基于感兴趣区域图像分割的红茶茶毫品质数字化评价研究

打开文本图片集

中图分类号：S571.1；S126文献标识码：A

文章编号：1000-369X（2025）04-0655-16

Digital Evaluation of Black Tea Hairs Quality Based on Region of Interest Image Segmentation

TONG Chen1， LIANG Xiuhua²，WANG Zhouli1， FAN Dongmei1，LIN Zhaoshui 3 WU Xiaomei4， QUE Yangzhan4， JIN Minli1，5*，LIN Jie1*

1.CollgeofTea SienceandTa Culture，ZhejiangA&FUniversity，Lin'an31130o，China;2.ShaoxingEconomicCropTechology ExtensionCenter，Shaoxing320o，China;3.ZhejiangLong'eVolcanoTeaCo.，Ltd.Taizhou376o，China;4.LishuiTchician CollegeofAgricultureandForestry，Lishui3234oo，China;5.CollegeofLandseapeArchitecture，ZhejiangA&FUniversity

Lin'an，China

Abstract：Tea hairsare an important indicator for evaluating the appearance qualityof black tea.Curently，the evaluation mainly relies on the sensory assessment of professionals， which is highly subjectiveand abstract，lacking objective and digital quality evaluation methods.To construct a digital evaluation method for the quality of tea hairs， this study collcted images of Qimen black tea samples with three different tea hairs quality grades.The HSVcolor image segmentation technique was used to extract the HSV color space component features of the region of interest （ROI），and a segmentation index （SI） wasconstructed toretrieve the optimal segmentation thresholds forteahairs， tea body，and shadows.The image segmentation efect was qualitativelyand quantitatively evaluated using the masking method and pixel point discrimination，and a quantification method for the proportion of tea hairs was established.The results show that the average segmentation acuracy of tea hairs，tea body，and shadow areas reached 98.70% .Furthermore， through the quantification of the proportion of tea hairs， the recommended hairs proportion thresholds for the three tea hairs quality grades of Qimen black tea（"Prominent golden hairs”， “"Observable hairs”，，and “Less hairs"） were obtained.The linear regression analysis of diferent hairs gradient blended tea samples （ R2=0.958 ， P<0.01 ） and the generalization application effects on‘Dianhong’and‘Jinjunmei' indicate that the digital evaluation method of tea hairs quality constructed in this study has good adaptability in different hairs quantity intervals and different black tea categories.

Keywords： black tea， region of interest （ROI），tea hairs， HSV color space， image segmentation， thresholds

茶叶是世界三大饮料之一，具有独特的风味品质和营养健康功能。（剩余21506字）