本文關(guān)鍵詞：基于機(jī)器視覺的文檔與印鑒缺陷檢測(cè)的方法與實(shí)現(xiàn)　出處：《南京理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 機(jī)器視覺 缺陷檢測(cè) 投影 特征匹配 輪廓跟蹤 SVM

【摘要】：隨著機(jī)器視覺技術(shù)與自動(dòng)化技術(shù)的發(fā)展,機(jī)器視覺技術(shù)已被廣泛應(yīng)用到各種缺陷檢測(cè)中。本文利用機(jī)器視覺技術(shù)與圖像處理領(lǐng)域相關(guān)知識(shí),針對(duì)在線檢測(cè)系統(tǒng)中,證書打印、蓋章的缺陷問題進(jìn)行檢測(cè)。主要包括以下內(nèi)容:(1)給出了一種基于邊緣像素點(diǎn)旋轉(zhuǎn)的文檔傾斜角度的快速計(jì)算方法。該方法先將文檔圖像進(jìn)行降采樣處理,再對(duì)降采樣的圖像使用沈俊算子提取邊緣。然后,采用由"粗"到"精"的方法對(duì)提取的邊緣像素點(diǎn)進(jìn)行旋轉(zhuǎn)投影,并計(jì)算投影方差。由于方差最大時(shí)對(duì)應(yīng)的旋轉(zhuǎn)角度最可能是文檔圖像的傾斜角度,故據(jù)此來計(jì)算傾斜角。實(shí)驗(yàn)結(jié)果表明,使用該方法能夠快速計(jì)算文檔圖像傾斜角度。(2)提出了一種基于直方圖波峰分析的文檔缺墨檢測(cè)方法。該方法首先去除文字筆畫周圍灰度過渡區(qū)。然后,采用滑動(dòng)窗口對(duì)圖像進(jìn)行遍歷,計(jì)算滑動(dòng)窗口內(nèi)圖像直方圖,根據(jù)直方圖波峰分布情況判斷是否缺墨。最后,統(tǒng)計(jì)每列檢測(cè)到的缺墨滑動(dòng)窗口個(gè)數(shù),若其大于一個(gè)閾值T,則該列為缺墨列。實(shí)驗(yàn)結(jié)果表明,該方法能夠?qū)θ蹦臋n圖像做出準(zhǔn)確判斷。(3)提出了一種基于殘差圖的印鑒缺陷檢測(cè)方法。該方法首先對(duì)印鑒進(jìn)行定位,接著將待測(cè)印鑒與標(biāo)準(zhǔn)印鑒進(jìn)行配準(zhǔn),然后計(jì)算配準(zhǔn)后印鑒的殘差圖,再對(duì)殘差圖進(jìn)行形態(tài)學(xué)濾波處理,最后對(duì)形態(tài)學(xué)濾波處理后的圖像測(cè)量目標(biāo)的周長(zhǎng)與面積。根據(jù)周長(zhǎng)與面積大小判斷印鑒是否存在缺陷問題。在印鑒定位中,本文根據(jù)圓形印鑒的對(duì)稱特征進(jìn)行印鑒定位,該方法能快速定位印鑒位置且魯棒性較高。在印鑒配準(zhǔn)中,本文采用了 ORB算法提取待測(cè)印鑒與標(biāo)準(zhǔn)印鑒的特征點(diǎn),對(duì)特征點(diǎn)進(jìn)行匹配,再使用投票策略,計(jì)算待測(cè)印鑒與標(biāo)準(zhǔn)印鑒之間的偏轉(zhuǎn)角,該方法能夠有效地計(jì)算待測(cè)印鑒與標(biāo)準(zhǔn)印鑒之間的偏轉(zhuǎn)角,實(shí)現(xiàn)配準(zhǔn)。(4)實(shí)現(xiàn)了基于灰度直方圖特征和SVM的文檔缺墨區(qū)域檢測(cè)。根據(jù)文本圖像的特征,本文選擇了灰度直方圖特征,使用SVM分類器對(duì)滑動(dòng)窗口內(nèi)圖像進(jìn)行檢測(cè)。實(shí)驗(yàn)結(jié)果表明,該方法能夠有效判斷窗口塊是否缺墨。(5)最后本文介紹了一種面向計(jì)量檢定測(cè)試中心的證書缺陷在線檢測(cè)系統(tǒng)。主要介紹了其硬件系統(tǒng)與軟件系統(tǒng)。
[Abstract]:With the development of machine vision technology and automation technology, machine vision technology has been widely applied to detect various defects. By using the machine vision technology and image processing knowledge, according to the online detection system, certificate printing, detect defects sealed. Mainly includes the following contents: (1) gives a fast calculate the edge pixel point of rotation of the document based on the tilt angle method. The down sampling processing of document image, and then use the Shen Jun operator to extract the edge image down sampling. Then, by using the "rough" to "fine" method of edge pixels to extract the rotation projection, and the projection variance. Because of the rotation angle corresponding to the maximum variance is most likely the tilt angle of the document image, so according to the calculated angle. The experimental results show that this method can quickly calculate the document image Tilt angle. (2) proposed a histogram peak analysis method based on document missing ink. This method firstly remove the strokes of characters around the gray transition zone. Then, using the sliding window to traverse the image, the image histogram is computed in the sliding window, according to the histogram peak distribution to determine whether tuppo ink. Finally, the statistics of each list of detected missing ink sliding window number, if it is greater than a threshold value T, the column is short of Molie. The experimental results show that this method can make accurate judgments on the ink document image. (3) proposed a seal defect detection method based on the residual graph. This method first carry on the localization the seal, then sample seal and seal standard registration, and then calculate the residual map seal registration, for residual image morphological filtering, finally measuring target on the perimeter of the processed image morphological filter The area and perimeter and area. According to whether the size of existing defects in the seal seal. The seal positioning, positioning according to the symmetrical characteristic of circle seal, the method can quickly locate the position of the seal and high robustness. In seal registration, this paper uses ORB algorithm to extract the feature points to be measured with the standard seal seal. To match the feature points, and then use the voting strategy, calculate the deflection angle between the seal and the seal of the standard to be measured, the method can effectively calculate the deflection angle between the measured and standard, seal seal to achieve registration. (4) the gray histogram and SVM document missing ink region detection according to the characteristics. The text image, this paper chooses the feature of gray histogram, sliding window image detection using SVM classifier. The experimental results show that this method can effectively block the window to determine whether the lack of ink (5). At last, this paper introduces a certificate defect online detection system oriented to metrological verification test center. It mainly introduces its hardware and software systems.

【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄧安良;任明武;;基于HSV空間的紙幣面額識(shí)別算法研究[J];現(xiàn)代電子技術(shù);2015年02期

2 張?jiān)?余靜;謝孟峽;;印章印文的鑒定方法[J];理化檢驗(yàn)(化學(xué)分冊(cè));2014年11期

3 孫日明;梁波;;一種高精度文本圖像傾斜檢測(cè)方法[J];大連交通大學(xué)學(xué)報(bào);2014年03期

4 李小紅;謝成明;賈易臻;張國(guó)富;;基于ORB特征的快速目標(biāo)檢測(cè)算法[J];電子測(cè)量與儀器學(xué)報(bào);2013年05期

5 張順利;李衛(wèi)斌;吉軍;;基于投影的文檔圖像傾斜校正方法[J];計(jì)算機(jī)工程與應(yīng)用;2010年03期

6 燕鵬;安如;;基于FAST改進(jìn)的快速角點(diǎn)探測(cè)算法[J];紅外與激光工程;2009年06期

7 喬德江;陳鴻昶;;基于粒子群優(yōu)化的文本圖像傾斜檢測(cè)[J];通信技術(shù);2009年07期

8 劉鐵根;鄧集杰;張忠傳;朱均超;何瑾;李秀艷;;基于平滑卷積定位的圓形印鑒提取方法研究[J];光電工程;2009年04期

9 嚴(yán)筱永;閻浩;沈維燕;任明武;;基于改進(jìn)的Hough變換的圓檢測(cè)[J];金陵科技學(xué)院學(xué)報(bào);2009年01期

10 楊萬扣;任明武;楊靜宇;;數(shù)字圖像中基于鏈碼的目標(biāo)面積計(jì)算方法[J];計(jì)算機(jī)工程;2008年01期

，

本文編號(hào)：1406437