We developed a scheme based on wood surface novel wood recognition spectral features that aimed to solve three problems. First was elimination of noise in some bands of wood spectral reflection curves. Second was imp...We developed a scheme based on wood surface novel wood recognition spectral features that aimed to solve three problems. First was elimination of noise in some bands of wood spectral reflection curves. Second was improvement of wood feature selection based on analysis of wood spectral data. The wood spectral band is 350-2500 nm, a 2150D vector with a spectral sampling interval of 1 nm. We developed a feature selection proce- dure and a filtering procedure by solving the eigenvalues of the dispersion matrix. Third, we optimized the design for the indoor radian＇s mounting height. We used a genetic algorithm to solve the optimal radian＇s height so that the spectral reflection curves had the best classification infor- mation for wood species. Experiments on fivecommon wood species in northeast China showed overall recogni- tion accuracy 〉95 % at optimal recognition velocity.展开更多
基金financially supported by the Fund of Forestry 948 Project (No. 2011-4-04)the Fundamental Research Funds for the Central Universities (No. 2572014EB05-01)
文摘We developed a scheme based on wood surface novel wood recognition spectral features that aimed to solve three problems. First was elimination of noise in some bands of wood spectral reflection curves. Second was improvement of wood feature selection based on analysis of wood spectral data. The wood spectral band is 350-2500 nm, a 2150D vector with a spectral sampling interval of 1 nm. We developed a feature selection proce- dure and a filtering procedure by solving the eigenvalues of the dispersion matrix. Third, we optimized the design for the indoor radian＇s mounting height. We used a genetic algorithm to solve the optimal radian＇s height so that the spectral reflection curves had the best classification infor- mation for wood species. Experiments on fivecommon wood species in northeast China showed overall recogni- tion accuracy 〉95 % at optimal recognition velocity.
