Đồ án tốt nghiệp - Semantic Segmentation Of Pet Images Using Segmentation Model Pytorch

HOCHIMINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION THESIS
MAJOR IN ELECTRONICS AND TELECOMMUNICATION
ENGINEERING TECHNOLOGY

SEMANTIC SEGMENTATION OF PET
IMAGES USING SEGMENTATION
MODEL PYTORCH

ADVISOR: LE MINH THANH, M.Eng.
STUDENT: CAO TRAN HUNG
CODE: 18161017

HoChiMinh city, June 2024

HOCHIMINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION THESIS
MAJOR IN ELECTRONICS AND TELECOMMUNICATION
ENGINEERING TECHNOLOGY

SEMANTIC SEGMENTATION OF PET
IMAGES USING SEGMENTATION
MODEL PYTORCH

ADVISOR: LE MINH THANH, M.Eng.
STUDENT: CAO TRAN HUNG
CODE: 1816101

HoChiMinh city, June 2024

HOCHIMINH CITY UNIVERSITY OF

THE SOCIALIST REPUBLIC OF VIETNAM

TECHNOLOGY AND EDUCATION

Independence - Freedom – Happiness

FACULTY OF INTERNATIONAL EDUCATION

-

HoChiMinh City, June 20th, 2024

GRADUATION PROJECT ASSIGNMENT
Student name: Cao Tran Hung

Student code: 18161017

Major: Electronics and Telecommunication Engineering Technology
Class: 18161CLA
Advisor: Le Minh Thanh, M.Eng.
Date of assignment: 01/3/2024

Date of submission: 20/6/2024

1. Thesis title: Semantic segmentation of pet images using Segmentation Model Pytorch
2. Initial materials provided by the advisor: Unet-based CNN, … dataset, image
segmentation methods.
3. Content of the thesis:
Content 1: The thesis is divided into five chapters covering the related literature and the
simulation.
Content 2: Study and apply the Unet-based pre-trained CNN to pet images.
Content 3: Simulation and evaluation of segmented pet images, including cats and dogs
inside.
CHAIR OF THE PROGRAM

ADVISOR

HOCHIMINH CITY UNIVERSITY OF

THE SOCIALIST REPUBLIC OF VIETNAM

TECHNOLOGY AND EDUCATION

Independence - Freedom – Happiness

FACULTY OF INTERNATIONAL EDUCATION

-

HoChiMinh City, June 20th, 2024

ADVISOR’S EVALUATION SHEET
Student name: Cao Tran Hung

Student ID: 18161017

Major: Electronics and Telecommunication Engineering Technology
Thesis title: Semantic Segmentation of Pet Images using Segmentation Model PyTorch
Advisor: Le Minh Thanh, M.Eng.
EVALUATION
1. Content of the thesis:
……………………………………………………………………………………………
2. Strengths:
……………………………………………………………………………………………
3. Weaknesses:
…………………………………………………………………………………………….
4. Approval for oral defense? (Approved or denied)
…………………………………………………………………………………………….
5. Overall evaluation: (Excellent, Good, Fair, Poor)
…
...

...
her than the problem. The
problem is to segment each animal into one frame, which is called “Instance
segmentation.”


Serves as a basis for identifying pet behavior by recording moments, serving the

purpose of training, which can be applied in many fields, such as training domestic
pets or circuses.

45

References
[1] R. L. a. D. He, Semantic Segmentation Based on Deeplabv3+ and Attention
Mechanism, 2021 IEEE 4th Advanced Information Management, Communicates,
Electronic and Automation Control Conference (IMCEC), Chongqing, China,
2021, pp. 255-259, doi: 10.1109/IMC.
[2] X. Li, Z. Zhao, and Q. Wang, ABSSNet: Attention-Based Spatial Segmentation
Network for Traffic Scene Understanding, in IEEE Transactions on Cybernetics,
vol. 52, no. 9, pp. 9352-9362, Sept. 2022, doi: 10.1109/TCYB.2021.3050558..
[3] A. Rosebrock, Instance segmentation with OpenCV, [Online]. Available:
https://pyimagesearch.com/2018/11/26/instance-segmentation-with-opencv/.

[4] A. Thakur, Image Segmentation Using Keras and Weights &amp Biases, [Online].
Available: https://wandb.ai/ayush-thakur/image-segmentation/reports/ImageSegmentation-Using-Keras-and-Weights-BiasesVmlldzoyNTE1Njc.
[5] Xu, Yan &amp Li, Yang &amp Liu, Mingyuan &amp Wang, Yipei &amp Lai, Maode &amp Chang,
Eric., Gland Instance Segmentation by Deep Multichannel Side Supervision.,
2016.
[6] Andy Chen, Chaitanya Asawa, Going beyond the bounding box with semantic
segmentation, [Online]. Available: https://thegradient.pub/semanticsegmentation/.
[7] Chhor, Guillaume and Cristian Bartolome Aramburu., “Satellite Image
Segmentation for Building Detection using U-net.”, 2017.
[8] Fritz, Deep Learning for Image Segmentation: U-Net Architecture, [Online].
Available: https://fritz.ai/deep-learning-for-image-segmentation-u-netarchitecture/.
[9] Omkar M Parkhi and Andrea Vedaldi and Andrew Zisserman and C. V. Jawahar,
46

The Oxford-IIIT Pet Dataset, [Online]. Available:
https://www.robots.ox.ac.uk/~vgg/data/pets/.
[10] The Difference Between Dice and Dice Loss, [Online]. Available:
https://pycad.co/the-difference-between-dice-and-dice-loss/
[11] Chauhan, Nagesh Singh. Model Evaluation Metrics in Machine Learning,
[Online]. Available: https://aiplanet.com/blog/model-evaluation-metrics-in-machinelearning/
[12] Koshike, Sai Kalyan. (2023). Semantic Segmentation of Lung Cancer Using
Custom U-Net Model.

47

APPENDIX
https://colab.research.google.com/drive/1YT7S3PU5MRK8FGCUVHNyWpErN
AUB6Ful?usp=sharing

48