ALDRIN CEDRIC BIN NICHOLAS 78717

CHONG GUI YI 81689

YEE SIAO YI 81537

MARINE DAYANG ANAK NGEDUN 81856

The number of training images used in the example is 916. The size of the input image is 256 x 256.

b. There are two types of images used for the training process. What are these images?

Two types of images used for the training process are Pristine Images and Bilaterally Filtered Images. Pristine images are original and unaltered images. Bilaterally filtered images are the result of applying a specific type of filter called bilateral filtering, which smoothens images while preserving important features like edges.

c. What are the inputs of the network? What are the desired responses of the network?

The inputs of the network are the Pristine Images, and the desired responses of the network are the corresponding Bilaterally Filtered Images.

d. What are the layers used in the multiscale CAN from the Deep Learning Toolbox™?

The layers used in the multiscale CAN from the Deep Learning Toolbox™ include imageInputLayer, convolution2dLayer, batchNormalizationLayer, leakyReluLayer, regressionLayer, adaptiveNormalizationMu and adaptiveNormalizationLambda.

e. What is the first layer, middle layer, and the last layer of the CAN network of the example?

The first layer is the imageInputLayer, the middle layers include convolutional layers, batch normalization layers, adaptive normalization layers, addition layers, and leaky ReLU layers. The last layer is the regression layer.

f. What is the training optimizer used to train the network? What are the default values of the hyperparameter of the network?

The training optimizer used to train the network is "Adam". The default values of the hyperparameters include learning rate of 0.0001, a maximum of 15 epochs, and a mini-batch size of 1.

1. marinedayangngedun@gmail.com

2.aldrincedric01@gmail.com

3.siaoyiyee@gmail.com

4. guiyichong727@gmail.com

📌4 December 2023

https://meet.google.com/hhf-scdd-nte?pli=1

Our agenda :

• Short Introduce for each group member

• Assignment Timeline

• Explanation for the assignment guidelines ( what we need to do first )

• Explain the goal of the group assignment ( Every Week need to have a progress and if have a problem need to inform in group what apps

📌7 January 2024

https://meet.google.com/pcq-heye-syq

Our agenda :

• Meeting details :

  Our meeting content on our presentation,

  1. Get Familiar with MATLAB

  2. Explain about part A

  3. Explain about part B

  4. Explain about part C

  5. Questioning each other about the assignment while teaching each other

Week 3

Group Assignment

Week 4- Brief and Install Matlab

Week 5- Start first move

Week 6-

Week 7-

Week 8-

Week 9-

Week 10- Able to finish all of the technical tasks and report

Preparation before presentation

Week 11-Report

Week 12-Slide and Report

Week 13- Presentation

Note : do the correction on part yang Dr Teh tegur

1. Introduction

2. Part a (explain about the output session and task 1-4)

3. part a (explain about task 5-6)

4. part b

5. part c i

6. part c ii

7. Conclusion

For the part a task, you need to explain what is grayscale, threshold and so on at the first of your sentence to make sure that you're understand what is it for.

📌8 & 11 January 2024

📌 Week 13

Report Submission :

📌15 January 2024

📌Week 14

📌 Monday ( Before 4.00 pm)

File name: appearing the file path for reference purpose

Grayscale

Removing noise by median

creating an image histogram

threshold image

adjusting intersity values using histogram equalization

detecting edge by using the edge function

detecting line by using the hough transform

clear button: to reset all of the output