摘要
在移动端直接上传获取的病害图像进行远程诊断时,因图片数据量大可导致上传速度缓慢,增大服务端数据处理难度,影响图像识别的及时性和准确性。针对这个问题,以黄瓜病害为例,提出在移动端先将获取的图像进行图像裁剪和阈值分割处理,提取用户感兴趣区域上传远程服务端。系统测试数据发现,病害图像经过裁剪和阈值分割处理后,在获得良好图像质量前提下,大大减少了图像数据容量,能加快图片上传速度,降低远程服务端图片数据处理难度,提高诊断的及时性,具有较高的实用性。
When disease Image upload to remote diagnosis In mobile,the large amount of image data will reduce upload speed and increase the difficulty of data processing on the server,and affect the timeliness and accuracy of image recognition.In order to solve this problem,this paper takes the cucumber disease as an example,proposes to cut and segment the image at the mobile at first,then extract the region of user interest,upload it to the remote server at last.The test data of the system show that after clipping and thresholding the image With good image quality,the image data capacity can be reduced greatly,the upload speed of the image can be accelerated,and the difficulty of image data processing on the remote server can be reduced,improve the timeliness of diagnosis,it has higher degree of practicality.
作者
刘小红
马凌
仇焕青
LIU Xiao-hong(Hunan Institute of Information Technology,Changsha,Hunan 410151)
出处
《农业灾害研究》
2021年第1期71-72,75,共3页
Journal of Agricultural Catastrophology
基金
湖南省教育厅科学研究项目“基于预处理图像压缩方法在农作物病害诊断中的应用研究”,校级科研重点项目(XXY018ZD01)。
