Simultaneously performing connected-component labeling and Euler number computing for real-time image recognition

2016 Fiscal Year Final Research Report

• Project/Area Number: 26330200
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Aichi Prefectural University
• Principal Investigator: HE Lifeng 愛知県立大学, 情報科学部, 教授 (80305515)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: パターン認識 / 画像処理 / ラベル付け / オイラー数計算

Outline of Final Research Achievements

By this research, we have achieved the following research results on connected-component labeling and Euler number computing, which are indispensable for pattern recognition, computer vision and image analysis.
(1) We proposed the fastest connected-component labeling algorithm in the world. (2) We proposed a connected-component labeling algorithm for hexagonal image. (3) We proposed a graph-theory-based Euler number computing algorithm. (4) We proposed a bit-quad-based Euler number computing algorithm. (5) We proposed two algorithms for performing connected-component labeling and Euler number computing simultaneously.
All of these research results have been published on related journals, including <Pattern Recognition>, the top journal in the field of pattern recognition, and <IEEE Transactions on Image Processing>, the top journal in the field of image processing.

Free Research Field

パターン認識