本文選題：圖像去模糊 + 卷積神經(jīng)網(wǎng)絡��； 參考：《江南大學》2017年碩士論文

【摘要】：隨著虛擬現(xiàn)實技術和移動互聯(lián)網(wǎng)的不斷發(fā)展,圖像在人類獲取和傳遞信息的過程中扮演著重要角色。在日常生活中,圖像和視頻不斷的充斥在我們的視野中。由于人眼對圖像的清晰度比較敏感,清晰度低的圖像會給觀看者帶來不舒服的感受。所以相關顯示設備技術才得以不斷發(fā)展來滿足人們的需求。然而現(xiàn)實生活中存在一些不可避免的因素會導致獲得的圖像失真,例如圖像采集過程中攝像機未聚焦、相機抖動等。所以說利用失真圖像來還原出原始圖像是一件非常重要的事情,具有很大的實際意義。實現(xiàn)這個過程的技術我們稱為圖像復原技術,是目前比較熱門的研究方向。本論文利用卷積神經(jīng)網(wǎng)絡模型在圖像復原上的優(yōu)勢,研究了圖像復原涉及的兩個熱門問題圖像去模糊和圖像超分辨率重建。本文研究內(nèi)容體現(xiàn)在下面幾個方面:(1)提出一種基于卷積神經(jīng)網(wǎng)絡的圖像去模糊模型。避免了傳統(tǒng)的圖像去模糊算法對模糊圖像先驗知識的依賴。在點擴散函數(shù)未知的情況下,通過網(wǎng)絡訓練學習輸入的模糊圖像與目標清晰圖像二者之間的非線性映射關系,實現(xiàn)圖像去模糊。通過實驗,在選擇網(wǎng)絡參數(shù)時,對該圖像去模糊方法在性能和時間上做出權衡,再將最佳的參數(shù)應用于該模型上。實驗表明該模型優(yōu)于傳統(tǒng)圖像去模糊算法。(2)提出一種基于混合神經(jīng)網(wǎng)絡的圖像去模糊模型�；旌仙窠�(jīng)網(wǎng)絡由卷積神經(jīng)網(wǎng)絡與BP神經(jīng)網(wǎng)絡(Back propagation Neural Network)組成,二者分步實現(xiàn)圖像復原。首先,通過訓練卷積神經(jīng)網(wǎng)絡提取退化圖像有效感知特征,再將提取的特征向量作為BP神經(jīng)網(wǎng)絡的輸入來訓練BP神經(jīng)網(wǎng)絡,從而實現(xiàn)圖像去模糊。實驗表明該方法在小尺度的模糊核上的復原效果顯然優(yōu)于現(xiàn)有方法,但是當模糊核的尺度超過23×23的情況下,復原效果明顯下降。(3)提出一種改進的基于卷積神經(jīng)網(wǎng)絡的圖像超分辨率重建模型。基于卷積神經(jīng)網(wǎng)絡的圖像超分辨率重建模型包含3個卷積層,它們的作用分別為提取圖像塊特征、非線性映射和重建。本文通過增加網(wǎng)絡的層數(shù),改變卷積層中濾波器的數(shù)量,改變卷積層中濾波器尺寸等來改進基于卷積神經(jīng)網(wǎng)絡的超分辨率重建技術。改進的卷積神經(jīng)網(wǎng)絡包含四個卷積層和一個下采樣層。下采樣層采用最大、中值、最小池三池聯(lián)合的方法,不僅可以有效提取圖像的質(zhì)量感知特征而且有利于提高訓練效率。實驗結果表明,該模型可以有效逼近真實的高分辨率圖像。
[Abstract]:With the development of virtual reality technology and mobile Internet, images play an important role in the process of obtaining and transmitting information. In our daily life, images and videos are constantly filled with our vision. Because the human eye is sensitive to the sharpness of the image, the low-definition image will bring uncomfortable feelings to the viewer. Therefore, the related display equipment technology can be continuously developed to meet the needs of people. However, there are some unavoidable factors in real life, such as camera unfocusing, camera jitter and so on. So it is very important to restore the original image by using the distorted image, which has great practical significance. The technology to realize this process, which is called image restoration technology, is a hot research direction at present. In this paper, the advantage of convolution neural network model in image restoration is used to study the image de-blurring and super-resolution reconstruction of two hot problems involved in image restoration. The main contents of this paper are as follows: (1) an image de-blurring model based on convolution neural network is proposed. It avoids the dependence of the traditional image de-blurring algorithm on the priori knowledge of the blurred image. When the point diffusion function is unknown, the nonlinear mapping relationship between the inputted fuzzy image and the target clear image is studied by network training, and the image deblurring is realized. Through experiments, when the network parameters are selected, the performance and time of the image de-blurring method are weighed, and the best parameters are applied to the model. Experiments show that the proposed model is superior to the traditional image de-blurring algorithm. (2) A hybrid neural network based image de-blurring model is proposed. Hybrid neural network is composed of convolution neural network and back propagation neural network. Firstly, the effective perceptual feature of degraded image is extracted by training convolution neural network, and then the extracted feature vector is used as the input of BP neural network to train BP neural network to realize image de-blurring. The experimental results show that the restoration effect of this method on the small scale fuzzy kernel is obviously better than that of the existing method, but when the scale of the fuzzy kernel is more than 23 脳 23, (3) an improved image super-resolution reconstruction model based on convolution neural network is proposed. The image super-resolution reconstruction model based on convolution neural network consists of three convolution layers which are used to extract image block features nonlinear mapping and reconstruction respectively. In this paper the super-resolution reconstruction technique based on convolution neural network is improved by increasing the number of layers in the network changing the number of filters in the convolution layer and changing the size of the filter in the convolution layer. The improved convolution neural network consists of four convolution layers and one downsampling layer. The method of maximum median and minimum pool is adopted in the lower sampling layer which not only can extract the image quality perception features effectively but also can improve the training efficiency. Experimental results show that the model can approach real high resolution images effectively.
【學位授予單位】：江南大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41;TP183

【參考文獻】

相關期刊論文 前5條

1 李艷琴;張立毅;孫云山;劉淑聰;;一種改進的圖像迭代盲反卷積算法[J];計算機工程;2012年08期

2 周玉;彭召意;;運動模糊圖像的維納濾波復原研究[J];計算機工程與應用;2009年19期

3 沈煥鋒;李平湘;張良培;王毅;;圖像超分辨率重建技術與方法綜述[J];光學技術;2009年02期

4 柏森,張邦禮,曹長修;神經(jīng)網(wǎng)絡圖象復原方法的研究進展[J];中國圖象圖形學報;2002年11期

5 尚鋼,鐘珞,陳立耀;神經(jīng)網(wǎng)絡結構與訓練參數(shù)選取[J];武漢工業(yè)大學學報;1997年02期

相關博士學位論文 前2條

1 趙雪青;降質(zhì)圖像復原方法研究[D];陜西師范大學;2013年

2 易麗婭;圖像復原的Bregman迭代正則化方法研究[D];華中科技大學;2011年

相關碩士學位論文 前1條

1 虞濤;基于鄰域嵌入的圖像超分辨率重建研究[D];南京郵電大學;2013年

，

本文編號：2112069