A study on feature transformation in pattern recognition

2018 Fiscal Year Final Research Report

• Project/Area Number: 15K00261
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Kobayashi Takumi 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (30443188)
• Project Period (FY): 2015-04-01 – 2019-03-31
• Keywords: 特徴抽出 / 特徴変換 / 画像認識 / 動画像認識

Outline of Final Research Achievements

In this study, we have proposed various feature transformation methods to enhance the discriminative power of features. In general, the feature to represent the content of input data contains structural information which is derived from the characteristics of feature extractors and input data distribution. The proposed methods leverage the essential structures to improve the discriminativity of the features. Those methods are formulated especially by focusing on the deblurring of histogram, prior probabilistic models, physical structures and invariance to input data perturbation. We can apply the methods in a computationally efficient manner, while contributing to the improvement of feature representation as well as performance of the whole recognition systems.

Free Research Field

パターン認識

Academic Significance and Societal Importance of the Research Achievements

近年、計測データの大規模化・多様化が進み、それらデータをサービス等へ利活用するためのデータ自動認識技術、いわゆるAIの需要が急速に拡大している。本研究成果は、自動認識の中核を成すパターン認識の性能改善に資するものである。特に、特徴抽出の後処理という位置づけで、様々な既存認識システムに容易かつ計算量的にも低コストで導入できるため波及効果も期待できる。さらにそのような実用面のみでなく、既存特徴量の変換処理に着目し、そこに数理的視点を導入した点でも学術的な意義が大きい。