【摘要】：質(zhì)量需求是現(xiàn)代企業(yè)的核心需求，產(chǎn)品質(zhì)量的好壞直接關(guān)系著企業(yè)的市場(chǎng)競(jìng)爭(zhēng)力和企業(yè)自身的存續(xù)。因此，將質(zhì)量放在首位是目前所有企業(yè)的共同選擇。質(zhì)量控制與質(zhì)量管理的方法與手段多種多樣，傳統(tǒng)檢測(cè)與測(cè)量往往依賴(lài)于人工完成。 本文著眼于流水線(xiàn)上、不間斷運(yùn)動(dòng)的連續(xù)物體視覺(jué)可識(shí)別量的在線(xiàn)檢測(cè)。利用機(jī)器視覺(jué)替代人工檢測(cè)，運(yùn)用計(jì)算機(jī)及軟件替代檢測(cè)工人，通過(guò)可重構(gòu)的視覺(jué)檢測(cè)方法實(shí)現(xiàn)在不同被檢對(duì)象上的快速反應(yīng)與裝備實(shí)現(xiàn)。 本文主要研究了可動(dòng)態(tài)增減檢測(cè)子系統(tǒng)的分布式網(wǎng)絡(luò)拓?fù)�，支撐采集控制硬件層、圖像處理識(shí)別層、界面顯示層、質(zhì)量等級(jí)評(píng)價(jià)等多層面的視覺(jué)重構(gòu)理論，建立了基于軟件芯片的視覺(jué)重構(gòu)體系，對(duì)重構(gòu)流程、重構(gòu)方案進(jìn)行了設(shè)計(jì)，采用規(guī)范化、標(biāo)準(zhǔn)化的方式設(shè)計(jì)了各個(gè)層次間交互接口。 針對(duì)市場(chǎng)上不同廠商的數(shù)字圖像獲取設(shè)備，本文均根據(jù)自身產(chǎn)品而定制、通用性差的缺點(diǎn)進(jìn)行了相關(guān)研究。首先，分析了不同數(shù)字圖像獲取標(biāo)準(zhǔn)的優(yōu)劣，建立了異構(gòu)硬件環(huán)境下的圖像獲取通用模型；接著，創(chuàng)建了通用圖像獲取接口，設(shè)計(jì)并完善了SDK，包括初始化函數(shù)、設(shè)置函數(shù)、獲取函數(shù)、圖像處理回調(diào)函數(shù)、存儲(chǔ)函數(shù)、輔助函數(shù)在內(nèi)的六大類(lèi)函數(shù)的定義；最后，對(duì)函數(shù)接口及其組態(tài)設(shè)計(jì)進(jìn)行了研究。 在圖像獲取的基礎(chǔ)上，對(duì)圖像處理環(huán)節(jié)進(jìn)行了探討。首先，分析了視覺(jué)檢測(cè)的基本需求，梳理了視覺(jué)檢測(cè)的基本流程；接著，根據(jù)視覺(jué)檢測(cè)流程的主要需求，設(shè)計(jì)了機(jī)器視覺(jué)在線(xiàn)檢測(cè)算法庫(kù)，將常用的圖像預(yù)處理、圖像分割、圖像復(fù)原、特征提取等算法進(jìn)行了標(biāo)準(zhǔn)化、參數(shù)化設(shè)計(jì)，著重突出優(yōu)化算法代碼、執(zhí)行效率、魯棒性等問(wèn)題；最后，建立并完善了一套基于配置信息的視覺(jué)檢測(cè)運(yùn)行環(huán)境，可實(shí)現(xiàn)檢測(cè)算子的搜索、調(diào)用、重載等功能，，有利于提高檢測(cè)系統(tǒng)的柔性，加速針對(duì)不同檢測(cè)對(duì)象的設(shè)備部署。 為實(shí)現(xiàn)圖像特征的提取與識(shí)別，本文首先研究了常用特征描述方法，分析了其優(yōu)缺點(diǎn)，并指出單一特征或過(guò)小規(guī)模特征集在可重構(gòu)視覺(jué)檢測(cè)方法中的局限性。其后，針對(duì)這一核心問(wèn)題展開(kāi)，設(shè)計(jì)了一套基于統(tǒng)計(jì)與時(shí)頻聯(lián)合的特征提取方法，建立了通用性機(jī)器視覺(jué)在線(xiàn)檢測(cè)特征集，并利用該特征集對(duì)三種產(chǎn)品的圖像圖形學(xué)特征進(jìn)行了描述。最后，嘗試設(shè)計(jì)了基于遺傳算法的特征解耦方法，并就其中關(guān)鍵技術(shù)進(jìn)行了研究。 最后，利用可重構(gòu)的機(jī)器視覺(jué)方法對(duì)粘扣帶、導(dǎo)爆管、網(wǎng)孔織物外觀質(zhì)量視覺(jué)檢測(cè)進(jìn)行了研究，開(kāi)發(fā)了具有自主知識(shí)產(chǎn)權(quán)的檢測(cè)系統(tǒng)，驗(yàn)證了可重構(gòu)的產(chǎn)品視覺(jué)檢測(cè)方法的可行性和有效性。
[Abstract]:Quality demand is the core demand of modern enterprises. The quality of products is directly related to the market competitiveness of enterprises and the survival of enterprises themselves. Therefore, quality in the first place is the common choice of all enterprises. There are a variety of methods and means for quality control and quality management, and traditional inspection and measurement often rely on manual completion. This paper focuses on the on-line detection of visual recognizable quantities of continuous objects with continuous motion on pipeline. Machine vision is used to replace manual detection, computer and software are used to replace workers, and reconfigurable visual detection method is used to realize rapid response and equipment on different objects. This paper mainly studies the distributed network topology of dynamic incremental and subtractive detection subsystem, supports the collection and control hardware layer, the image processing recognition layer, the interface display layer, the quality grade evaluation and so on multi-layer vision reconstruction theory. The visual reconfiguration system based on software chip is established. The reconstruction process and reconfiguration scheme are designed. The interface between different levels is designed in a standardized and standardized way. Aiming at the digital image acquisition equipment of different manufacturers in the market, this paper studies the shortcomings of customization and poor generality according to their own products. Firstly, the advantages and disadvantages of different digital image acquisition standards are analyzed, and the general image acquisition model under heterogeneous hardware environment is established. Then, the general image acquisition interface is created, and the initialization function and setting function are designed and perfected in SDK,. Get function, image processing callback function, storage function, auxiliary function, etc. Finally, the function interface and its configuration design are studied. On the basis of image acquisition, the link of image processing is discussed. Firstly, the basic requirements of visual detection are analyzed, and the basic flow of visual detection is combed. Then, according to the main requirements of visual detection process, the online detection algorithm library of machine vision is designed to preprocess and segment the commonly used images. Image restoration, feature extraction and other algorithms are standardized, parameterized design, focusing on the optimization of algorithm code, execution efficiency, robustness and other issues. Finally, a set of visual detection environment based on configuration information is established and improved. The functions of searching, calling and overloading of detection operators can be realized, which can improve the flexibility of the detection system and accelerate the equipment deployment for different detection objects. In order to achieve image feature extraction and recognition, this paper first studies common feature description methods, analyzes their advantages and disadvantages, and points out the limitations of single feature or too small feature set in reconfigurable vision detection method. Then, aiming at this core problem, a set of feature extraction method based on statistical and time-frequency combination is designed, and the feature set of universal machine vision on-line detection is established. The feature set is used to describe the image graphics features of three kinds of products. Finally, the feature decoupling method based on genetic algorithm is designed and the key technologies are studied. Finally, using the reconfigurable machine vision method to study the visual inspection of the appearance quality of the adhesive tape, the detonation tube and the mesh fabric, the inspection system with independent intellectual property rights is developed. The feasibility and effectiveness of the reconfigurable visual inspection method are verified.
【學(xué)位授予單位】：武漢科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP274;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李立輕,黃秀寶;用于疵點(diǎn)檢測(cè)的織物自適應(yīng)正交小波的實(shí)現(xiàn)[J];東華大學(xué)學(xué)報(bào)(自然科學(xué)版);2002年02期

2 李立輕,黃秀寶;圖像處理用于織物疵點(diǎn)自動(dòng)檢測(cè)的研究進(jìn)展[J];東華大學(xué)學(xué)報(bào)(自然科學(xué)版);2002年04期

3 鄧貴仕,李朝輝;信息系統(tǒng)組態(tài)平臺(tái)及其構(gòu)件復(fù)用技術(shù)[J];大連理工大學(xué)學(xué)報(bào);2004年01期

4 韓春雷,王庫(kù),馬健;一種數(shù)碼相機(jī)成像和視頻處理前端的設(shè)計(jì)[J];單片機(jī)與嵌入式系統(tǒng)應(yīng)用;2004年09期

5 杜世宏;秦其明;王橋;;空間關(guān)系及其應(yīng)用[J];地學(xué)前緣;2006年03期

6 陳洋;王潤(rùn)生;;結(jié)合Gabor濾波器和ICA技術(shù)的紋理分類(lèi)方法[J];電子學(xué)報(bào);2007年02期

7 楊芙清,梅宏,李克勤;軟件復(fù)用與軟件構(gòu)件技術(shù)[J];電子學(xué)報(bào);1999年02期

8 張瑞林,徐軼峰;基于PCNN的織物疵點(diǎn)識(shí)別研究[J];紡織學(xué)報(bào);2004年06期

9 賈曉宏;雷智軍;;淺談國(guó)內(nèi)外導(dǎo)爆管雷管標(biāo)準(zhǔn)的差異[J];國(guó)防技術(shù)基礎(chǔ);2009年11期

10 徐惠萍;;可重構(gòu)技術(shù)綜述[J];甘肅科技;2007年10期

相關(guān)博士學(xué)位論文 前1條

1 劉懷廣;浮法玻璃缺陷在線(xiàn)識(shí)別算法的研究及系統(tǒng)實(shí)現(xiàn)[D];華中科技大學(xué);2011年

本文編號(hào)：2233431