林颢,宋奔腾,金鸿娟,管彬彬.基于嗅觉可视化与图像处理的食醋醋龄检测[J].农业机械学报,2017,48(1):275-280.
LIN Hao,SONG Benteng,JIN Hongjuan,GUAN Binbin.Age Discrimination of Vinegar Based on Artificial Olfaction Visualization and Image Processing[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(1):275-280.
摘要点击次数: 2264
全文下载次数: 1428
基于嗅觉可视化与图像处理的食醋醋龄检测   [下载全文]
Age Discrimination of Vinegar Based on Artificial Olfaction Visualization and Image Processing   [Download Pdf][in English]
投稿时间:2016-05-28  
DOI:10.6041/j.issn.1000-1298.2017.01.036
中文关键词:  食醋醋龄  检测  可视化传感器  图像处理
基金项目:江苏省自然科学基金项目(BK2012286)和中国博士后科学基金特别项目(2013T60509)
作者单位
林颢 江苏大学 
宋奔腾 江苏大学 
金鸿娟 江苏大学 
管彬彬 江苏大学 
中文摘要:应用基于色敏传感器阵列的嗅觉可视化系统对不同醋龄的食醋进行鉴别。运用系统的图像处理模块,比较了不同方法对目标图像的中心点定位和特征区域选取的影响。尤其在基于不同颜色空间提取特征值方面,对比了RGB、HSV、Lab颜色空间,结果表明Lab的效果最好。利用3种颜色空间中获得的特征数据并结合主成分分析(PCA)和线性判别分析(LDA)等模式识别方法,鉴别食醋醋龄,Lab颜色空间下的训练集和预测集识别率均大于90%。
LIN Hao  SONG Benteng  JIN Hongjuan  GUAN Binbin
Jiangsu University,Jiangsu University,Jiangsu University and Jiangsu University
Key Words:vinegar age  detection  visualization sensor  image processing
Abstract:An artificial olfaction system based on visualization sensor array was employed to identify different ages of vinegar. In the image processing module of this system, the influence of different methods on the localization of the target image center was compared, including minimum enclosing rectangle, ellipse fitting and one-order moment. Since the target image was similar to the circle, all of the three methods could obtain center coordinates exactly, except that the last method consumed less time. Moreover, the characteristic region was reselected, which could better represent features of the target image. Usually, feature values are extracted based on the RGB color space. Then, each component and coordinate value in RGB, HSV and Lab color spaces were extracted and used as eigenvalues. The result showed that the data obtained from the Lab space had high stability. In order to identify different ages of vinegar, five different years of vinegar samples from 2011 to 2015 were selected in the experiment. The characteristic data from three kinds of color spaces was analyzed with principal component analysis (PCA) and linear discriminant analysis (LDA). Although the samples of vinegar in different years had a certain clustering tendency, especially in the Lab color space, there were still some samples overlapping each other and difficult to separate by PCA alone. Then this data was used as the input of LDA classifier for discriminate analysis. The recognition accuracy rate in the training set and testing set achieved 98% and 94% respectively in Lab color space, while the detection accuracies were not higher than 90% in other color spaces.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器