1.1影像測(cè)量?jī)x機(jī)器視覺(jué)檢測(cè)

1.1.1機(jī)器視覺(jué)

機(jī)器視覺(jué)是研究用相機(jī)和計(jì)算機(jī)來(lái)模仿人的眼睛和大腦完成對(duì)目標(biāo)的識(shí)別、跟蹤和測(cè)量等任務(wù)的科學(xué)【11。由于機(jī)器視覺(jué)涉及到多個(gè)學(xué)科，給出一個(gè)精確的定義是很困難的。美國(guó)制造工程師協(xié)會(huì)(SME)機(jī)器視覺(jué)分會(huì)和美國(guó)機(jī)器人工業(yè)協(xié)會(huì)(RIA)自動(dòng)化視覺(jué)分會(huì)關(guān)于機(jī)器視覺(jué)的定義是:“機(jī)器視覺(jué)是使用光學(xué)器件進(jìn)行非接觸感知，自動(dòng)獲取和解釋一個(gè)真實(shí)場(chǎng)景的圖像，以獲取信息或控制機(jī)器或過(guò)程?！?/p>

人們從20世紀(jì)50年代開(kāi)始研究二維圖像的統(tǒng)計(jì)模式識(shí)別，60年代Roberts開(kāi)始進(jìn)行三維機(jī)器視覺(jué)的研究，70年代中期，Mrr人工智能實(shí)驗(yàn)室正式開(kāi)設(shè)《機(jī)器視覺(jué)》課程，80年代初期開(kāi)始了全球性的研究熱潮，機(jī)器視覺(jué)獲得了蓬勃發(fā)展，新概念、新理論不斷涌現(xiàn)。伴隨著計(jì)算機(jī)技術(shù)的不斷提高和圖像處理與傳輸技術(shù)的日益成熟，機(jī)器視覺(jué)在生產(chǎn)實(shí)踐中的應(yīng)用也加快了步伐?，F(xiàn)在機(jī)器視覺(jué)已經(jīng)廣泛地用于工業(yè)、農(nóng)業(yè)、軍事、航空、醫(yī)學(xué)等領(lǐng)域中。同時(shí)，機(jī)器視覺(jué)在理論研究上也取得了很大的發(fā)展，現(xiàn)在機(jī)器視覺(jué)涉及了多們學(xué)科，包括:光學(xué)、機(jī)械、圖像處理、計(jì)算機(jī)圖形學(xué)、模式識(shí)別、人工智能、人工神經(jīng)網(wǎng)絡(luò)等。

1.1.2機(jī)器視覺(jué)檢測(cè)技術(shù)

隨著制造業(yè)的不斷發(fā)展，先進(jìn)制造技術(shù)的研究和應(yīng)用越來(lái)越廣泛。先進(jìn)制造技術(shù)以及自動(dòng)化制造系統(tǒng)和先進(jìn)生產(chǎn)模式的推廣應(yīng)用都要求先進(jìn)的檢測(cè)手段與之相適應(yīng)。將機(jī)器視覺(jué)應(yīng)用到制造業(yè)的檢測(cè)領(lǐng)域中，用機(jī)器視覺(jué)系統(tǒng)確定產(chǎn)品相對(duì)于一組標(biāo)準(zhǔn)要求的偏差的過(guò)程通常稱(chēng)為機(jī)器視覺(jué)檢測(cè)2。它特指機(jī)器視覺(jué)在工業(yè)檢測(cè)方面的應(yīng)用，是機(jī)器視覺(jué)應(yīng)用和研究領(lǐng)域中的一個(gè)重要分支。視覺(jué)檢測(cè)就是檢測(cè)被測(cè)目標(biāo)時(shí)，把圖像當(dāng)作檢測(cè)和傳遞信息的手段或載體加以利用的檢測(cè)方法，其目的是從圖像中提取有用的信號(hào)，它是以現(xiàn)代光學(xué)為基礎(chǔ)，融合電子學(xué)、計(jì)算機(jī)圖像學(xué)、信息處理、計(jì)算機(jī)視覺(jué)等科學(xué)技術(shù)為一體的現(xiàn)代檢測(cè)技術(shù)。由于機(jī)器視覺(jué)系統(tǒng)可以快速獲取大量信息，而且易于與設(shè)計(jì)信息及加工控制信息集成，基于視覺(jué)檢測(cè)技術(shù)的儀器設(shè)備能夠?qū)崿F(xiàn)智能化、數(shù)字化、小型化、網(wǎng)絡(luò)化和多功能化，具備在線(xiàn)檢測(cè)、實(shí)時(shí)分析、實(shí)時(shí)控制的能力，在

軍事、工業(yè)、商業(yè)、醫(yī)學(xué)等領(lǐng)域得到廣泛關(guān)注和應(yīng)用【3】【4】。機(jī)器視覺(jué)檢測(cè)通常涉及指定零件的特征如配件完整性、表面完好性和幾何尺寸的測(cè)量等。機(jī)器視覺(jué)檢測(cè)的工作過(guò)程大致為:首先，使用相機(jī)將被攝取目標(biāo)轉(zhuǎn)換成圖像信號(hào)，傳送給專(zhuān)用的圖像處理系統(tǒng)，圖像系統(tǒng)對(duì)這些圖像中包含的信息進(jìn)行處理和計(jì)算;然后計(jì)算機(jī)根據(jù)處理的結(jié)果做出判斷或決策;最后將控制信號(hào)傳送給執(zhí)行機(jī)構(gòu)。機(jī)器視覺(jué)的特點(diǎn)是自動(dòng)化、客觀(guān)、非接觸和高精度，與一般意義上的圖像處理系統(tǒng)相比，機(jī)器視覺(jué)強(qiáng)調(diào)的是精度和速度以及工業(yè)現(xiàn)場(chǎng)環(huán)境下的可靠性。機(jī)器視覺(jué)檢測(cè)與傳統(tǒng)的人工檢測(cè)相比效率更高，檢測(cè)結(jié)果更加準(zhǔn)確可靠。由于機(jī)器視覺(jué)檢測(cè)不會(huì)受到操作者的疲勞度、責(zé)任心和經(jīng)驗(yàn)等因素的影響，在一些不適合人工作業(yè)的危險(xiǎn)場(chǎng)合，工視覺(jué)難以滿(mǎn)足要求的場(chǎng)合和帶有高度重復(fù)性、智能性并且靠人的眼睛無(wú)法連續(xù)穩(wěn)定地進(jìn)行產(chǎn)品檢測(cè)的場(chǎng)合，機(jī)器視覺(jué)可以發(fā)揮它自身的優(yōu)勢(shì)來(lái)高效、高質(zhì)量的完成檢測(cè)任務(wù)。

1.2虛擬儀器

虛擬儀器(virtual Instrument)是日益發(fā)展的計(jì)算機(jī)硬、軟件和總線(xiàn)技術(shù)在向其它相關(guān)技術(shù)領(lǐng)域密集滲透的過(guò)程中，與測(cè)試技術(shù)、儀器儀表技術(shù)密切結(jié)合共同孕育出的一項(xiàng)全新的成果【5】。虛擬儀器利用IO接口設(shè)備完成信號(hào)的采集與處理，利用計(jì)算機(jī)的顯示功能來(lái)模擬傳統(tǒng)儀器的控制面板，以多種形式輸出檢測(cè)結(jié)果，利用計(jì)算機(jī)強(qiáng)大的軟件功能實(shí)現(xiàn)信號(hào)數(shù)據(jù)的運(yùn)算、分析和處理，從而完成各種測(cè)試功能的一種計(jì)算機(jī)儀器系統(tǒng)。虛擬儀器是現(xiàn)代計(jì)算機(jī)技術(shù)和儀器技術(shù)深層次結(jié)合的產(chǎn)物，也是當(dāng)今計(jì)算機(jī)輔助測(cè)試(CAT)領(lǐng)域的一項(xiàng)重要技術(shù)。虛擬儀器可利用計(jì)算機(jī)強(qiáng)大的圖形環(huán)境和在線(xiàn)幫助功能，構(gòu)成既有普通儀器的基本功能又有一般儀器所沒(méi)有的特殊功能的高檔、廉價(jià)的新型儀器。它可建立中英文界面的虛擬儀器面板，完成對(duì)儀器的控制、數(shù)據(jù)分析和顯示，它改變了傳統(tǒng)儀器的使用方式，使儀器的功能和使用效率明顯提高，大幅度降低了儀器的價(jià)格，使用戶(hù)可以根據(jù)自己需要定義儀器的新功能。在虛擬儀器系統(tǒng)中，硬件僅僅是為了解決信號(hào)的輸入輸出，軟件才是整個(gè)儀器的關(guān)鍵，基于軟件體系的結(jié)構(gòu)可以大大節(jié)省開(kāi)發(fā)和維護(hù)的費(fèi)用。虛擬儀器的品種多、功能強(qiáng)、自動(dòng)化程度高、具有良好的人機(jī)界面，它與傳統(tǒng)儀器的功能是相同的:采集數(shù)據(jù)，對(duì)數(shù)據(jù)分析處理，以及數(shù)據(jù)的結(jié)果處理。它們之間重要區(qū)別之一是靈活性方面。虛擬儀器可由用戶(hù)自己定義，這意味著用戶(hù)可以自由地組合計(jì)算機(jī)平臺(tái)、硬件、軟件以及各種完成應(yīng)用系統(tǒng)所需要的附件。而這種靈活性在由供應(yīng)商定義、功能固定的傳統(tǒng)儀器中是做不到的。因此，虛擬儀器是儀器發(fā)展史上的一場(chǎng)革命，代表著儀器發(fā)展的最新方向和潮流，并且是信息技術(shù)的一個(gè)重要領(lǐng)域，對(duì)科學(xué)技術(shù)的發(fā)展和工業(yè)生產(chǎn)將產(chǎn)生巨大的作用，將成為儀器發(fā)展的方向和趨勢(shì)。1.3機(jī)器視覺(jué)檢測(cè)的發(fā)展現(xiàn)狀在國(guó)外機(jī)器視覺(jué)檢測(cè)從上世紀(jì)八十年代初開(kāi)始已經(jīng)得到了廣泛的研究，國(guó)內(nèi)的機(jī)器視覺(jué)檢測(cè)研究從上世紀(jì)九十年代才逐步開(kāi)始。當(dāng)前，隨著機(jī)器視覺(jué)檢測(cè)系統(tǒng)應(yīng)用的增加，對(duì)機(jī)器視覺(jué)的研究也越來(lái)越多。根據(jù)機(jī)器視覺(jué)的應(yīng)用領(lǐng)域不同，對(duì)機(jī)器視覺(jué)檢測(cè)的研究可以分為不同的種類(lèi)，不同的學(xué)者對(duì)分類(lèi)也有不同的見(jiàn)解。文獻(xiàn)【4】將工業(yè)中應(yīng)用的機(jī)器視覺(jué)質(zhì)量控制系統(tǒng)分為四個(gè)類(lèi)別:尺寸質(zhì)量、表面質(zhì)量、裝配結(jié)構(gòu)和操作質(zhì)量。文獻(xiàn)61機(jī)器視覺(jué)的應(yīng)用領(lǐng)域分為四類(lèi):產(chǎn)品檢查、機(jī)器人、產(chǎn)品分類(lèi)和其他應(yīng)用。尺寸測(cè)量是機(jī)器視覺(jué)研究和應(yīng)用的重要應(yīng)用領(lǐng)域，也是一個(gè)比較早開(kāi)始的研究的方向。機(jī)器視覺(jué)應(yīng)用于尺寸測(cè)量工程中時(shí)，從機(jī)器視覺(jué)系統(tǒng)的硬件(光源、圖像傳感器等)的選用到軟件算法的設(shè)計(jì)中的每一個(gè)環(huán)節(jié)都對(duì)最終的性能產(chǎn)生影響。需要根據(jù)工程的自身特點(diǎn)選擇合適的硬件。文獻(xiàn)【7】研究電盤(pán)尺寸的檢測(cè)，采用兩個(gè)756X581象素的CCD傳感器分別采集電盤(pán)兩個(gè)側(cè)面的圖像，通過(guò)輪廓跟蹤、直線(xiàn)分割、和亞象素定位獲得工件的尺寸。系統(tǒng)精度達(dá)到正負(fù)0．3毫米，每個(gè)工件檢測(cè)花費(fèi)的時(shí)間約0．3秒。

文獻(xiàn)【8】研究了基于計(jì)算機(jī)視覺(jué)的活塞環(huán)閉151間隙測(cè)量系統(tǒng)。采用795 X595象素?cái)?shù)的CCD傳感器，根據(jù)活塞環(huán)本身幾何參數(shù)的特點(diǎn)推導(dǎo)出了活塞環(huán)各個(gè)參數(shù)之間的關(guān)系。使用了對(duì)圖像邊緣的亞像素定位技術(shù)對(duì)300微米的開(kāi)口進(jìn)行測(cè)量，測(cè)量系統(tǒng)的測(cè)量精度為士47微米。

文獻(xiàn)9】研究的機(jī)器視覺(jué)在線(xiàn)測(cè)量系統(tǒng)測(cè)量范圍從十幾絲到30毫米工件的外輪廓，經(jīng)過(guò)實(shí)驗(yàn)在同一狀態(tài)下長(zhǎng)時(shí)間測(cè)量同一工件誤差達(dá)到±3微米。

總之，機(jī)器視覺(jué)在高精度的尺寸測(cè)量領(lǐng)域有著很大的應(yīng)用空間，隨著機(jī)器視覺(jué)硬件制造技術(shù)的成熟和硬件成本的降低，機(jī)器視覺(jué)在現(xiàn)代化生產(chǎn)中將應(yīng)用的越來(lái)越廣泛，其測(cè)量精度也會(huì)逐漸提高【10】。

1.4設(shè)計(jì)的主要內(nèi)容

在查閱大量國(guó)內(nèi)外文獻(xiàn)的基礎(chǔ)上設(shè)計(jì)基于虛擬儀器和機(jī)器視覺(jué)技術(shù)的機(jī)械零件尺寸測(cè)量?jī)x系統(tǒng)。從理論上對(duì)機(jī)器視覺(jué)尺寸檢測(cè)進(jìn)行研究，設(shè)計(jì)適合課題要求、與硬件設(shè)備配套使用的視覺(jué)檢測(cè)程序。本課題具體的工作內(nèi)容包括:

1．機(jī)器視覺(jué)系統(tǒng)的總體構(gòu)建與實(shí)施方案設(shè)計(jì)，按照機(jī)器視覺(jué)系統(tǒng)的結(jié)構(gòu)，分析系統(tǒng)的組成和硬件的參數(shù)以及性能，這些硬件包括:光學(xué)鏡頭、光源、CCD相機(jī)、圖像采集卡，步進(jìn)電機(jī)控制模塊，選擇各軟件模塊，完成整個(gè)系統(tǒng)的系統(tǒng)設(shè)計(jì)設(shè)計(jì)。

2．對(duì)圖像處理方法進(jìn)行研究，對(duì)常用的圖像濾波和邊緣檢算法進(jìn)行研究。通過(guò)試驗(yàn)比較它們對(duì)機(jī)械加工零件圖像的處理效果，找到適合零件圖像的預(yù)處理方法。

3．研究基于IMAQ Vision的圖像處理函數(shù)以及相機(jī)的模型和相機(jī)標(biāo)定算法。對(duì)本文搭建的機(jī)器視覺(jué)的相機(jī)進(jìn)行標(biāo)定，利用標(biāo)定獲得的內(nèi)參數(shù)校正采集到的圖像的畸變，提高測(cè)量效果。

4．編制軟件程序?qū)崿F(xiàn)圖像的采集、圖像處理、特征提取和參數(shù)計(jì)算等功能。

5.分析影像測(cè)量?jī)x的精度是否合理。

1.5設(shè)計(jì)的背景和意義

隨著我國(guó)經(jīng)濟(jì)的持續(xù)增長(zhǎng)和工業(yè)產(chǎn)品精密程度的提高，以及對(duì)產(chǎn)品數(shù)量和質(zhì)量要求的提高，傳統(tǒng)的尺寸測(cè)量手段(如:卡尺、量規(guī)、萬(wàn)能工具顯微鏡、輪廓儀、X射線(xiàn)等)己經(jīng)不能滿(mǎn)足生產(chǎn)的需要。卡尺、量規(guī)等檢測(cè)手段雖然簡(jiǎn)便、快捷，但測(cè)量數(shù)據(jù)較少、精度不高;萬(wàn)能工具顯微鏡、輪廓儀等檢測(cè)手段雖然有較高的精度，但要求在特定的設(shè)備、特定的環(huán)境下進(jìn)行檢測(cè)，不但勞動(dòng)強(qiáng)度大，效率低，而且檢測(cè)過(guò)程同生產(chǎn)過(guò)程是分離的，這與現(xiàn)代工業(yè)所要求的在線(xiàn)檢測(cè)、實(shí)時(shí)控制的要求不符。機(jī)器視覺(jué)檢測(cè)可以高速、可靠和不間斷地對(duì)工業(yè)產(chǎn)品的質(zhì)量問(wèn)題進(jìn)行準(zhǔn)確的檢測(cè)，所以有望能取代以往費(fèi)時(shí)費(fèi)神但又無(wú)法保證檢測(cè)質(zhì)量的人工檢測(cè)方法?；谔摂M儀器的視覺(jué)測(cè)量系統(tǒng)融合了最新的傳感器、電子測(cè)量和計(jì)算機(jī)等技術(shù)，使得視覺(jué)檢測(cè)設(shè)備具有前所未有的速度、靈活性、測(cè)量精度和資源的可重用性。CCD攝像設(shè)備的分辨率和成像速度等技術(shù)性能的不斷提高，數(shù)字圖像處理技術(shù)的逐步完善，以及計(jì)算機(jī)的性能和性?xún)r(jià)比的迅速提高，為這一領(lǐng)域的研究提供了相當(dāng)有利的條件。此外，采用先進(jìn)的虛擬儀器技術(shù)還可以大大縮短產(chǎn)品的開(kāi)發(fā)周期，通過(guò)計(jì)算機(jī)網(wǎng)絡(luò)可獲得豐富的信息亦有助于我們解決各種各樣的技術(shù)問(wèn)題。鑒于現(xiàn)在機(jī)器視覺(jué)在產(chǎn)品測(cè)量中應(yīng)用的現(xiàn)狀，本課題針對(duì)機(jī)器視覺(jué)在機(jī)械加工零件尺寸檢測(cè)中的應(yīng)用進(jìn)行研究。課題的目標(biāo)是利用機(jī)器視覺(jué)在工業(yè)檢測(cè)中的優(yōu)勢(shì)對(duì)工業(yè)產(chǎn)品中基本的直線(xiàn)和圓形特征進(jìn)行檢測(cè)。本課題的目標(biāo)是研究開(kāi)發(fā)基于機(jī)器視覺(jué)的柔性好、效率高的工件尺寸檢測(cè)系統(tǒng)。本文的研究對(duì)提高我國(guó)機(jī)器視覺(jué)檢測(cè)系統(tǒng)的開(kāi)發(fā)應(yīng)用水平，提高工業(yè)檢測(cè)的質(zhì)量和效率以及突破國(guó)外公司對(duì)我國(guó)機(jī)器視覺(jué)市場(chǎng)的技術(shù)壟斷都具有現(xiàn)實(shí)意義，所研究的機(jī)器視覺(jué)系統(tǒng)具有一定的經(jīng)濟(jì)價(jià)值。

英斯特力儀器是一家集研發(fā)、生產(chǎn)及銷(xiāo)售于一體的 影像測(cè)量?jī)x，拉力試驗(yàn)機(jī), 硬度計(jì) ,探傷儀, 粗糙度儀, 測(cè)厚儀, 金相設(shè)備廠(chǎng)家, 致力于為客戶(hù)提供更好的檢測(cè)儀器。

1.1 Machine vision detection  

1.1.1 Machine vision  

Machine vision is a science that studies the use of cameras and computers to imitate human eyes and brain to complete tasks such as target recognition, tracking and measurement [11]. As machine vision involves multiple disciplines, it is difficult to give an accurate definition.  Machine vision is defined by the Machine Vision branch of the Society of Manufacturing Engineers (SME) and the Automation Vision Branch of the Robotics Industry association of America (RIA) as: "Machine vision is the use of optical devices for contactless perception to automatically acquire and interpret an image of a real scene in order to obtain information or control a machine or process."  

People began to study statistical pattern recognition of two-dimensional images in the 1950s, Roberts began to study THREE-DIMENSIONAL machine vision in the 1960s, and Mrr Artificial Intelligence Laboratory formally opened the course machine Vision in the mid-1970s. In the early 1980s, global research boom began, and machine vision gained vigorous development.  New concepts and theories keep emerging.  With the continuous improvement of computer technology and the increasingly mature image processing and transmission technology, the application of machine vision in production practice has accelerated the pace.  Now machine vision has been widely used in industry, agriculture, military, aviation, medicine and other fields.  At the same time, machine vision has made great progress in theoretical research. Now machine vision involves many disciplines, including optics, machinery, image processing, computer graphics, pattern recognition, artificial intelligence, artificial neural network and so on.  

1.1.2 Machine vision detection technology  

With the continuous development of manufacturing industry, the research and application of advanced manufacturing technology are more and more extensive.  The popularization and application of advanced manufacturing technology, automatic manufacturing system and advanced production mode require advanced testing methods to adapt to them.  Machine vision is applied to the testing field of manufacturing industry, and the process of determining the deviation of products relative to a set of standard requirements with machine vision system is usually called machine vision testing 2.  It refers to the application of machine vision in industrial inspection and is an important branch in the field of machine vision application and research.  Visual inspection is to be measured, the image as a means of testing and pass information or carrier to take advantage of detection method, the purpose of useful signal is extracted from the image, it is based on the modern optics, image fusion of electronics, computer science, information processing, computer vision and so on science and technology for the integration of modern testing technology.  Because machine vision system can quickly obtain a lot of information, and easy to integrate with the design information and processing control information, based on the vision detection technology of the instrument and equipment to achieve intelligence, digitalization, miniaturization, networking and multi-function, with online detection, real-time analysis, real-time control ability, in  

Military, industrial, commercial, medical and other fields have been widely concerned and applied [3] [4].  Machine vision inspection usually involves the measurement of the characteristics of specified parts such as accessory integrity, surface integrity and geometric dimensions.  The working process of machine vision detection is roughly as follows: First, the camera will be used to convert the target into image signals and send them to a special image processing system, which will process and calculate the information contained in these images;  The computer then makes a judgment or decision based on the result of processing;  Finally, the control signal is transmitted to the actuator.  Machine vision is characterized by automation, objectivity, non-contact and high precision. Compared with general image processing systems, machine vision emphasizes accuracy and speed as well as reliability in the industrial field environment.  Compared with traditional manual detection, machine vision detection is more efficient and the detection results are more accurate and reliable.  Because machine vision detection will not be affected by the operator's fatigue, sense of responsibility and experience and other factors, in some dangerous occasions not suitable for manual operation, work vision is difficult to meet the requirements of the occasion and with a high degree of repeatability, intelligence and rely on people's eyes can not be continuous and stable product detection occasions,  Machine vision can play its own advantages to complete the detection task efficiently and with high quality.  

1.2 Virtual Instrument  

Virtual Instrument is a brand new achievement which is closely combined with testing technology and Instrument technology in the process of intensive penetration of computer hardware, software and bus technology into other related technical fields [5].  Virtual instrument using IO interface equipment complete signal acquisition and processing, the use of computer display function to simulate the traditional instrument control panel, the output test results with a variety of forms, using computer powerful software implementation evaluation of signal data, analysis and processing, so as to complete a computer instrument system which has the function of the various tests.  Virtual instrument is the product of the deep combination of modern computer technology and instrument technology, and it is also an important technology in the field of computer aided testing (CAT).  Virtual instrument can make use of the powerful graphics environment and online help function of computer to form a high-grade and cheap new instrument which has both the basic functions of common instruments and special functions that common instruments do not have.  It can establish the virtual instrument panel with Chinese and English interface, complete the control, data analysis and display of the instrument, it changes the way of using the traditional instrument, improve the function and efficiency of the instrument, greatly reduce the price of the instrument, the user can define the new function of the instrument according to their own needs.  In the virtual instrument system, hardware is only to solve the signal input and output, software is the key of the whole instrument, the structure based on software system can greatly save the development and maintenance cost.  The virtual instrument has many varieties, strong functions, high degree of automation and good man-machine interface. Its functions are the same as those of traditional instruments: data collection, data analysis and processing, and data result processing.  One of the key differences between them is flexibility.  Virtual instruments can be customized by users, which means that users are free to combine computer platforms, hardware, software, and accessories needed to complete applications.  This flexibility is not available in traditional vendor-defined, fixed-function instruments.  Therefore, virtual instrument is a revolution in the history of instrument development, representing the latest direction and trend of instrument development, and is an important field of information technology, will have a huge effect on the development of science and technology and industrial production, will become the direction and trend of instrument development.  1.3 The development status of machine vision detection in foreign machine vision detection from the beginning of the 1980s has been widely studied, the domestic machine vision detection research from the 1990s gradually began.  At present, with the increase of the application of machine vision inspection system, more and more research on machine vision.  According to the different application fields of machine vision, the research on machine vision inspection can be divided into different categories, and different scholars have different opinions on classification.  Literature [4] divides machine vision quality control systems applied in industry into four categories: dimension quality, surface quality, assembly structure and operation quality.  Reference 61 The application fields of machine vision are divided into four categories: product inspection, robotics, product classification and other applications.  Dimensional measurement is an important field of machine vision research and application, and it is also a relatively early research direction.  When machine vision is applied to dimension measurement engineering, every link from the choice of hardware (light source, image sensor, etc.) of machine vision system to the design of software algorithm will affect the final performance.  The proper hardware should be selected according to the characteristics of the project.  Literature [7] studied the size detection of electrical disk. Two CCD sensors with 756X581 pixels were used to collect images from the two sides of electrical disk respectively, and the size of the workpiece was obtained through contour tracking, straight line segmentation and sub-pixel positioning.  The accuracy of the system reaches plus or minus 0.3 mm, and the detection time of each workpiece is about 0.3 seconds.  

Reference [8] studied the piston ring closing 151 clearance measurement system based on computer vision.  Using CCD sensor with 795 X595 pixels, the relationship between piston ring parameters is deduced according to the characteristics of piston ring geometry parameters.  The sub-pixel positioning technology of the image edge was used to measure the 300 micron opening, and the measurement accuracy of the system was 47 microns.  

Reference 9】 The machine vision online measurement system studied measured the range from a dozen threads to the outer contour of 30 mm workpiece. After the experiment, the error of measuring the same workpiece for a long time in the same state reached ±3 microns.  

In short, machine vision has great application space in the field of high-precision dimensional measurement. With the maturity of machine vision hardware manufacturing technology and the reduction of hardware cost, machine vision will be more and more widely used in modern production, and its measurement accuracy will gradually improve [10].  

1.4 Main contents of the design  

On the basis of consulting a large number of domestic and foreign literature design of mechanical parts size measuring instrument system based on virtual instrument and machine vision technology.  From the theory of machine vision size detection research, design suitable for the subject requirements, and supporting the use of hardware visual detection program.  The specific work content of this project includes:  

1.  Machine vision system overall construction and implementation of the scheme design, according to the structure of the machine vision system, the analysis and the parameters of the hardware and the system performance, the hardware includes: optical lens, light source, CCD camera, image acquisition card, the stepper motor control module, select each software module, complete the system design of the whole system design.  

2.  Image processing methods are studied, and common image filtering and edge detection algorithms are studied.  By comparing their processing effects on machined parts image, a suitable preprocessing method for parts image is found.  

3.  The image processing function, camera model and camera calibration algorithm based on IMAQ Vision are studied.  To calibrate the machine vision camera built in this paper, the internal parameters obtained from the calibration are used to correct the distortion of the image collected and improve the measurement effect.  

4.  The software program is designed to realize the functions of image acquisition, image processing, feature extraction and parameter calculation.  

5. Analyze whether the accuracy of the image measuring instrument is reasonable.  

1.5 Background and significance of the design  

With the continuous growth of China's economy and the improvement of the precision of industrial products, as well as the improvement of the requirements for the quantity and quality of products, the traditional measurement methods (such as calipers, gauges, universal tool microscope, profilometer, X-ray, etc.) have been unable to meet the needs of production.  Caliper, gauge and other detection methods are simple and fast, but the measurement data is less, the accuracy is not high;  Although universal tool microscope, profilometer and other detection methods have higher accuracy, they require detection in specific equipment and specific environment, which not only has high labor intensity and low efficiency, but also separates the detection process from the production process, which is inconsistent with the requirements of online detection and real-time control required by modern industry.  Machine vision inspection can be high-speed, reliable and uninterrupted quality problems of industrial products for accurate detection, so it is expected to replace the previous time-consuming and laborious but unable to ensure the quality of the manual detection method.  The visual measurement system based on virtual instrument integrates the latest sensor, electronic measurement and computer technology, which makes the visual inspection equipment have unprecedented speed, flexibility, measurement accuracy and resource reuse.  The continuous improvement of resolution and imaging speed of CCD camera equipment, the gradual improvement of digital image processing technology, as well as the rapid improvement of computer performance and cost performance, provide quite favorable conditions for the research in this field.  In addition, the use of advanced virtual instrument technology can greatly shorten the product development cycle, through the computer network can obtain rich information also helps us to solve a variety of technical problems.  In view of the current situation of the application of machine vision in product measurement, this topic is aimed at the application of machine vision in machining parts size detection.  The goal of this project is to use the advantages of machine vision in industrial inspection to detect the basic straight and circular features in industrial products.  The goal of this topic is to develop a flexible and efficient workpiece size detection system based on machine vision.  The research of this paper has practical significance for improving the development and application level of machine vision inspection system in Our country, improving the quality and efficiency of industrial inspection and breaking through the technological monopoly of foreign companies on the machine vision market in our country. The machine vision system studied has certain economic value.