2022 Fiscal Year Final Research Report
Development of Parametric Image Generation Model for Machine Learning
Project/Area Number |
19K12033
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 61010:Perceptual information processing-related
|
Research Institution | Sendai National College of Technology |
Principal Investigator |
Omachi Masako 仙台高等専門学校, 総合工学科, 教授 (90316448)
|
Co-Investigator(Kenkyū-buntansha) |
大町 真一郎 東北大学, 工学研究科, 教授 (30250856)
|
Project Period (FY) |
2019-04-01 – 2023-03-31
|
Keywords | パターン認識 |
Outline of Final Research Achievements |
We have conducted research to develop an image generation model capable of generating diverse and highly interpretable image data that can be used as training data for machine learning. The image is decomposed into meaningful basic elements, the basic elements are modeled, and the image is generated by combining the basic elements. The decomposition into basic elements was achieved by utilizing the correlation between pixels in the image and integrating pixels with high correlation. Experiments were conducted using images of road environments to confirm the effectiveness of the proposed method.
|
Free Research Field |
パターン認識
|
Academic Significance and Societal Importance of the Research Achievements |
画像認識や画像処理の分野では、大規模データを用いた機械学習による手法が成果を挙げている。しかし、学習に必要な正確にラベル付けされたデータを大量に収集することは現実的には困難な場合が多い。画像の自動生成を目的とした研究は行われているが、機械学習の精度向上に寄与できている保証はない。本研究の成果を活用して機械学習の精度向上に寄与できる画像データを生成することが可能になれば、画像認識技術のさらなる高精度化が期待できる。
|