کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
1711206 | 1519543 | 2014 | 10 صفحه PDF | دانلود رایگان |
• A method to detect dead entomopathogenic nematodes using machine vision was proposed.
• We proposed a novel angle analysis method to detect straighter lines in biological images.
• Dead entomopathogenic nematodes were detected even from clusters.
• Recognition rates were over 85%.
Entomopathogenic nematodes are soil-dwelling living organisms which have been widely used for controlling agricultural insect pests as part of biological control. Because easy to use procedures have been developed for their application using standard sprayers, they are one of the best alternatives to pesticides. In laboratory procedures, counting is the most common, laborious, time-consuming and approximate part of the studies conducted on entomopathogenic nematodes. Here, a novel method was proposed to detect and count dead Heterorhabditis bacteriophora nematodes from microscope images using computer vision. The proposed method consisted of three main algorithm steps: pre-processing to obtain the medial axes of the nematode worms as accurately as possible, separation of overlapped nematode worms with a skeleton analysis; and detection of dead nematodes using two different straighter line detection methods. The proposed method was tested on 68 microscope images which included 935 live worms and 780 dead worms. Proposed method was able to detect the worms in microscope images successfully with recognition rates of over 85%.
Journal: Biosystems Engineering - Volume 118, February 2014, Pages 29–38