2023 Fiscal Year Final Research Report
Development of a Data Retrieval Method with Wide Availability Based on Images by Data Embedding and Image Identification
| Project/Area Number |
20K04476
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 21020:Communication and network engineering-related
|
|---|
| Research Institution | Kansai University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
吉田 壮 関西大学, システム理工学部, 准教授 (70780584)
|
|---|
| Project Period (FY) |
2020-04-01 – 2024-03-31
|
| Keywords | 曲面 / データ埋め込み / 深層学習 / GAN / 携帯端末 / ARマーカ / Pix2PixHD / 画像特徴量 |
|---|
| Outline of Final Research Achievements |
In this study, we focused on two main objectives to make data embedding into images usable in various situations. The first is data acquisition from an image attached to a curved surface. By adding a marker surrounding the embedded image to correct the image from a curved surface to a flat surface, it is possible to acquire data whose image quality and detection rate are almost the same as those of a flat surface. The second is the development of a real-world environment simulator that uses a neural network to simulate the degradation caused by printing and capturing and adds lens distortion and geometrical distortion to it. This simulator can reproduce almost the same degree of degradation as that obtained from the real environment and can be used to verify the method in various situations.
|
| Free Research Field |
画像処理工学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究の研究成果の意義は，実空間上の印刷画像に埋め込んだデータを仮想空間上の情報に連携させることで，仮想現実やトレーサビリティに応用可能な柔軟性と自由度をもった手法を提供できる点にある．ここでは，特に曲面に貼付ないしは投影された画像に対して，データを取得可能な手法を提案することによって，曲面を有する様々な物体に利用可能となる．また，印刷・撮影という処理における劣化を再現するために開発したシミュレータは，提案技術の検証だけではなく，印刷というプロセスを含む様々なアルゴリズムの評価に応用可能となり，これらに共通する非常に手間のかかる検証プロセスを簡略化できるという意味で大きな意義を持っている．
|
