activity.

10.29.17. Abstracts to be submitted for the ‘First National Coffee Education Congress 2017′ for evaluation. 

Photo by Engr. Edwin Arboleda

[racoolanding]

Finally, the reporting was over!!

10.24.17 After the reporting of the downloaded journal, I have learned the use of the classifiers in doing such journals based on its different usage from every report I heard.

Engr. Arboleda, also present to us his journal about Cavite Coffee Beans processed using the Artificial Intelligence of Matlab. He also taught us how he had done that  using Matlab; the neutral network tool –nntool; and how to input data such as the ‘inputs’, ‘outputs’,  and ‘test’ data from the excel to matlab.

Moreover, he also informed us to the upcoming “First National Coffee Congress” on the second week of November that will be held in our University and we are challenge to make our own journal to be pass during the congress, and the abstract must be pass as a major activity on Saturday, October 28, 2017. (Hopefully we’ll make it in four days :-) hahaha

[racoolanding]

No Classes Tuesday!

10.17.17 I prepared for school last night, I even finished my laboratory report and slept early, waking up this morning with this news- nationwide class suspension due to the continuation of 2-day strike of the Jeepney drivers,..  so DSP reporting was also suspended -.-

Source: ABS-CBN News- Facebook Page ;; https://www.facebook.com/abscbnNEWS/posts/10155627282985168

[racoolanding]

UGames2017.

10.10.17. No DSP Class today due to the University Games.

© image by: The Gazette –Student Publication Unit of  Cavite State University Main Campus. https://www.facebook.com/TheGazetteSPU/ 

[racoolanding]

2MajorActivities.

10.03.17 No DSP class today due to an unexpected reason, but we passed the hardcopies of the two major activities on our Instructor’s table at the Department. :-)

[racoolanding]

2nd MajorActivity.

9.29.17 Morphological features (Surface area, perimeter, equivalent diameter and roundness) were extracted from the three varieties of coffee beans: Robusta, Excelsa and Liberica from different parts of Cavite, with the use Matlab. 

[racoolanding]

Major Activity Day.

09.26.17 No DSP class today, but we are given the 2nd major activity; it is to extract the morphological features for the variety of three coffee beans which are the robusta, excelsa, and liberica. Surface area, perimeter, equivalent diameter and roundness are to be extract and plot in excel. This activity is almost similar to the exercise we had done few weeks ago when the image processing was introduced to the class by our instructor.

[racoolanding]

Report.

09.19.17 Since, the reporting was suspended for two consecutive weeks; I decided to just continue my report here at tumblr… :-)

The journal entitled “Monitoring and Controlling Rice Diseases Using Image Processing Techniques” by A. Joshi and B. Jadhav from Savitribai Phule Pune University, India, 2016 aims the development of an automated system for identifying and classifying different diseases of rice plants in their country. They collected 115 images of four diseases -The Rice Bacterial Blight (RBB); the Rice Blast (RB); the Rice Brown Spot (RBS); and the Rice Sheath Rot (RSR), where the color and shape features extraction using the image processing tool of Matlab have been carried out.

The image was converted from RGB image into YCbCr space for some reasons: first since in YCbCr plane infected part can be easily detected; second is that the color difference of human discrimination can directly uttered by Euclidean distance in YCbCr color space; third is that the intensity and chromatic components can be used separately; and fourth is that plants’ infected spots form small cluster in Cr space.

The feature extraction of the leaves was done because it might help to the study since the color of the leaves is changed when it is infected by any disease. Informations on shapes and the colors of the infected parts are gathered and the segmented image is converted into a binary image and the number of connected components is calculated. Area and centroid of each connected components are calculated as well.

The logic to find following features is based on the extraction techniques used for recognition of hand written character:

1.       The number of horizontal lines.

2.       The average length of horizontal lines.

3.       The number of right diagonal lines.

4.       The average length of right diagonal lines.

5.       The number of vertical lines.

6.       The average length of vertical lines.

7.       The number of left diagonal lines.

8.       The average length of the length diagonal lines.

9.       The number of intersection points.

 These extracted features are combined and used as an input to classifiers to help not only to diagnose the diseases accurately but to classify diseases as well.

[racoolanding]

FreeDay.

09.19.19 No DSP class today.

[racoolanding]

Suspended.

09.12.17 I woke up late today (9:30 am), then I hurriedly went out of my room and asked my mother why she didn’t wake me up, because that time I don’t have any idea about the class suspension made by Governor Remulla due to heavy rainfall caused by Thunderstorms, because I gone to bed early last night, right after I finished reviewing Principles of Communication as well as my assignment (a journal) for Signals, Spectra and signal processing which I supposed to report today.

Since classes are suspended today, allow me to share to you guys my report :-)

This journal entitled “Monitoring and Controlling Rice Diseases Using Image Processing Techniques” by A. Joshi and B. Jadhav from Savitribai Phule Pune University, India, that aims the development of an automated system for identifying and classifying different diseases of rice plants in their country. To conduct the study, they collected 115 images of four diseases -The Rice Bacterial Blight (RBB); the Rice Blast (RB); the Rice Brown Spot (RBS); and the Rice Sheath Rot (RSR), where the color and shape features extraction using the image processing tool of Matlab have been carried out.

To be continued…

© image by GMA News Online

[racoolanding]

Major Activity 1

09.08.17 Formatting a journal and using mendeley......

.

.

.

.

.

yes, activity sent!

[racoolanding]

Image Processing.

09.05.17 Before, I have no idea with the so called Image processing, how it is being use and done. Today, our instructor -Engr. Arboleda, introduced us the image processing which surprisingly a part or process that can be done using the Matlab software.

Image Processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. It is a type of signal processing in which input is an image and output may be image or characteristics/ features associated with that image. [1]

With a series of imread which can read the image file name for the image to appear in the software; variable descriptions which make use of the alphabet letters to represent what you want to see, for example b=rgb2gray(a)-that converts the image of variable (a) into a grayscale image; imshow which make the variable descriptions appear as the old or new image; and figure which renames the new variable image.

Since the main purpose of this is to process image –to describe things in the picture in terms of area, perimeter, Equivalent Diameter and roundness since it is irregular in shape, we can actually get this with the matlab image process.

With this exercise using a series of pictures of different coffee beans in Cavite with white background (some pictures are from the journal of Engr. Arboleda), we can compare the difference of the coffee beans of different kinds from different parts of Cavite such as the Excelsa from Indang, Liberica from Amadeo, Excelsa from Alfonso and Liberica from Indang in terms of areas, perimeter, equivalent diameter and roundness which we plotted in Microsoft excel.

 [1] https://sisu.ut.ee/imageprocessing/book/1

[racoolanding]

Operations on Sequences

08.29.17. More function editors for the last meeting in the month of August.

Signal Addition uses the arithmetic operator “+” for a sample- by sample addition given by { x1(n)} +  { x2(n)} = { x1(n) +  x2(n)}, and it uses the sigadd function

function [y,n] = sigadd (x1, n1, x2, n2)

% implements y(n)= x1(n) + x2(n)

% ------------------------------

% [y,n]= sigadd(x1, n1, x2, n2)

% y = sum sequence over n, which includes n1 and n2

% x1 = second sequence over n2 (n2 can be different from n1)

%

n = min(min(n1), min(n2)):max(max(n1), max(n2)); % duration of y(n)

y1 = zeros(1,length(n)); y2 = y1; %initialization

y1(find((n>=min(n1))&(n<=max(n1))==1))=x1; % x1 with duration of y

y2(find((n>=min(n2))&(n<=max(n2))==1))=x2; % x2 with duration of y

y=y1 + y2;

 Signal Multiplication uses the array operator “.*” for a sample-by sample multiplication (or “dot” multiplication) given by { x1(n)} .  { x2(n)} = { x1(n)  x2(n)}, and it uses the sigmult function which is almost similar to the sigadd function,

function [y,n] = sigmult (x1, n1, x2, n2)

% implements y(n)= x1(n) * x2(n)

% ------------------------------

% [y,n]= sigmult(x1, n1, x2, n2)

% y = product sequence over n, which includes n1 and n2

% x1 = first sequence over n1

% x2 = second sequence over n2 (n2 can be different from n1)

%

n = min(min(n1), min(n2)):max(max(n1), max(n2)); % duration of y(n)

y1 = zeros(1,length(n)); y2 = y1;                %

y1(find((n>=min(n1))&(n<=max(n1))==1))=x1;       % x1 with duration of y

y2(find((n>=min(n1))&(n<=max(n1))==1))=x2;       % x2 with duration of y

y=y1.*y2;

 Scaling , where each sample is multiplied by scalar α given by: α{ x(n)} = { α x(n)},that uses the operator “*” to implement the scaling operation in Matlab.

Shifting where each sample of x(n) is shifted by an amount k to obtain a shifted sequence y(n) given by y(n)= { x(n-k)} and uses the function,

function [y,n] = sigshift (x, m, n0)

% implements y(n) = x(n-n0)

% -------------------------

%[y,n] = sigshift(x, m, n0)

%

n = m + n0; y = x;

 Folding that flips the given sample such as y(n)= { x(-n)} that uses the function,

function [y,n] = sigfold(x,n)

% implements y(n) = x(-n)

% -------------------------

%[y,n] = sigfold(x,n)

%

y = fliplr(x);

n= -fliplr(n);

[racoolanding]

DSP Activity

08.22.17. Since classes are suspended due to high tides, we had just installed the Matlab software and worked with the activity on Digital Signal Processing(DSP). From the books in the library and from other internet sources, I had collected five examples for each -Unit sample, Unit step, Unit ramp and Even-odd, then plotted those examples using the M-file and Direct Methods. This are actually the methods to output desired signal, the first one is the M-file method which make use of the function editor, where each -Unit sample, Unit step, Unit ramp and Even-odd has its own:

Unit Sample:

function [x,n] =impseq(n0,n1,n2)

% generates x(n) = delta (n-n0); n1 <= n <= n2

% --------------------------------------------

% [x,n]=impseq(n0,n1,n2)

%

n= [n1:n2]; x = [(n-n0)==0];

 Unit Step:

function [x,n] = stepseq(n0,n1,n2)

% generates x(n)=u(n-n0); n1 <= n <= n2

%-------------------------------------

% [x,n]=stepseq (n0,n1,n2)

%

n= [n1:n2]; x=[(n-n0) >= 0];

 Unit Ramp:

function [x,n]= unitramp(n0,n1,n2)

% generates x(n) = r(n-n0); n1 <= n <= n2

% ---------------------------------------

% [x,n]= unitramp (n0,n1,n2)

%

n=[n1:n2];

x=[(n-n0).*(n >= n0)];

 Evev-Odd:

function [xe,xo,m] = evenodd(x,n)

% Real signal decomposition into even and odd parts

% -------------------------------------------------

% [xe, xo, m] = evenodd(x,n)

%

if any(imag(x) ~= 0)

   error('x is not a real sequence')

end

m = -fliplr(n);

m1 = min([m,n]); m2 = max([m,n]); m = m1:m2;

nm = n(1)-m(1); n1 = 1:length(n);

x1 = zeros(1, length(m));

x1(n1+nm) = x; x = x1;

xe = 0.5*(x + fliplr(x));

xo = 0.5*(x - fliplr(x));

 This function editors/ function m-file are being used to overcome the shortcomings of the script m-file, while the second one is the Direct Method which can be done even without the function editor.