苹果内部品质的光谱图像检测技术研究
he Study of Non-destructive Measurement Apple Internal Qualities using Spectral Imaging
应用光谱图像技术进行了苹果内部品质无损检测技术的研究。通过采集不同波长（分别为632nm、650nm、670nm、780nm、850nm和900nm）的光谱图像，对所采集的光谱图像灰度分布进行洛伦茨分布（LD）、高斯分布（GD）、指数分布（ED）函数的拟合，通过比较发现洛伦茨分布为最优灰度分布拟合函数。将苹果的糖度和硬度与洛伦茨分布函数拟合所得参数分别进行多元线性回归，建立最佳单波长、最佳双波长组合、最佳三波长组合和最佳四波长组合的校正方程，相关系数分别是最佳单波长R为0.622（糖度）、0.706（硬度）；最佳双波长R为0.776（糖度）、0.837（硬度）；最佳三波长R为0.831（糖度）、0.869（硬度）；最佳四波长R为0.813（糖度）、0.880（硬度）。试验表明：利用光谱图像技术无损检测苹果糖度、硬度等内部品质是可行性的，为计算机图像对水果进行内部品质的无损检测提供技术依据。
he internal qualities of apple were detected using spectral imaging in this paper. The spectral imaging in wavelength of 632nm、650nm、670nm、780nm、850nm and 900nm were captured. The Lorentzian distribution (LD), Gaussian distribution (GD) and Exponential distribution (ED) with three parameters were used to fit scattering profiles for all wavelengths. LD was found to be the best function for fitting gray distribution of imaging. The multi-linear regression model relating Lorentzian parameters to fruit firmness and sugar content were development using best single wavelength, double wavelengths, three wavelengths and four wavelengths. The best model with four wavelengths was able to predict apple sugar content with r=0.831 and predict apple firmness with r=0.880. Results show that the multispectral scattering imaging is nondestructive, fast and easy to implement, and it can provide a nondestructive means for measuring fruit internal quality.
程仁发、刘木华、胡淑芬、林怀蔚、周小梅
农业科学技术发展生物科学研究方法、生物科学研究技术园艺
苹果 光谱图像 糖度 硬度 多元线性回归
pple Spectral imaging sugar content firmness Multi-linear regression
程仁发,刘木华,胡淑芬,林怀蔚,周小梅.苹果内部品质的光谱图像检测技术研究[EB/OL].(2006-12-19)[2025-08-02].http://www.paper.edu.cn/releasepaper/content/200612-293.点此复制
评论