《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > MEMS|傳感技術(shù) > 設(shè)計(jì)應(yīng)用 > 基于改進(jìn)暗通道先驗(yàn)的車牌圖像去霧方法研究
基于改進(jìn)暗通道先驗(yàn)的車牌圖像去霧方法研究
2022年電子技術(shù)應(yīng)用第11期
石冬陽(yáng)1,,張俊林1,,賈 兵1,聶 玲1,,楊慧敏2
1.重慶科技學(xué)院 電氣工程學(xué)院,,重慶401331;2.湘潭大學(xué) 數(shù)學(xué)與計(jì)算科學(xué)學(xué)院,,湖南 湘潭411105
摘要: 針對(duì)霧霾場(chǎng)景下車牌識(shí)別系統(tǒng)存在識(shí)別精度較差的問(wèn)題,,提出改進(jìn)型車牌識(shí)別模型。該模型運(yùn)用改進(jìn)型暗通道先驗(yàn)去霧算法進(jìn)行去霧處理,考慮到原去霧算法處理含明亮區(qū)域霧霾圖像時(shí)會(huì)出現(xiàn)顏色失真等問(wèn)題,,首先對(duì)大氣光值進(jìn)行閾值限制,其次對(duì)引入因子進(jìn)行優(yōu)化選擇,,最后引入容差機(jī)制以修正透射率,,并對(duì)圖像亮度進(jìn)行調(diào)整以提升圖像可視化效果。仿真結(jié)果表明,,運(yùn)用改進(jìn)后算法得到的去霧結(jié)果在PSNR,、SSIM、Entropy,、e性能上相對(duì)于改進(jìn)前分別平均提升1.934 dB,、0.082、0.235,、38.995,。將去霧前后車牌圖像進(jìn)行識(shí)別測(cè)試,車牌識(shí)別精度提升22%,,證明了所提模型的優(yōu)越性,。
中圖分類號(hào): TP394.1
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.223211
中文引用格式: 石冬陽(yáng),張俊林,,賈兵,,等. 基于改進(jìn)暗通道先驗(yàn)的車牌圖像去霧方法研究[J].電子技術(shù)應(yīng)用,2022,,48(11):13-18.
英文引用格式: Shi Dongyang,,Zhang Junlin,Jia Bing,,et al. Research on defogging method of license plate image based on improved dark channel prior[J]. Application of Electronic Technique,,2022,48(11):13-18.
Research on defogging method of license plate image based on improved dark channel prior
Shi Dongyang1,,Zhang Junlin1,,Jia Bing1,Nie Ling1,,Yang Huimin2
1.School of Electrical Engineering,,Chongqing University of Science and Technology,Chongqing 401331,,China,; 2.School of Mathematics and Computing Science,Xiangtan University,,Xiangtan 411105,,China
Abstract: Aiming at the problem of poor recognition accuracy of license plate recognition system in haze scene, an improved license plate recognition model is proposed. The model uses the improved dark channel apriori defogging algorithm for defogging. Considering the color distortion and other problems when the original defogging algorithm processes the haze image with bright areas, firstly, the atmospheric light value is limited by the threshold value. Secondly, the introduction factor is optimized. And finally, the tolerance mechanism is introduced to correct the transmittance, and the image brightness is adjusted to improve the image visualization effect. The simulation results show that the performance of PSNR, SSIM, enterprise and e improved by 1.934 dB, 0.082, 0.235 and 38.995 respectively. The recognition test of the license plate image before and after defogging shows that the recognition accuracy of the license plate is improved by 22%, which proves the superiority of the proposed model.
Key words : license plate recognition;color distortion,;threshold limit,;introducing factors,;tolerance mechanism

0 引言

    隨著社會(huì)經(jīng)濟(jì)快速發(fā)展,車輛逐漸成為我們?nèi)粘1夭豢缮俚慕煌üぞ撸?a class="innerlink" href="http://forexkbc.com/tags/車牌識(shí)別" target="_blank">車牌識(shí)別系統(tǒng)因此被應(yīng)用到道路監(jiān)控中,,一定程度上提高了交通管理的效率,。在無(wú)霧的場(chǎng)景下,車牌識(shí)別系統(tǒng)能獲得較好的識(shí)別效果[1],;在霧霾天氣下,,受到大氣中懸浮顆粒的影響,使得圖像可見(jiàn)度降低[2],,車牌識(shí)別系統(tǒng)采集到的車牌圖像變得模糊不清,,圖像中車牌信息特征無(wú)法及時(shí)有效呈現(xiàn)出來(lái),導(dǎo)致車牌定位與識(shí)別的精度嚴(yán)重下降,。

    為了直接有效地提升車牌識(shí)別精度,,必須首先對(duì)車牌識(shí)別系統(tǒng)采集到的圖像進(jìn)行去霧處理。在圖像去霧方法中,,圖像增強(qiáng)和圖像復(fù)原是兩種常見(jiàn)的去霧方法,。前者在處理具有復(fù)雜結(jié)構(gòu)的有霧圖像時(shí)效果并不理想。后者基于大氣散射模型,,進(jìn)而求解無(wú)霧圖像,,獲得了較好的圖像去霧效果,但自身仍有局限性,。Tan[3]采用最大化恢復(fù)圖像的局部對(duì)比度來(lái)消除霧霾,,但結(jié)果中出現(xiàn)了圖像色調(diào)飽和的現(xiàn)象。He等人[4]提出了基于導(dǎo)向?yàn)V波的暗通道去霧算法,,縮短了去霧時(shí)間,,但在處理含有天空等明亮區(qū)域的霧霾圖像時(shí)出現(xiàn)了顏色的失真和偏移。Tarel等人[5]構(gòu)建大氣耗散函數(shù)以實(shí)現(xiàn)圖像去霧,,去霧結(jié)果中出現(xiàn)了顏色失真的現(xiàn)象,。Fattal等[6]通過(guò)計(jì)算場(chǎng)景內(nèi)反射率得到無(wú)霧圖像,但該方法不適用于模糊圖像和灰度圖像。目前暗通道先驗(yàn)去霧算法取得了較好的去霧效果,,但該算法處理含有天空等明亮區(qū)域圖像時(shí)存在顏色失真和偏移等問(wèn)題,,故本次在暗通道先驗(yàn)去霧算法的基礎(chǔ)上進(jìn)行相應(yīng)的改進(jìn)。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000004998,。




作者信息:

石冬陽(yáng)1,,張俊林1,賈  兵1,,聶  玲1,,楊慧敏2

(1.重慶科技學(xué)院 電氣工程學(xué)院,重慶401331;2.湘潭大學(xué) 數(shù)學(xué)與計(jì)算科學(xué)學(xué)院,,湖南 湘潭411105)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。