检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:马文杰[1] 唐俊[1] 邓立苗[2] 陈辉[1] 栾涛[1] 孟祥霞[3]
机构地区:[1]青岛农业大学动漫与传媒学院,山东青岛266109 [2]青岛农业大学理学与信息学院,山东青岛266109 [3]青岛农业大学资源与环境学院,山东青岛266109
出 处:《农机化研究》2014年第6期167-172,共6页Journal of Agricultural Mechanization Research
基 金:青岛市公共领域科技支撑计划项目(10-3-3-17-nsh)
摘 要:利用不同品种糯玉米各生长时期叶片的反射与透射数字图像特征,以叶片数字特征研究不同糯玉米品种的识别方法,以及不同类特征或特征类组合的识别稳定性。连续2年采集不同生长时期各糯玉米品种的叶片,提取叶片反射与透射图像特征各48个(其中,形态类特征11个、颜色类特征24个、纹理类特征13个),利用自建的BP神经网络模型对两种图像模式下的单特征和特征组合进行识别。结果表明,反射图像和透射图像的单特征和特征组合的平均识别率均达到了90%以上;基于反射图像,单特征中的纹理特征和颜色特征以及组合特征中的颜色+纹理特征组合均具有较高的识别稳定性;基于透射图像,单特征中的纹理特征以及形态+颜色、形态+纹理特征组合均具有相对较高的识别稳定性。利用各生长时期的叶片实现对糯玉米的品种识别具有一定的可行性;同时引入透射图像特征也为其它农作物的品种识别提供了一种新的借鉴方法。Based on characteristics of reflection and transmission images of different varieties of waxy maize leaf in different growth periods,identification methods of different waxy maize were studied.Stability of features or feature combinations used for the identification was examined.In this paper,48 features were extracted from reflection and transmission images of two consecutive years in different growth stages of the waxy maize leaves,which include 11 morphological characteristics,24 color features and 13 texture characteristics.Waxy maize was identified based on extracted features or feature combinations using BP neural network model.The results show that the average recognition rate reached 90% based on the single feature or feature combinations of the reflection image and the transmission image.It's found that both enjoy high stability of identification as for a single feature of texture and color characteristics,and the combined features of both color combination and texture of the reflection image.The results also indicate that a single feature of the texture characteristics and shape + color,shape + texture combinations of transmission images all achieve relatively high stability of identification.This study demonstrated that it's feasible to identify the waxy maize species by the characteristics of leaves of different growth periods.The introduction of features of transmission images provides a new method for the other crop species identification.
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222