首页> 外国专利> plant disease detection system, computer-implemented method for detecting plant diseases and plant disease detection computer program product

plant disease detection system, computer-implemented method for detecting plant diseases and plant disease detection computer program product

机译:植物病害检测系统,用于检测植物病害的计算机实现的方法以及植物病害检测计算机程序产品

摘要

a computer program system (100), method and product for determining plant diseases. the system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11) of at least one plant element (1). a color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color normalized image. an extractor module (130) is configured to extract one or more image parts (11e) from the color normalized image, wherein the extracted image parts (11e) correspond to at least one plant element (1). a filter module (140) configured: to identify one or more groupings (c1 to cn) by one or more visual characteristics within the extracted image parts (11e), wherein each grouping is associated with a plant element part showing characteristics of a plant disease; and to filter one or more candidate regions from one or more identified groupings (c1 to cn) according to a predefined threshold, using a bayes classifier that models visual trait statistics that are always present in a diseased plant image. a plant disease diagnostic module (150) configured to extract, using a statistical inference method, from each candidate region (c4, c5, c6, cn) one or more visual characteristics to determine for each candidate region one or more more probabilities indicating a particular disease; and to calculate a confidence score (cs1) for the particular disease by assessing all probabilities determined from the candidate regions (c4, c5, c6, cn).
机译:用于确定植物病害的计算机程序系统(100),方法和产品。该系统包括被配置为接收植物的图像(10)的接口模块(110),该图像(10)包括至少一个植物元素(1)的视觉表示(11)。颜色归一化模块(120)被配置为对接收到的图像(10)应用颜色恒定性方法以生成颜色归一化图像。提取器模块(130)被配置为从颜色归一化图像中提取一个或多个图像部分(11e),其中提取的图像部分(11e)对应于至少一个植物元素(1)。过滤器模块(140),其被配置为:通过所提取的图像部分(11e)内的一个或多个视觉特征来识别一个或多个分组(c1至cn),其中每个分组与示出植物病害特征的植物元素部分相关联。 ;并使用贝叶斯分类器根据预定义的阈值从一个或多个已识别的组(C1到cn)中过滤一个或多个候选区域,该贝叶斯分类器对始终存在于患病植物图像中的视觉特征统计数据进行建模。植物病害诊断模块(150),其配置为使用统计推断方法从每个候选区域(c4,c5,c6,cn)中提取一个或多个视觉特征,以便为每个候选区域确定一个或多个指示特定概率的概率。疾病;并通过评估从候选区域(c4,c5,c6,cn)确定的所有概率来计算特定疾病的置信度得分(cs1)。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号