Đồ án tốt nghiệp - Approximate computing in sobel edge detection

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

APPROXIMATE COMPUTING IN SOBEL EDGE
DETECTION
NGUYEN TRUNG TIN
Student ID: 21161268
DOAN THI MY PHUONG
Student ID: 21161259
Major: ELECTRONICS AND COMMUNICATION ENGINEERING
TECHNOLOGY
Advisor: PHAM VAN KHOA, Ph.D.

Ho Chi Minh City, July 2025
i

H O CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

APPROXIMATE COMPUTING IN SOBEL EDGE
DETECTION
NGUYEN TRUNG TIN
Student ID: 21161268
DOAN THI MY PHUONG
Student ID: 21161259
Major: ELECTRONICS AND COMMUNICATION ENGINEERING
TECHNOLOGY
Advisor: PHAM VAN KHOA, Ph.D.

Ho Chi Minh City, July 2025
ii

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

-Ho Chi Minh City, July 07, 2025

GRADUATION PROJECT ASSIGNMENT
Student ID: _21161268_____________
Student ID: _21161259_____________
Student ID: ___________________
Class: _21161FIE_________________
Phone number: ___________
Date of submission: ___________________
1. Project title: __ Approximate Computing In Sobel Edge Detection ___________
2. Initial materials provided by the advisor: ____________________________________
3. Content of the project: This thesis focuses on accelerating the Sobel edge detection algorithm
using approximate computing techniques on FPGA platforms. To reduce hardware resource usage
and power consumption, the study integrates approximate algorithm into the Sobel processing
pipeline and implements the design using Xilinx Vitis HLS. The system is deployed on a PYNQZ2 development board and compared against both an exact FPGA-based implementation and a
software-based CPU implementation. The results demonstrate that the approximate design
significantly reduces resource utilization and improves processing speed, while maintaining
acceptable image quality.
4. Final product: __Evaluation result between FPGA and compare to x86/ARM._ ________
ADVISOR
(Sign with full name)

iii

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

-Ho Chi Minh City, July 07, 2025

ADVISOR’S EVALUATION SHEET
Student name: ...NguyễnTrung Tín................................. Student ID: .....21161268.............
Student name: .. Đoàn Thị Mỹ Phương.......................

Student ID: .....21161259.............

Student name: ................................................................. Student ID: ................................
...

...
t., vol. 16, no. 2, 2011.
A. Canis et al., “LegUp: High-Level Synthesis for FPGA-Based
Processor/Accelerator Systems,” in Proc. ACM/SIGDA FPGA, 2011.
Xilinx Inc., Vitis HLS User Guide (UG1399), v2023.1. Available:
https://docs.amd.com
A. Capalija and F. A. Farahmand, “High-level synthesis of image processing
applications on FPGAs using Vivado HLS,” Proc. IEEE ISPACS, 2015.
AMD
Xilinx,
Vitis
Libraries:
Vision,
2023.
Available:
https://xilinx.github.io/Vitis_Libraries/vision
M. Sobhani and K. K. Parhi, “Efficient FPGA Implementation of Image
Processing Pipelines Using High-Level Synthesis and Optimized Vision
Libraries,” IEEE Access, vol. 8, pp. 128356–128370, 2020.
A. Tumeo et al., “Accelerating Real-Time Vision Applications on FPGAs Using
HLS Libraries,” Proc. IEEE FCCM, 2019.
Xilinx Inc., Zynq-7000 SoC Technical Reference Manual, UG585 (v1.13), 2023.
AMD, Vitis Unified Software Platform Documentation, 2023. Available:
https://docs.amd.com
J. Fowers et al., “A Configurable Cloud-Scale DNN Processor for Real-Time AI,”
Proc. ACM/IEEE ISCA, 2018.
Yu-Ting Pai and Yu-Kumg Chen. “The Fastest Carry Lookahead Adder”.
Proceedings of the Second IEEE International Workshop on Electronic Design,
Test and Applications (DELTA’04) 0-7695-2081-2/04 $ 20.00 © 2004 IEEE.
58

[19].
[20].

[21].

[22].

[23].

Padmanabhan Balasubramanian, Nikos E. Mastorakis. “High-Speed and EnergyEfficient Carry Look-Ahead Adder”. J. Low Power Electron. Appl. 2022, 12, 46.
Dr. Nataraj K R, Dr. Choodarathnakara A L, Chethan K S, Sinchana G S.
“Analysis of Image Quality using Sobel Filter”. International Conference on
Inventive Systems and Control (ICISC 2019). IEEE Xplore Part Number:
CFP19J06-ART ISBN: 978-1-5386-3950-4
Yunchul Chung and Youngmin Kim. “Comparison of Approximate Computing
with Sobel Edge Detection”. IEIE Transactions on Smart Processing and
Computing,
vol.
10,
no.
4,
August
2021.
https://doi.org/10.5573/IEIESPC.2021.10.4.355
Thang Viet Huynh. “FPGA-based Acceleration for Convolutional Neural
Networks on PYNQ-Z2”. International Journal of Computing and Digital Systems
ISSN (2210-142X) Int. J. Com. Dig. Sys. 11, No.1 (Jan-2022).
https://dx.doi.org/10.12785/ijcds/110136
Leonardo B. Soares, Morgana M. A. da Rosa, Claudio M. Diniz , Eduardo A. C.
da Costa, Sergio Bampi, PGMicro. “xploring Power-Performance-Quality
Tradeoff of Approximate Adders for Energy Efficient Sobel Filterin”. 2018 IEEE
9th Latin American Symposium on Circuits &amp Systems (LASCAS).

59