應(yīng)用獨(dú)立成分分析的太陽(yáng)能電池圖像去噪
發(fā)布時(shí)間:2018-11-10 11:09
【摘要】:研究用于太陽(yáng)能電池缺陷檢測(cè)的電致發(fā)光圖像噪聲去除的問(wèn)題。太陽(yáng)能電池電致發(fā)光圖像是近紅外圖像,一般來(lái)說(shuō)采集到的圖像具有噪聲嚴(yán)重、亮度不均勻等特點(diǎn),使用快速獨(dú)立成分分析(Fast ICA)將圖像分離成兩個(gè)獨(dú)立成分,一個(gè)是噪聲,一個(gè)是所需的分離結(jié)果。由于分離結(jié)果中仍存在椒鹽噪聲,對(duì)分離結(jié)果再進(jìn)行均值濾波,最后得到理想的太陽(yáng)能電池圖像。實(shí)驗(yàn)結(jié)果表明,此方法對(duì)太陽(yáng)能電池電致發(fā)光圖像的去噪效果顯著,為進(jìn)一步的圖像處理做好了準(zhǔn)備。
[Abstract]:The problem of noise removal from electroluminescent images used for defect detection of solar cells is studied. The electroluminescent image of solar cell is near infrared image. Generally speaking, the collected image has the characteristics of serious noise and uneven brightness. The image is separated into two independent components by fast independent component analysis (Fast ICA), one is noise, and the other is noise. One is the desired separation result. Because there is still salt and pepper noise in the separation result, the mean filter is applied to the separation result, and finally the ideal solar cell image is obtained. The experimental results show that the proposed method is effective in de-noising the electroluminescent images of solar cells, and is ready for further image processing.
【作者單位】: 北京工商大學(xué)計(jì)算機(jī)與信息工程學(xué)院;
【基金】:北京市教委科研計(jì)劃面上項(xiàng)目(KM201210011003)
【分類號(hào)】:TP391.41;TM914.4
[Abstract]:The problem of noise removal from electroluminescent images used for defect detection of solar cells is studied. The electroluminescent image of solar cell is near infrared image. Generally speaking, the collected image has the characteristics of serious noise and uneven brightness. The image is separated into two independent components by fast independent component analysis (Fast ICA), one is noise, and the other is noise. One is the desired separation result. Because there is still salt and pepper noise in the separation result, the mean filter is applied to the separation result, and finally the ideal solar cell image is obtained. The experimental results show that the proposed method is effective in de-noising the electroluminescent images of solar cells, and is ready for further image processing.
【作者單位】: 北京工商大學(xué)計(jì)算機(jī)與信息工程學(xué)院;
【基金】:北京市教委科研計(jì)劃面上項(xiàng)目(KM201210011003)
【分類號(hào)】:TP391.41;TM914.4
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 王超;蔣曉瑜;柳效輝;;基于電致發(fā)光成像理論的硅太陽(yáng)電池缺陷檢測(cè)[J];光電子.激光;2011年09期
【共引文獻(xiàn)】
相關(guān)期刊論文 前10條
1 肖文波;何興道;王慶;賴相霖;黃蘇華;;透鏡與電池間距對(duì)聚光光伏系統(tǒng)特性影響的實(shí)驗(yàn)研究[J];光電子.激光;2012年06期
2 姚紅兵;馬桂殿;沈?qū)殗?guó);顧寄南;曾祥波;鄭學(xué)良;蔣光平;;基于圖像處理技術(shù)的樹(shù)脂鏡片瑕疵分類特征研究[J];光電子.激光;2014年02期
3 趙珊;裴亮;劉翠;王濤;王新亮;朱雪嬌;;基于MATLAB圖像處理的汽車牌照識(shí)別研究[J];測(cè)繪工程;2014年01期
4 劉鵬;何雯;肖巍巍;;基于GPGPU技術(shù)快速提取數(shù)字表面模型[J];測(cè)繪地理信息;2014年02期
5 吳s,
本文編號(hào):2322303
本文鏈接:http://sikaile.net/kejilunwen/dianlilw/2322303.html
最近更新
教材專著