【摘要】：人類主要依賴視覺(jué)系統(tǒng)獲取外界信息,一旦視覺(jué)通路發(fā)生病變或者損傷就會(huì)導(dǎo)致人類視力的衰弱甚至失明,作為一種新型的輔助設(shè)備,視覺(jué)假體能夠通過(guò)電刺激視覺(jué)神經(jīng)系統(tǒng)使患者產(chǎn)生光幻視,幫助盲人重見(jiàn)光明。在視覺(jué)假體的輔助下,盲人是可以完成日常生活中的人臉識(shí)別任務(wù)的,然而在實(shí)際應(yīng)用中復(fù)雜的光照變化會(huì)導(dǎo)致人臉識(shí)別率的下降,因此對(duì)光照變化下的人臉圖像進(jìn)行光照補(bǔ)償具有很重要的意義。本文針對(duì)單尺度Retinex算法的光暈缺陷,從硬件實(shí)現(xiàn)的角度上提出了改進(jìn)的基于雙邊濾波的單尺度Retinex算法。在用雙邊濾波對(duì)圖像的光照分量進(jìn)行估計(jì)的基礎(chǔ)上,對(duì)對(duì)數(shù)域中圖像反射分量進(jìn)行自適應(yīng)亮度調(diào)整。通過(guò)將經(jīng)典的單尺度Retinex算法(SSR)、多尺度Retinex算法(MSR)、基于雙邊濾波的SSR算法和本文改進(jìn)算法進(jìn)行MATLAB仿真。試驗(yàn)結(jié)果表明改進(jìn)算法能夠有效地消除各種條件下的光照影響,具有較好的光照魯棒性,并且與經(jīng)典的MSR算法相比亮度提升了 26%,對(duì)比度提升了 23%,在ExtendedYaleB人臉庫(kù)上的平均人臉識(shí)別率較經(jīng)典的Retinex算法提升了 13%,在人臉識(shí)別系統(tǒng)的應(yīng)用中具有很強(qiáng)的適用性。本文完成了光照補(bǔ)償算法的FPGA硬件實(shí)現(xiàn),并利用ModelSim對(duì)各個(gè)模塊進(jìn)行了功能仿真。然后在DE2-115開(kāi)發(fā)板上搭建相關(guān)硬件平臺(tái)對(duì)算法進(jìn)行了功能性驗(yàn)證。為了直觀地驗(yàn)證算法對(duì)不同圖像的處理效果,本文通過(guò)串口輸入數(shù)據(jù)到算法處理模塊,并用VGA顯示處理后的圖像。同時(shí)通過(guò)SignalTap Ⅱ捕獲算法處理的圖像數(shù)據(jù)與matlab的軟件結(jié)果對(duì)比。最終硬件驗(yàn)證結(jié)果表明,本文提出的算法在硬件上取得了與軟件相同的處理效果,能夠在消除圖像光照影響的同時(shí),顯現(xiàn)增強(qiáng)人臉暗部區(qū)域的輪廓細(xì)節(jié)。
[Abstract]:People rely mainly on the visual system to obtain external information. Once the visual pathway changes or damages, it will lead to human vision decline or even blindness, as a new type of auxiliary equipment. Visual prostheses can help blind people rediscover light by electrical stimulation of the visual nervous system. With the aid of visual prosthesis, blind people can complete the task of face recognition in daily life. However, in practical applications, complicated illumination changes will lead to the decline of face recognition rate. Therefore, it is very important to compensate face images with illumination. Aiming at the halo defect of single-scale Retinex algorithm, an improved single-scale Retinex algorithm based on bilateral filtering is proposed from the point of view of hardware implementation. On the basis of estimating the illumination component of the image by using bilateral filtering, the image reflection component in logarithmic domain is adjusted adaptively. The classical single-scale Retinex algorithm (SSR), the multi-scale Retinex algorithm (MSR), the two-sided filter based SSR algorithm and the improved algorithm are simulated in MATLAB. The experimental results show that the improved algorithm can effectively eliminate the illumination effect under various conditions, and has better illumination robustness. Compared with the classical MSR algorithm, the brightness and contrast are improved by 26% and 23% respectively. The average face recognition rate in extended YaleB face database is 13% higher than that in the classical Retinex algorithm. It has strong applicability in the application of face recognition system. In this paper, FPGA hardware implementation of illumination compensation algorithm is completed, and each module is simulated by ModelSim. Then build the related hardware platform on the DE2-115 development board to verify the function of the algorithm. In order to intuitively verify the processing effect of the algorithm to different images, this paper input data into the algorithm processing module through serial port, and display the processed image with VGA. At the same time, the image data processed by signal Tap II acquisition algorithm is compared with the results of matlab software. Finally, the hardware verification results show that the proposed algorithm achieves the same processing effect as the software in hardware, which can eliminate the influence of image illumination and show the contour details of the enhanced dark area of the face at the same time.
【學(xué)位授予單位】：西安理工大學(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 陳超;;改進(jìn)單尺度Retinex算法在圖像增強(qiáng)中的應(yīng)用[J];計(jì)算機(jī)應(yīng)用與軟件;2013年04期

2 袁琳;陳暄;龍丹;;光照變化條件下的人臉識(shí)別技術(shù)研究[J];計(jì)算機(jī)工程與應(yīng)用;2014年04期

3 吳小貝;陸燕玉;王靜;柴新禹;;仿真假體視覺(jué)下的人臉識(shí)別研究進(jìn)展[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;2012年04期

4 楊大為;王琰;;一種人臉識(shí)別中的光照補(bǔ)償方法[J];計(jì)算機(jī)應(yīng)用;2012年S1期

5 孫勁光;李揚(yáng);孟祥福;劉軍立;;改進(jìn)的單尺度Retinex及其在人臉識(shí)別中的應(yīng)用[J];計(jì)算機(jī)應(yīng)用研究;2011年12期

6 劉篤晉;孫淑霞;李思明;;人臉識(shí)別中光照處理方法的分析[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2011年01期

7 胡韋偉;汪榮貴;方帥;胡瓊;;基于雙邊濾波的Retinex圖像增強(qiáng)算法[J];工程圖學(xué)學(xué)報(bào);2010年02期

8 葛微;李桂菊;程宇奇;薛陳;朱明;;利用改進(jìn)的Retinex進(jìn)行人臉圖像光照處理[J];光學(xué)精密工程;2010年04期

9 紀(jì)則軒;陳強(qiáng);孫權(quán)森;夏德深;;基于雙邊濾波的單尺度Retinex圖像增強(qiáng)算法[J];微電子學(xué)與計(jì)算機(jī);2009年10期

10 許欣;陳強(qiáng);王平安;孫懷江;夏德深;;消除光暈現(xiàn)象的快速Retinex圖像增強(qiáng)[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2008年10期

相關(guān)碩士學(xué)位論文 前7條

1 宋浩東;基于Retinex的變化光照條件下人臉識(shí)別研究[D];北京化工大學(xué);2014年

2 黃震川;基于噪聲估計(jì)的DR圖像處理算法研究[D];華南理工大學(xué);2014年

3 秦攀;光照魯棒的人臉檢測(cè)和人臉識(shí)別方法研究[D];華東理工大學(xué);2014年

4 李俊峰;雙邊濾波算法的快速實(shí)現(xiàn)及其在圖像處理的應(yīng)用[D];南方醫(yī)科大學(xué);2013年

5 王海洋;人臉光照矯正算法研究與實(shí)現(xiàn)[D];電子科技大學(xué);2013年

6 王良勤;人臉識(shí)別中光照預(yù)處理與識(shí)別算法的研究[D];華中科技大學(xué);2008年

7 陳霧;基于Retinex理論的圖像增強(qiáng)算法研究[D];南京理工大學(xué);2006年

，

本文編號(hào)：2120391