Đồ án tốt nghiệp - Development of an AI system for data extraction from Vietnamese printed documents

Tên môn học: Khóa luận tốt nghiệp

Giá: 97.000đ

Tổng thanh toán:

97.000đ

Người đăng tải:

#10377

Chi tiết tài liệu :

Đồ án tốt nghiệp ngành Robot và trí tuệ nhân tạo - Development of an AI system for data extraction from Vietnamese printed documents - Trường Đại học Sư phạm Kỹ thuật Thành phố Hồ Chí Minh (HCMUTE)

Định dạng	PDF
Dung lượng	6.01 MB
Số trang	109
Ngành Ngành học chỉ mang tính chất tham khảo	Robot và trí tuệ nhân tạo

Lượt xem	99
Ngày đăng	04/01/2026

MINISTRY OF EDUCATION AND TRAINING
HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION

FACULTY OF MECHANICAL ENGINEERING

GRADUATION THESIS

DEVELOPMENT OF AN AI SYSTEM FOR
DATA EXTRACTION FROM VIETNAMESE
PRINTED DOCUMENTS
Supervisor:
Student:
Student ID:
Student:
Student ID:
Student:
Student ID:
Year of Admission:

BUI HA DUC, PhD
HUYNH VINH PHUC
20134005
NGUYEN XUAN PHI
20134004
CHU NHAT MINH QUAN
20134021
2020-2024

Ho Chi Minh city, July 2024

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF MECHANICAL ENGINEERING

DEPARTMENT OF MECHATRONICS

GRADUATION THESIS

DEVELOPMENT OF AN AI SYSTEM FOR
DATA EXTRACTION FROM VIETNAMESE
PRINTED DOCUMENTS
Supervisor:

BUI HA DUC, PhD

Student:

HUYNH VINH PHUC

Student ID:

20134005

Student:

NGUYEN XUAN PHI

Student ID:

20134004

Student:

CHU NHAT MINH QUAN

Student ID:

20134021

Class:

20134

Year of Admission:

2020 - 2024

Ho Chi Minh City, July 2024

COMMITMENT
• Project: DEVELOPMENT OF AN AI SYSTEM FOR DATA EXTRACTION
FROM VIETNAMESE PRINTED DOCUMENTS
• Lecturer: Bui Ha Duc, PhD
• Student: Huynh Vinh Phuc
• Student ID: 20134005

- Class: 20134

• Adress: Hiep Phu Ward, Thu Duc City, Ho Chi Minh City
• Phone number: 0357642052
• Email: [email protected]
• Student: Nguyen Xuan Phi
• Student ID: 20134004

- Class: 20134

• Adress: Linh Chieu Ward, Thu Duc City, Ho Chi Minh City
• Phone number: 094540064
• Email: [email protected]
• Student: Chu Nhat Minh quan
• Student ID: 20134021

- Class: 20134

• Adress: Hiep Phu Ward, Thu Duc City, Ho Chi Minh City
• Phone number: 0938822147
• Email: [email protected]
• Graduation thesis submission date: 04/07/2024
• Commitment: “I affirm that the graduation thesis presented here is the result of my
research and efforts. I have not replicated any content from published articles
without appropriate citations. Should any breach be identified, I acknowledge full
accountability for the consequences.”
Ho Chi Minh City, July 4, 2024

i

ACKNOWLEDGEMENT
We would like to begin by expressing our profound gratitude, on behalf of our team,
to our supervisor, Bui Ha Duc, PhD. Your unwavering commitment, expertise, and guidance
have been instrumental in shaping our research and leading us to success. Your mentorship,
patience, and continuous encouragement have been vital in navigating our academic
journey. Your extensive knowledge and valuable in
...

...
invariant
keypoints. International journal of computer vision, 60, 91-110.
[15] Muja, M., &amp Lowe, D. G. (2009). Fast approximate nearest neighbors
with automatic algorithm configuration. VISAPP (1), 2(331-340), 2.
[16] Brown, M., &amp Lowe, D. G. (2002, September). Invariant features from
interest point groups. In Bmvc (Vol. 4, No. Sep, pp. 398-410).
[17] Liao, M., Wan, Z., Yao, C., Chen, K., &amp Bai, X. (2020, April). Realtime scene text detection with differentiable binarization. In
Proceedings of the AAAI conference on artificial intelligence (Vol. 34,
No. 07, pp. 11474-11481).
[18] Pham, Q. (n.d.). VietOCR - Nhận Dạng Tiếng Việt Sử Dụng Mô Hình
Transformer và AttentionOCR. https://pbcquoc.github.io/vietocr
[19] Wu, T., &amp Dong, Y. (2023). YOLO-SE: Improved YOLOv8 for
Remote Sensing Object Detection and Recognition. Applied Sciences,
13(24), 12977.

Table IV shows the results of some correctly recognized
images and Table V shows some results of misidentified
images after testing the TransformerOCR model. From the
two tables, it is shown that as the number of characters in the
image grows, the model struggles to accurately recognize
them. For instance, consider the image major_6.png with the
label CNKT IN, containing only 6 characters, which is
recognized correctly. Conversely, in the case of the image
major_48.png with the label Kỹ thuật nữ công, consisting of
13 characters, the model struggles to recognize accurately.
TABLE IV.

Name

ILLUSTRATION OF CORRECTLY RECOGNIZED IMAGES

Label

Recognition

name_10.png

Nguyễn Hồng
Sơn

Nguyễn Hồng
Sơn

major_6.png

CNKT In

CNKT In

dept_25.png

Đào tạo QT

Đào tạo QT

TABLE V.

Name

Image

ILLUSTRATION OF MISIDENTIFIED IMAGES

Image

Label

Recognition

name_36.png

Võ Trần Hoài
Ân

Vố Tân Hoài
An

major_48.png

Kỹ thuật nữ
công

khi thuột nử
công

dept_44.png

Cơ khí động
lực

Có Khi đông
lược

IV. CONCLUSION
This research endeavors to a system employing AI
techniques to accurately and efficiently extract information
from Vietnamese documents. Utilizing deep learning models
like YOLO for layout analysis, layout parsing, DBN for text
detection, and TransformerOCR for text recognition. We have
built a system that can handle handwriting text. Various
preprocessing methods were explored to enhance accuracy
and efficiency. The study delves into the realm of Deep
Learning, focusing on extracting text from images and its
applications. Evaluation of methods revealed the effectiveness

6