本文選題：圖像預(yù)處理 + 人臉超分辨率重建�。� 參考：《上海電力學(xué)院》2017年碩士論文

【摘要】：當(dāng)下社會,隨著人們安全意識的提高,視頻監(jiān)控技術(shù)得到廣泛利用,已發(fā)展到凡有安全防范的地方,必有視頻監(jiān)控的地步。傳統(tǒng)的視頻監(jiān)控僅提供事發(fā)后的視頻數(shù)據(jù)查詢,而不能做到事前預(yù)警。并且,由于視頻數(shù)據(jù)規(guī)模較大,監(jiān)控人員無法監(jiān)看成百上千視頻畫面,其很大程度上失去了視頻監(jiān)控事前預(yù)警的功能。因此,智能視頻監(jiān)控技術(shù)得到了大力發(fā)展和應(yīng)用,智能視頻監(jiān)控利用計(jì)算機(jī)強(qiáng)大的數(shù)據(jù)處理功能,對海量的視頻數(shù)據(jù)進(jìn)行處理分析,濾除無關(guān)信息,提供關(guān)鍵信息,并根據(jù)設(shè)定的規(guī)則進(jìn)行判斷和報(bào)警。大部分的智能視頻監(jiān)控的對象主要以人為主體,智能視頻監(jiān)控主要對人體的異常行為和人體的生物特征進(jìn)行檢測、跟蹤、處理和識別。鑒于人臉識別技術(shù)具有非接觸性、操作簡單、可靠性高等優(yōu)越性,將人臉識別技術(shù)應(yīng)用到智能視頻監(jiān)控中成為了研究的熱點(diǎn)。視頻監(jiān)控環(huán)境下的人臉圖像在獲取過程中,受成像條件和環(huán)境干擾等諸多因素的影響,圖像的分辨率較低。低分辨率的人臉圖像不利于后續(xù)的人臉識別,本文首先對視頻中的低分辨率人臉圖像進(jìn)行超分辨率重建,將重建后的人臉圖像用于后續(xù)的識別。本文的研究內(nèi)容由以下幾個(gè)方面構(gòu)成:(1)本文研究了運(yùn)動目標(biāo)檢測方法、人臉檢測方法和圖像預(yù)處理方法。首先利用背景減除法和幀間差分法實(shí)現(xiàn)了視頻中的運(yùn)動目標(biāo)檢測,然后利用OpenCV源代碼中已經(jīng)訓(xùn)練好的人臉分類器實(shí)現(xiàn)了人臉檢測,并利用直方圖均衡化、均值濾波、中值濾波、幾何歸一化等方法實(shí)現(xiàn)了人臉圖像的預(yù)處理。(2)研究圖像觀測模型、圖像質(zhì)量評價(jià)方法、超分辨率重建的常用方法和基于鄰域嵌入的人臉超分辨率重建方法。針對現(xiàn)有的基于鄰域嵌入的人臉超分辨率重建方法存在的不足,本文提出基于聯(lián)合局部約束和自適應(yīng)鄰域選擇的鄰域嵌入人臉超分辨率重建方法。并在CAS-PEAL-R1人臉庫上進(jìn)行實(shí)驗(yàn),與前沿的人臉超分辨率算法進(jìn)行比較,相較于傳統(tǒng)的基于鄰域嵌入的人臉超分辨率重建方法,本文算法在PSNR和SSIM上分別提升了0.39dB和0.02。(3)研究人臉識別中常用的特征提取方法,尤其是基于方向邊緣幅值的特征提取算子。針對方向邊緣幅值模式提取的人臉特征維數(shù)過高和計(jì)算復(fù)雜度較大的問題,提出了結(jié)合方向邊緣幅值模式和有監(jiān)督的局部保持投影的人臉識別方法。首先,采用POEM算子進(jìn)行特征提取;其次,將高維特征數(shù)據(jù)投影到SLPP算法求出的低維樣本空間進(jìn)行降維;最后,采用最近鄰法對測試樣本進(jìn)行分類。在CAS-PEAL-R1人臉庫上的實(shí)驗(yàn)結(jié)果表明,在表情、背景、飾物、時(shí)間、距離測試集上,該算法的平均識別率較POEM+LPP算法提高了22%,較POEM+PCA提高了2%。(4)搭建視頻人臉識別系統(tǒng),該系統(tǒng)實(shí)現(xiàn)了人臉檢測、預(yù)處理、超分辨率重建和識別的功能。輸入拍攝的視頻對系統(tǒng)進(jìn)行測試,測試結(jié)果表明,系統(tǒng)能夠順利實(shí)現(xiàn)視頻人臉識別,標(biāo)準(zhǔn)樣本庫內(nèi)的測試樣本正確識別率達(dá)到90%,標(biāo)準(zhǔn)樣本庫外的測試樣本拒識率為100%。
[Abstract]:In the present society, with the improvement of people's security awareness, video surveillance technology has been widely used. It has developed to where there is security prevention, there must be a video surveillance site. Traditional video monitoring only provides video data query after the incident, but can not be prewarning. And, because of the large scale of video data, monitoring personnel can not. Watching hundreds of video images, it largely loses the function of pre-warning of video surveillance. Therefore, intelligent video surveillance technology has been developed and applied. Intelligent video monitoring and monitoring use the powerful data processing function of the computer to process and analyze massive video data, filter out unrelated information, and provide key information. According to the set rules to judge and alarm. Most of the intelligent video surveillance objects are mainly human body. Intelligent video surveillance mainly detects, tracks, processes and identifies human body's abnormal behavior and human biological characteristics. In view of the non touch, simple operation, high reliability and superiority of face recognition technology, the human face recognition technology will be superior to people. Face recognition technology has become a hot spot in the application of intelligent video surveillance. In the process of video surveillance, face image is affected by many factors such as imaging conditions and environmental interference, the resolution of image is low. Low resolution face image is not conducive to subsequent face recognition. First, the low resolution in video is used in this paper. The research content of this paper is composed of the following aspects: (1) this paper studies the detection method of moving target, the method of face detection and the method of image preprocessing. First, we use the background subtraction method and the inter frame difference method to realize the motion of the video. Mark detection, and then use the trained face classifier in OpenCV source code to realize face detection, and make use of histogram equalization, mean filtering, median filtering, geometric normalization and other methods to realize face image preprocessing. (2) study image observation model, image quality evaluation method, super-resolution reconstruction method and base The face super-resolution reconstruction method is embedded in the neighborhood. In view of the shortcomings of the existing face super-resolution reconstruction methods based on the neighborhood embedding, this paper proposes a neighborhood embedded face super-resolution reconstruction method based on joint local constraints and adaptive neighborhood selection. Experiments on the CAS-PEAL-R1 face database and the front face face are carried out. Compared to the traditional method of face super-resolution reconstruction based on neighborhood embedding, the algorithm improves the feature extraction methods commonly used in PSNR and 0.02. (3) research on face recognition, especially the feature extraction operator based on the direction edge amplitude, compared with the traditional method of face super-resolution reconstruction based on the neighborhood embedding. A face recognition method combining direction edge amplitude pattern and supervised local preserving projection is proposed. First, feature extraction is carried out by POEM operator. Secondly, the high dimension feature data is projected to the low dimension sample space obtained by SLPP algorithm to reduce the dimension. The test samples are classified by the nearest neighbor method. The experimental results on the CAS-PEAL-R1 face database show that the average recognition rate of the algorithm is 22% higher than that of the POEM+LPP algorithm on the expression, background, decorations, time and distance test sets. Compared with POEM+PCA, the algorithm improves the 2%. (4) construction of video face recognition system. The system realizes face detection, preprocessing, and super. The function of resolution reconstruction and recognition. The input video is tested on the system. The test results show that the system can successfully realize video face recognition. The correct recognition rate of the test samples in the standard sample library is 90%, and the rejection rate of the test samples outside the standard sample library is 100%.

【學(xué)位授予單位】：上海電力學(xué)院
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TN948.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙麗;齊興斌;李雪梅;;基于回歸函數(shù)結(jié)合局部自相似的單幀圖像超分辨率算法[J];計(jì)算機(jī)測量與控制;2016年04期

2 朱俊勇;賴劍煌;;面向視頻的動態(tài)人臉識別研究進(jìn)展[J];廣東公安科技;2015年02期

3 王志明;;無參考圖像質(zhì)量評價(jià)綜述[J];自動化學(xué)報(bào);2015年06期

4 王慶偉;應(yīng)自爐;;一種基于Haar-Like T特征的人臉檢測算法[J];模式識別與人工智能;2015年01期

5 楊利平;辜小花;;用于人臉識別的相對梯度直方圖特征描述[J];光學(xué)精密工程;2014年01期

6 褚江;陳強(qiáng);楊曦晨;;全參考圖像質(zhì)量評價(jià)綜述[J];計(jì)算機(jī)應(yīng)用研究;2014年01期

7 桑運(yùn)昌;高歆;蔣捷;;未來智能視頻監(jiān)控技術(shù)發(fā)展及應(yīng)用[J];自動化與儀器儀表;2012年05期

8 張青苗;李鵬;趙勇;何寶富;孫_g;;一種基于OpenCV實(shí)現(xiàn)的運(yùn)動目標(biāo)檢測算法的研究[J];艦船電子工程;2010年07期

9 王旭;彭宗舉;楊鈾;邵楓;蔣志迪;;質(zhì)降參考圖像質(zhì)量評價(jià)方法研究[J];寧波大學(xué)學(xué)報(bào)(理工版);2009年04期

10 田啟川;張潤生;;生物特征識別綜述[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

相關(guān)博士學(xué)位論文 前1條

1 錢建軍;人臉圖像特征提取和分類的若干方法研究[D];南京理工大學(xué);2014年

相關(guān)碩士學(xué)位論文 前1條

1 孫正春;智能視頻監(jiān)控中的人臉識別[D];電子科技大學(xué);2012年

，

本文編號：1834402