Computer vision techniques for recognition and retrieval of volumetric biological organs

2014 Fiscal Year Final Research Report

• Project/Area Number: 24500197
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Chiba University
• Principal Investigator: IMIYA Atsushi 千葉大学, 統合情報センター, 教授 (10176505)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 変分原理 / データ蓄積 / 大域的整合計算 / 局所的整合計算 / 学習 / 臓器モデル / 形状解析

Outline of Final Research Achievements

In this research, we introduced a fast and robust method for registration, recognition and retrieval of volumetric biological organs. The method allows us to construct robust and repairable statistical models for organs in human torso. For the construction of models, (1) we develop a segmentation methods for organs in torso, (2) we define the average organ, (3) we clarify the difference among temporal, spatial and sopatio-temporal averages of organs and (4) we construct a robust and reliable image registration method with data in large database dictionary.

Free Research Field

数理画像工学