T
Takumi Kobayashi
Researcher at National Institute of Advanced Industrial Science and Technology
Publications - 65
Citations - 771
Takumi Kobayashi is an academic researcher from National Institute of Advanced Industrial Science and Technology. The author has contributed to research in topics: Feature extraction & Contextual image classification. The author has an hindex of 13, co-authored 64 publications receiving 662 citations.
Papers
More filters
Book ChapterDOI
Image Feature Extraction Using Gradient Local Auto-Correlations
Takumi Kobayashi,Nobuyuki Otsu +1 more
TL;DR: A method for extracting image features which utilizes 2nd order statistics, i.e., spatial and orientational auto-correlations of local gradients, enables us to extract richer information from images and to obtain more discriminative power than standard histogram based methods.
Journal ArticleDOI
Motion recognition using local auto-correlation of space-time gradients
Takumi Kobayashi,Nobuyuki Otsu +1 more
TL;DR: A motion recognition scheme based on a novel method of motion feature extraction that utilizes auto-correlations of space-time gradients of three-dimensional motion shape in a video sequence and applies the framework of bag-of-frame-features for recognizing motions.
Journal ArticleDOI
Three-way auto-correlation approach to motion recognition
Takumi Kobayashi,Nobuyuki Otsu +1 more
TL;DR: The experimental results on large datasets for gesture and gait recognition showed the effectiveness of the CHLAC method, which effectively extracts spatio-temporal local geometric features characterizing the motion, such as gradients and curvatures.
Proceedings ArticleDOI
Acoustic feature extraction by statistics based local binary pattern for environmental sound classification
Takumi Kobayashi,Jiaxing Ye +1 more
TL;DR: The proposed method is motivated from the image processing technique, local binary pattern (LBP), and works on a spectrogram which forms two-dimensional data like an image, and effectively incorporate the local statistics, mean and standard deviation on local pixels, to establish robust LBP.
Journal ArticleDOI
Urban sound event classification based on local and global features aggregation
TL;DR: The proposed machine learning-based scheme for urban sound classification in real-life noise conditions achieves superior performance compared with 3 other latest approaches and can be a fundamental building block of various urban multimedia information processing systems that help to improve quality of life.