CAJ | 학술논문

粮粒孔洞的自动检测是近红外高光谱图像技术检测粮粒内部害虫中的一个关键问题。提出基于差分图像边界距离的粮粒孔洞自动检测方法，该方法通过求取粮粒（内部）轮廓与阈值分割后二值图像的差分，若差分图像中的目标与粮粒边界的最远距离大于某个阈值时，则该目标应判别为边界（内部）孔洞。用米象的幼虫、蛹和成虫3个侵染阶段粮粒的900帧近红外图像进行训练，用450帧近红外图像进行检验，结果表明该方法不仅可以判断粮粒是否存在孔洞，还能检测出孔洞的数量及形态，其中边界孔洞和内部孔洞的识别率分别为97.33％和95.56％，证实了基于差分图像边界距离的粮粒孔洞检测方法是可行的。
량립공동적자동검측시근홍외고광보도상기술검측량립내부해충중적일개관건문제。제출기우차분도상변계거리적량립공동자동검측방법，해방법통과구취량립（내부）륜곽여역치분할후이치도상적차분，약차분도상중적목표여량립변계적최원거리대우모개역치시，칙해목표응판별위변계（내부）공동。용미상적유충、용화성충3개침염계단량립적900정근홍외도상진행훈련，용450정근홍외도상진행검험，결과표명해방법불부가이판단량립시부존재공동，환능검측출공동적수량급형태，기중변계공동화내부공동적식별솔분별위97.33％화95.56％，증실료기우차분도상변계거리적량립공동검측방법시가행적。
The automatic detection of wheat kernel holes is one of the key elements to detect insects in wheat kernels based on near -infrared hyperspectral imaging technology.A method of automatically wheat kernel holes de-tection was proposed based on boundary distance of differential image in the paper.The differential images were ac-quired between the kernel (internal)contours images and the binary images after thresholding.On condition that the maximum distance between the object and the kernel boundary was more than a threshold in differential images,the object was acted as a boundary or internal hole.The near infrared -images were acquired from the infested wheat kernels with the larva,pupa and adult stages of sitophilus oryzae (L.)The method was trained by 900 images and tested by 450 images.The results showed that the method had a ability to judge whether there were holes in wheat kernel or not.Meanwhile,the number of holes and morphology could be detected.The correct identification ratios of boundary holes and internal holes were over 97.33% and 95.56% respectively.The experiment showed that the method was practical and feasible.