R
Ryuei Nishii
Researcher at Kyushu University
Publications - Â 90
Citations - Â 1065
Ryuei Nishii is an academic researcher from Kyushu University. The author has contributed to research in topics: Contextual image classification & AdaBoost. The author has an hindex of 16, co-authored 90 publications receiving 924 citations. Previous affiliations of Ryuei Nishii include Shimane University & University of Pittsburgh.
Papers
More filters
Journal ArticleDOI
Maximum likelihood principle and model selection when the true model is unspecified
TL;DR: In this paper, the authors examined the asymptotic properties of the maximum likelihood estimate and the model selection problem for independent observations coming from an unknown unknown distribution, and applied these results to model selection problems.
Journal ArticleDOI
Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective
Keiichi Mochida,Satoru Koda,Komaki Inoue,Takashi Hirayama,Shojiro Tanaka,Ryuei Nishii,Farid Melgani +6 more
TL;DR: Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.
Journal ArticleDOI
Enhancement of low spatial resolution image based on high resolution-bands
TL;DR: In this paper, a statistical approach to enhance the resolution of low spatial resolution image by using remaining bands was proposed, which employed a multivariate normal distribution for the seven band values.
Journal ArticleDOI
Accuracy and inaccuracy assessments in land-cover classification
Ryuei Nishii,S. Tanaka +1 more
TL;DR: Several measures assessing accuracy of land-cover classification are available, e.g., overall and class-averaged accuracies and an alternative coefficient based on Kullback-Leibler information is proposed.
Journal ArticleDOI
Hyperspectral Image Classification by Bootstrap AdaBoost With Random Decision Stumps
Shuji Kawaguchi,Ryuei Nishii +1 more
TL;DR: In numerical experiments with multispectral and hyperspectral data, the proposed method performed extremely well and showed itself to be superior to support vector machines, artificial neural networks, and other well-known classification methods.