This paper focuses on exploring Machine learning methods to automate this process. The main challenge we face is in generating adequate training datasets to train the Machine learning model. Creating training data by manually segmenting real images is very labour-intensive, so we have instead tested methods of automatically creating synthetic training datasets which have the same attributes of the original images. The generated synthetic images are used to train a U-net Model, which is then used to segment the original bread dough images. The trained U-net outperformed the previously used segmentation techniques while taking less manual effort.
Nội dung trích xuất từ tài liệu:
Thesis for the degree of Master of Engineering: Machine Learning for Volumetric Data Analysis of Bread Dough: Meeting the Synchrotron Challenge
Thesis for the degree of Master of Engineering: Machine Learning for Volumetric Data Analysis of Bread Dough: Meeting the Synchrotron Challenge
Số trang: 75
Loại file: pdf
Dung lượng: 16.72 MB
Lượt xem: 5
Lượt tải: 0
Thông tin tài liệu:
Tìm kiếm theo từ khóa liên quan:
Thesis for the degree of Master Thesis for the degree of Master of Engineering Machine Learning Volumetric Data Analysis Bread Dough Synchrotron ChallengeTài liệu có liên quan:
-
9 trang 192 0 0
-
Nuclear energy system's behavior and decision making using machine learning
8 trang 118 0 0 -
95 trang 74 0 0
-
Ebook Disrupting finance: FinTech and strategy in the 21st century
194 trang 58 0 0 -
Bài giảng Trí tuệ nhân tạo dành cho mọi người - ThS. Nguyễn Ngọc Tú
149 trang 58 0 0 -
Knowledge management system building blocks
12 trang 50 0 0 -
Ebook The data science design manual: Part 2
240 trang 48 0 0 -
Building credit scoring process in Vietnamese commercial banks using machine learning
14 trang 47 0 0 -
Phát hiện tin giả với python và machine learning
14 trang 46 0 0 -
Pseudorandom sequences classification algorithm
8 trang 44 0 0
