相对特征在昆虫目级阶元图像自动鉴定中的应用

应用计算机图像技术并结合昆虫分类学原理,设计和开发了一套"昆虫目级阶元标本图像自动鉴定系统",提出了一组基于昆虫标本图像的相对特征,并通过前馈人工神经网络方法进行鉴定测试.测试结果表明,相对特征应用于昆虫目级阶元图像的自动鉴定是有效的,在对7个常见昆虫目的测试中,系统表现出良好的准确性和稳定性,最高正确识别率可以达到95%.     

昆虫图像自动鉴别技术

昆虫是地球上物种多样性最为丰富的生物类群,其物种鉴定任务复杂而艰巨,可靠的物种鉴定是开展昆虫学工作的重要基础之一。当前,国内外的人工昆虫物种鉴定能力均不能满足实际需求,因而人们开始不断探索利用计算机自动鉴定昆虫的原理和方法。目前,模式识别技术的迅猛发展已为昆虫图像的自动鉴定提供可能。文章概述昆虫图像自动鉴定技术研究的历史与现状,总结主要原理和方法,介绍工作流程,并展望发展前景。     

基于颜色特征的昆虫自动鉴定方法

对昆虫实现自动鉴定是将相关专家从大量重复性的鉴定工作中解脱出来的最有效的方法之一。本章文着重论述昆虫自动鉴定系统鉴定的基本原理,开发步骤和使用昆虫自动鉴定系统进行自动鉴定的步骤,基于颜色特征的昆虫自动鉴定系统开发中在图像获取、颜色特征提取方面的难点和相应的解决方案。最后,经过测试开发出的基于颜色特征的蝴蝶自动鉴定系统在对43种蝴蝶的自动鉴定上取得了95.2%准确率。     

几何形态计量学在昆虫自动鉴定中的应用与展望

几何形态计量学着重研究的是生物形态的拓扑结构信息,不受标本大小和形状变化的影响,是进行昆虫自动鉴定的一个新的手段。本文首先介绍了传统形态计量学和几何形态计量学两种昆虫自动鉴定的方法,并着重介绍了轮廓分析法和标志点分析法等几何形态计量学的分析方法,以及目前开发的几何形态计量学昆虫自动鉴定软件,简述了该方法应用于昆虫自动鉴定的工作流程,最后对几何形态计量学在昆虫自动鉴定方面的未来发展进行了展望。     

检疫性昆虫DNA条形码检测技术的研发与应用实例

【目的】DNA条形码技术是近年来生物分类鉴定的研究热点之一,已成为植物检疫性昆虫鉴定的有力工具。为快速、准确地鉴定口岸截获的昆虫种类,实现"检得出、检得准、检得快"的要求,我们研发了昆虫DNA条形码试剂盒检测技术(Insect DNA barcoding identification kit)。【方法】该检测技术针对出入境植物检疫性及危险性昆虫的主要类群,选择合适的基因片段、设计引物、对目标基因进行扩增测序,找出基因片段上区分每个物种的多态位点规律,作为该物种的鉴定特征并建立数据库,应用于植物检疫性及危险性昆虫的物种鉴定。【结果】以检疫性昆虫木蠹象属Pissodes为例,确定了木蠹象属5种昆虫的多态位点规律(鉴定特征),构建了用于物种鉴定的数据库。通过比对数据库里的鉴定特征,将未知样品鉴定为榛梢木蠹象P.terminalis(相似度100%),与形态鉴定结果一致。本文介绍了检测技术的原理、方法、技术流程及应用实例,并展望了其在有害生物检测中的推广应用前景。【结论】昆虫DNA条形码试剂盒检测技术为建立标准化,准确性高的物种鉴定平台打下基础,有着良好的推广应用前景。     

昆虫远程鉴定方法

介绍了利用数码显微镜用摄像仪、计算机网络传输图像的远程鉴定技术在昆虫鉴定方面尝试 ,认为该远程鉴定技术在昆虫的鉴定或复核方面有开发前景     

昆虫图像分割方法及其应用

昆虫图像自动鉴定是一种快速鉴定昆虫的方法,图像分割则是其中关键步骤。通过搜集和整理国内外近年来针对昆虫图像的分割方法和研究,发现对昆虫图像分割的研究日趋增多。随着计算机图像技术的发展,昆虫图像分割方法吸收了许多图像分割领域中新兴的方法, 诸如采用水平集、边缘流以及结合形状、纹理、色彩等多种要素的智能分割(如JSEG方法)等。虽然大量的图像分割方法被引入到昆虫图像研究中,但是目前分割技术依然是阻碍昆虫图像广泛应用的关键。本文经过总结和分析,发现目前昆虫图像分割研究的往往在各自的测试集上有良好表现, 但是缺乏统一的评价标准, 因此很多方法在昆虫图像中应用难以推广。针对研究中的存在的这些问题,需建立良好的昆虫图像分割评价体系,本文建议通过建立统一的昆虫图像库以及对昆虫图像分割的评价方法深入研究,并且这些工作是当前昆虫图像分割研究亟待完善任务。     

昆虫翅脉特征自动获取技术的初步研究

昆虫翅的形态特征是某些类群昆虫分类中的重要依据,怎样快速科学提取这些数据是昆虫数字鉴定技术中必须解决的重要问题之一。本文介绍了目前国内外这方面的进展,并介绍了DrawWing软件的详细功能。该软件能比较准确方便地提取昆虫翅轮廓和翅脉特征值,因此详细描述了其算法原理。利用该软件的DOS和Windows两种不同版本对意大利蜜蜂和昼鸣蝉的翅进行了其特征提取的实验研究,结果证明该软件可以成功提取蜜蜂翅脉特征值,但对昼鸣蝉翅处理尚存在问题。在此基础上,本文对昆虫翅脉特征自动获取技术乃至昆虫种类的计算机识别方法的进一步发展提出了讨论。     

DNA条形码试剂盒检测技术在大小蠹属种类鉴定中的应用

[目的]DNA条形码技术已成为生物分类鉴定的有力工具.DNA条形码技术的相关问题,如物种种内和种间的遗传距离出现重叠区域,将直接影响到物种鉴定的准确性.我们应用DNA条形码试剂盒检测技术来快速、准确地鉴定口岸截获的检疫性大小蠹属种类.[方法]针对大小蠹昆虫设计引物以提高PCR扩增效率.运用自主研发的基因条码分析软件找出基因片段上区分每个物种的多态位点规律,作为该物种的鉴定特征并建立数据库,应用于物种鉴定.[结果]使用针对大小蠹属昆虫设计的引物成功扩增出325 bp的COI基因片段.将大小蠹属12种昆虫的COI基因片段上的核苷酸诊断位点的组合作为物种的鉴定特征,可以准确地区分近似种.通过比对植物检疫鉴定系统数据库里的鉴定特征,将6个大小蠹属的未知样品成功鉴定到种(核苷酸序列一致性为100％),与形态鉴定结果一致.[结论]结果表明DNA条形码试剂盒检测技术可以准确鉴定大小蠹属的种类.该检测技术可以应用于其他经济重要性有害生物的检测鉴定.     

DNA条形码技术在农林入侵害虫鉴定与溯源研究中的应用

快速准确识别鉴定昆虫的方法在植物检疫中具有重要意义.长期以来,基于形态特征的入侵害虫鉴定研究由于经常遇到诸如幼期(包括卵、幼虫/若虫、蛹/前蛹/拟蛹),隐存种、复合种以及样本受损等情况,致使物种的快速准确鉴定陷入举步维艰的境地.DNA条形码技术的发展为上述问题的解决提供了新契机,已成为昆虫分类鉴定、植物及其产品的产地检疫和调运检疫以及出入境检验检疫中备受关注的一种新兴技术.本文以重大农林害虫类群介壳虫类、蓟马类、粉虱类和实蝇类等为例,简要介绍DNA条形码技术在农林入侵害虫鉴定和溯源研究中的应用,并对DNA条形码技术的进一步完善进行了探讨和展望.     

Machine vision automated species identification scaled towards production levels

Computer‐automated identification of insect species has long been sought to support activities such as environmental monitoring, forensics, pest diagnostics, border security and vector epidemiology, to name just a few. In order to succeed, an automated identification programme capable of addressing the needs of the end user should be able to classify hundreds of taxa, if not thousands, and is expected to distinguish closely related and hence morphologically similar species. However, it remains unknown how automated identification methods might handle an increase in data quantity, be it in reference imagery or taxonomic diversity. We sought to test the scalability of an automated identification method in terms of the number of reference specimens used to train the classifier and the number of taxa into which the classifier should assign unknown specimens. Is there an optimal number of reference images, where the cost of acquiring more images becomes greater than the marginal increase in identification success? Does increasing taxonomic diversity affect identification success, whether negatively or positively? In order to test the scalability of the automated insect identification enterprise, we used a sparse processing technique and support vector machine to test the largest dataset to date: 72 species of fruit flies (Diptera: Tephritidae) and 76 species of mosquitoes (Diptera: Culicidae). We found that: (i) machine vision methods are capable of correctly classifying large numbers of closely related species; (ii) when the misclassification of a specimen occurs at the species level, it is often classified in the correct genus; (iii) classification success increases asymptotically as new training images are added to the dataset; (iv) broad taxon sampling outside a focal group can increase classification success within it.     

Artificial intelligence in pest insect monitoring

Abstract Global problems of hunger and malnutrition induced us to introduce a new tool for semi‐automated pest insect identification and monitoring: an artificial neural network system. Multilayer perceptrons, an artificial intelligence method, seem to be efficient for this purpose. We evaluated 101 European economically important thrips (Thysanoptera) species: extrapolation of the verification test data indicated 95% reliability at least for some taxa analysed. Mainly quantitative morphometric characters, such as head, clavus, wing, ovipositor length and width, formed the input variable computation set in a Trajan neural network simulator. The technique may be combined with digital image analysis.     

Production of a recombinant antibody fragment in whole insect larvae

Infection of insect cells with baculovirus expression constructs is commonly used to produce recombinant proteins that require post-translational modifications for their activity, such as mammalian proteins. However, technical restraints limit the capacity of insect cell-based culture systems to be scaled up to produce the large amounts of recombinant protein required for human pharmaceuticals. In this study, we designed an automated insect rearing system and whole insect baculovirus expression system (PERLXpress™) for the expression and purification of recombinant proteins on a large scale. As a test model, we produced a recombinant mouse anti-botulinum antibody fragment (Fab) in Trichoplusia ni larvae. A recombinant baculovirus co-expressing the Fab heavy and light chains together with N-terminal sequences from the silkworm hormone bombyxin, to direct proteins into the secretory pathway, was constructed. Fifth instar larvae were reared and infected orally with recombinant (pre- occluded) baculovirus using the automated system and harvested approximately after 4 days. The total yield of recombinant Fab was 1.1 g/kg of larvae, resulting in 127 mg of pure Fab in one production run. The Fab was purified to homogeneity using immobilized metal affinity chromatography, gel filtration, and anion exchange chromatography. The identity of the purified protein was verified by Western blots and size-exclusion chromatography. Purified recombinant Fab was used to detect botulinum toxin in ELISA experiments, demonstrating that the heavy and light chains were properly assembled and folded into functional heterodimers. We believe that this is the first demonstration of the expression of a recombinant antibody in whole insect larvae. Our results demonstrate that a baculovirus-whole larvae expression system can be used to express functionally active recombinant Fab fragments. As the PERLXpress™ system is an automated and linearly scalable technology, it represents an attractive alternative to insect cell culture for the production of large amounts of human pharmaceuticals.     

Automatic greenhouse insect pest detection and recognition based on a cascaded deep learning classification method

Inspection of insect sticky paper traps is an essential task for an effective integrated pest management (IPM) programme. However, identification and counting of the insect pests stuck on the traps is a very cumbersome task. Therefore, an efficient approach is needed to alleviate the problem and to provide timely information on insect pests. In this research, an automatic method for the multi-class recognition of small-size greenhouse insect pests on sticky paper trap images acquired by wireless imaging devices is proposed. The developed algorithm features a cascaded approach that uses a convolutional neural network (CNN) object detector and CNN image classifiers, separately. The object detector was trained for detecting objects in an image, and a CNN classifier was applied to further filter out non-insect objects from the detected objects in the first stage. The obtained insect objects were then further classified into flies (Diptera: Drosophilidae), gnats (Diptera: Sciaridae), thrips (Thysanoptera: Thripidae) and whiteflies (Hemiptera: Aleyrodidae), using a multi-class CNN classifier in the second stage. Advantages of this approach include flexibility in adding more classes to the multi-class insect classifier and sample control strategies to improve classification performance. The algorithm was developed and tested for images taken by multiple wireless imaging devices installed in several greenhouses under natural and variable lighting environments. Based on the testing results from long-term experiments in greenhouses, it was found that the algorithm could achieve average F₁-scores of 0.92 and 0.90 and mean counting accuracies of 0.91 and 0.90, as tested on a separate 6-month image data set and on an image data set from a different greenhouse, respectively. The proposed method in this research resolves important problems for the automated recognition of insect pests and provides instantaneous information of insect pest occurrences in greenhouses, which offers vast potential for developing more efficient IPM strategies in agriculture.     

Performance of an analytical, dual infrared-beam, stored-product insect monitoring system

A system is described for automated monitoring of pest insects in stored grain. It provides quantitative data indicative of the species of detected insects and is self-calibrating to maintain reliable operation over time across adverse environmental and biological conditions. The system uses electronic grain probes, each with a dual infrared-beam sensor head providing orthogonal views of falling insects. Sensor analog signals are analyzed by an embedded microprocessor, and extracted waveform parameters are transmitted back to a central computer. Filtering algorithms recognize and eliminate false detections due to extraneous (nonfalling) insect activities and provide an indication of species based on body size. Laboratory test data provide species identification templates and an analysis of Montana field test data acquired in aerated and nonaerated bins demonstrates the effectiveness of the filtering algorithms. The described system technology has been licensed by OPIsystems, Inc., Calgary, Alberta, Canada, and is commercially available as Insector.     

昆虫化学信息物质及其在害虫综合治理上的应用

本文阐述了昆虫化学信息物质的定义和分类,昆虫的化学通讯原理,以及利用化学信息物质在害虫综合治理上的应用。     

温室白粉虱自动计数技术研究初报

应用计算机视觉技术对温室白粉虱自动计数技术进行了研究。采用胶卷照相机和家用摄像机对田间温室白粉虱等生的叶片进行拍摄,以获得其数字图象,对白粉虱图象的分割采用Ｊohannsen基于熵的分割算法,对分割后的二值图象利用区域标记算法得到白粉虱个体的数量。对叶片挨在一起的白粉虱个体采用数学形态学算法进行了分离。用１９个虫叶片样本的统计结果表明,直接利用分割图象进行白粉虱个体计数的累积准确率达９１．９９％,而分离处理的算法则需要改进,因此,这一技术具有进一步在生态研究和ＩＰＭ实践中推广的可能性,这将使田间微小昆虫的种群数量监测和测查的工作量大幅度降低,而铉得到显著提高。