Institute of Zoology, Chinese Academy of Sciences, Beijing, China.
Institute of Automation, Chinese Academy of Sciences, Beijing, China.
Pest Manag Sci. 2017 Jul;73(7):1511-1528. doi: 10.1002/ps.4487. Epub 2016 Dec 30.
Many species of Tephritidae are damaging to fruit, which might negatively impact international fruit trade. Automatic or semi-automatic identification of fruit flies are greatly needed for diagnosing causes of damage and quarantine protocols for economically relevant insects.
A fruit fly image identification system named AFIS1.0 has been developed using 74 species belonging to six genera, which include the majority of pests in the Tephritidae. The system combines automated image identification and manual verification, balancing operability and accuracy. AFIS1.0 integrates image analysis and expert system into a content-based image retrieval framework. In the the automatic identification module, AFIS1.0 gives candidate identification results. Afterwards users can do manual selection based on comparing unidentified images with a subset of images corresponding to the automatic identification result. The system uses Gabor surface features in automated identification and yielded an overall classification success rate of 87% to the species level by Independent Multi-part Image Automatic Identification Test.
The system is useful for users with or without specific expertise on Tephritidae in the task of rapid and effective identification of fruit flies. It makes the application of computer vision technology to fruit fly recognition much closer to production level. © 2016 Society of Chemical Industry.
多种实蝇科物种对水果具有破坏性，这可能会对国际水果贸易产生负面影响。自动或半自动的实蝇识别对于诊断损害原因和制定具有经济意义的昆虫检疫方案非常必要。
我们开发了一种名为 AFIS1.0 的实蝇图像识别系统，该系统使用了 74 个种，隶属于六个属，其中包括实蝇科中的大多数害虫。该系统结合了自动图像识别和手动验证，平衡了可操作性和准确性。AFIS1.0 将图像分析和专家系统集成到基于内容的图像检索框架中。在自动识别模块中，AFIS1.0 提供候选识别结果。然后，用户可以根据将未识别图像与自动识别结果对应的子集进行比较，进行手动选择。该系统在自动识别中使用 Gabor 表面特征，通过独立多部分图像自动识别测试，达到了 87%的整体分类成功率。
该系统对于具有或不具有实蝇科专业知识的用户来说，在快速有效地识别实蝇方面都非常有用。它使计算机视觉技术在实蝇识别中的应用更接近生产水平。 © 2016 化学工业学会。
