基于色度域划分的马铃薯绿皮检测方法

绿皮是马铃薯品质缺陷之一。为了检测马铃薯的品质，该文提出了一种基于色度域划分的马铃薯绿皮检测方法，从量化角度实现了马铃薯表皮颜色信息的提取。利用基于统计的逐步判别分析方法和支持向量机识别方法构建模型，因局限于特定样本集的特征空间，识别结果稳定性不好。该研究克服了上述方法的缺点，提取色度作为模式识别的特征，并确定了区分正常和绿皮马铃薯的有效色度值区间57～64，再结合二次阈值判别方法对马铃薯的绿皮进行检测。试验结果表明该方法简单、识别率高，而且稳定性强。

Greened potatoes detection based on hue threshold division

Green rind is one kind of the quality defects of potato. This paper put forward a method based on the hue threshold to detect green rind of potato, and extract the color information from the quantitative perspective. The models of stepwise discriminated analysis based on the statistical and support vector machine have disadvantages of the unsteady results due to the limitations of characteristics space of a particular sample set. To overcome the foregoing methods shortcomings, the new method extracted hue as features, confirmed effective range of hue 57 to 64 which could distinguish normal potatoes and greened ones. With the second threshold discrimination, the results showed that the method had the characteristics of simple, high detection accuracy rate and stable.