【正文】 系統(tǒng)的設(shè)計與實現(xiàn) ...................................................................................................... 7 系統(tǒng)總體結(jié)構(gòu) ................................................................................................................. 7 硬件系統(tǒng)的設(shè)計與實現(xiàn) ................................................................................................. 7 硬件系統(tǒng)設(shè)計 .......................................................................................................... 8 系統(tǒng)關(guān)鍵設(shè)備選型 .................................................................................................. 8 硬件系統(tǒng)的實現(xiàn) .................................................................................................... 10 軟件系統(tǒng)的設(shè)計與實現(xiàn) ............................................................................................... 12 軟件系統(tǒng)基本框架 ................................................................................................ 12 圖像的采集與顯示模塊 ........................................................................................ 13 系統(tǒng)通訊模塊 ........................................................................................................ 15 輔助功能模塊 ........................................................................................................ 17 本章小結(jié) ....................................................................................................................... 18 第三章 注塑制品圖像處理 .................................................................................................... 19 注塑制品圖像處理總述 ............................................................................................... 19 注塑制品圖像背景分割 ............................................................................................... 19 傳統(tǒng)背景分割方法 ................................................................................................ 20 傳統(tǒng)方法在注塑制品背景分割中的應(yīng)用分析 .................................................... 21 注塑制品背景分割方法設(shè)計 ................................................................................ 23 注塑制品圖像濾波 ....................................................................................................... 24 傳統(tǒng)濾波方法 ........................................................................................................ 25 東北大學(xué)本科畢業(yè)設(shè)計（論文） 目錄 － V－ 傳統(tǒng)濾波方法應(yīng)用效果分析 ................................................................................ 27 注塑制品圖像濾波方法設(shè)計 ................................................................................ 27 本章小結(jié) ....................................................................................................................... 29 第四章 結(jié)束語 ........................................................................................................................ 31 參考文獻(xiàn) .................................................................................................................................. 33 致謝 .......................................................................................................................................... 35 東北大學(xué)本科畢業(yè)設(shè)計（論文） 第一章 緒 論 － 1－ 第一章 緒論 機(jī)器視覺檢測技術(shù)概述 機(jī)器視覺是研究用相機(jī)和計算機(jī)來模仿人的眼睛和大腦完成對目標(biāo)的識別、跟蹤和測量等任務(wù)的科學(xué) [1]。 Image Processing。 關(guān)鍵詞 ： 機(jī)器視覺 ； 注塑制品 ； 圖像處理 ； 特征提取 ； 多分類支持向量機(jī) 東北大學(xué)本科畢業(yè)設(shè)計（論文） Abstract － III－ Research on Injection Product Defects Detection System Based on Machine Vision Abstract The technique of product inspection based on machine vision has been propelled by the development of puter science and machine vision in most recent years, and it seizes more and more researchers’ attention. By snatching the images of the produce and paring them with standard one, machine vision based inspection can give a realtime evaluation on the quality of the product without contiguity. For these merits, this study focuses on the defects detection of injection molding machine (IMM) product based on machine vision. This research is sponsored by NEU key laboratory of process industry automation fund. Firstly, by researching the process of injection production and analyzing relative literatures, this thesis finishes the hardware and software design of defects detection system and solves the problems in capturing and processing images. The background and noise in the captured image makes the defect detection much harder. A method bining threshold and image subtraction is proposed to segment the background from the object image entirely. To filtering the noise and enhance the robustness of the segmentation method, a new filter algorithm is presented which provides a better result than the traditional methods. The research on defect detection feature extraction consists of two parts. For detecting shape defects, a rapidinspecting method is proposed under the condition that the defect’s information is reserved entirely. For detecting texture defects, by regroup the texture feature vectors, a new method is presented to enhance the efficiency of classification. At last, a multiclass classification support vector is designed for the multiclass defects detection. The basic structure of IMM products defect detection system based on machine vision is pleted by using methods proposed above. The test results show that this system demonstrate a high detecting precision. Keywords： Machine Vision。 最后，本文根據(jù)注塑產(chǎn)品多缺陷種類并存的特點(diǎn)設(shè)計了基于多分類支持向量機(jī)的特征分類方法。 在完成圖像處理之后，本文針對注塑制品常見形狀以及紋理缺陷的特征提取進(jìn)行了研究。 針對所獲取的圖像存在背景、噪聲等干擾信息，不適于直接進(jìn)行缺陷檢測的問題，本文研究了相關(guān)的圖像處理算法?；诖?，本文依托東北大學(xué)流程工業(yè)綜合自動化重點(diǎn)實驗室基金項目，針對機(jī)器視覺技術(shù)在注塑制品缺 陷檢測中的應(yīng)用展開研究。 基于機(jī)器視覺的注塑制品缺陷檢測系統(tǒng)研 究 作 者 姓 名： 指 導(dǎo) 教 師： 單 位 名 稱： 信息科學(xué)與工程學(xué)院 專 業(yè) 名 稱： 自動化 東 北 大 學(xué) 2021 年 6 月 Research on Injection Product Defects Detection System Based on Machine Vision by Supervisor: Professor Northeastern University June 20