鞘翅目害蟲的鑒別工作是由數(shù)量有限的專業(yè)研究人員進(jìn)行，大部分非專業(yè)人員因缺乏相關(guān)知識(shí)和技術(shù)培訓(xùn)，要快速鑒定害蟲種屬具有相當(dāng)?shù)碾y度，不利于害蟲防治。為此提出利用計(jì)算機(jī)視覺技術(shù)對(duì)鞘翅目害蟲進(jìn)行自動(dòng)識(shí)別。用不同的圖像獲取系統(tǒng)分別采集體長不同的鞘翅目害蟲圖像，然后通過數(shù)字圖像分析技術(shù)，提取和計(jì)算害蟲圖像的幾何形狀特征參數(shù)。采用模糊模式識(shí)別算法建立害蟲的模式庫和隸屬函數(shù)，然后根據(jù)模糊集理論的極小極大準(zhǔn)則完成待識(shí)別害蟲的歸類。對(duì)29 種鞘翅目害蟲進(jìn)行識(shí)別，識(shí)別正確率為
86.2%。為鞘翅目害蟲的快速鑒定提供了一個(gè)新的途徑。
關(guān)鍵詞：鞘翅目害蟲; 計(jì)算機(jī)視覺; 特征提取; 自動(dòng)識(shí)別
Abstract: Identification of Beetle Insects has been performed by human experts with rich experience. However, sufficient number of competent human experts are not available to cover the large area. This paper presents a computer vision-based method to identify beetle insects. Two image acquisition systems were designed to capture the images with respect to insects’ length. And median filtering was used to enhance the images for further segmentation. Parameters related to shape features were extracted to represent the image content. Fuzzy classifier was adopted to identify beetle insects. Results showed that the correct recognition rate is 86.2% . It is a feasible way for beetle insect’s rapid identification.
Key words: Beetle Insect; Computer Vision; Feature Measuring; Automated Identification