本文選題：反卷積　切入點(diǎn)：多尺度　出處：《哈爾濱工程大學(xué)》2016年碩士論文

【摘要】：神經(jīng)元是構(gòu)成神經(jīng)系統(tǒng)結(jié)構(gòu)和功能的基本單元,神經(jīng)元形態(tài)結(jié)構(gòu)的三維重建對于神經(jīng)系統(tǒng)結(jié)構(gòu)和功能的研究具有重要的意義。共聚焦顯微成像在成像過程中有圖像退化和模糊現(xiàn)象。此外,神經(jīng)元圖像軸突和樹突等樹形結(jié)構(gòu)具有密度、尺度變化大,像素分布不均勻和背景目標(biāo)混雜等問題,這給神經(jīng)元樹形結(jié)構(gòu)的分割帶來了很大的困難,從而不利于神經(jīng)元形態(tài)結(jié)構(gòu)的三維重建。針對上述問題,本文將從圖像復(fù)原和去燥、樹形結(jié)構(gòu)增強(qiáng)與二值化、樹形結(jié)構(gòu)追蹤方面展開研究,主要研究內(nèi)容如下:首先,針對共聚焦顯微成像過程中的圖像退化和模糊現(xiàn)象,本文引入了反卷積算法對圖像進(jìn)行復(fù)原處理。通過分析成像過程中的圖像退化原因,建立了退化模型,并通過對比實(shí)驗(yàn)分析了約束最小二乘反卷積算法和Lucy-Richardson反卷積算法。此外,針對神經(jīng)元圖像的噪聲特點(diǎn)和神經(jīng)元的結(jié)構(gòu)特點(diǎn),通過對比實(shí)驗(yàn)分析了幾種具有邊緣保留特性的去噪算法對于神經(jīng)元圖像去噪的適應(yīng)性。其次,針對神經(jīng)元圖像像素分布不均勻、線形結(jié)構(gòu)尺度變化大的特點(diǎn),本文在借鑒血管、視網(wǎng)膜等圖像線形結(jié)構(gòu)分割算法的基礎(chǔ)上,將多尺度線形結(jié)構(gòu)增強(qiáng)濾波運(yùn)用于神經(jīng)元圖像軸突和樹突的分割。針對分割結(jié)果存在尺度間不連續(xù)的問題,引入了各向異性高斯平滑算法,借鑒各向異性濾波的思想,本文設(shè)計了一種各向異性均值和中值濾波算法。經(jīng)實(shí)驗(yàn)驗(yàn)證,這種算法在保持線形結(jié)構(gòu)原始尺度不變的同時,很好的解決了多尺度融合時尺度間不連續(xù)的問題。然后,針對神經(jīng)元圖像背景和目標(biāo)的特點(diǎn),分析了傳統(tǒng)閾值化方法對神經(jīng)元圖像分割的優(yōu)缺點(diǎn)。在此基礎(chǔ)上,本文設(shè)計了一種基于連通域的二值圖像線形結(jié)構(gòu)分割方法,在本文算法中,參與閾值化的對象不再是孤立的像素點(diǎn),而是連接起來的連通域。經(jīng)實(shí)驗(yàn)驗(yàn)證,本文算法可以較好的提取出經(jīng)局部閾值化方法處理后的圖像中的線形結(jié)構(gòu),本文算法為噪聲干擾嚴(yán)重的二值圖像中線形結(jié)構(gòu)的提取提供了一種新的思路。最后,因?yàn)樯鲜龅难芯慷际且匀痔幚頌榻Y(jié)果的,研究人員無法對感興趣結(jié)構(gòu)或重要結(jié)構(gòu)進(jìn)行重點(diǎn)處理,也就是說缺乏交互性。此外,全局處理通常只有在圖像成像質(zhì)量高的情況下才能取得良好的分割效果。因此,相對于全局處理,對基于局部搜索的樹形結(jié)構(gòu)追蹤算法的研究很有必要。本文分別從二維和三維角度研究了基于局部搜索的追蹤算法和實(shí)現(xiàn)原理,并通過現(xiàn)有工具進(jìn)行了神經(jīng)元樹形結(jié)構(gòu)追蹤實(shí)驗(yàn)分析。
[Abstract]:Neurons are the basic units that make up the structure and function of the nervous system, Three-dimensional reconstruction of neuronal morphology is of great significance in the study of nervous system structure and function. Confocal microscopic imaging has image degradation and blur in the imaging process. The dendritic structure of neuronal image has many problems, such as density, large scale change, uneven pixel distribution and mixed background target, which brings great difficulties to the segmentation of neuronal tree structure. In view of the above problems, this paper will focus on image restoration and dryness, tree structure enhancement and binarization, tree structure tracking. The main research contents are as follows: first, Aiming at image degradation and blur in confocal microscopy, this paper introduces deconvolution algorithm to restore the image. By analyzing the causes of image degradation in the imaging process, a degradation model is established. The constrained least square deconvolution algorithm and the Lucy-Richardson deconvolution algorithm are analyzed by contrast experiments. Through comparative experiments, the adaptability of several denoising algorithms with edge reservation to neural image denoising is analyzed. Secondly, aiming at the characteristics of uneven pixel distribution of neuron image and large scale change of linear structure, this paper uses blood vessels as reference. Based on the linear structure segmentation algorithm of retinal image, the multi-scale linear structure enhancement filter is applied to the segmentation of neuronal image axons and dendrites. The anisotropic Gao Si smoothing algorithm is introduced, and an anisotropic mean and median filtering algorithm is designed based on the idea of anisotropic filtering. The experimental results show that this algorithm keeps the original scale of the linear structure unchanged at the same time. The problem of discontinuity between scales in multiscale fusion is well solved. Secondly, the advantages and disadvantages of the traditional thresholding method for neuronal image segmentation are analyzed according to the characteristics of the background and target of neuron image. In this paper, a linear structure segmentation method of binary image based on connected domain is designed. In this algorithm, the object involved in thresholding is not isolated pixel, but connected connected domain. The algorithm in this paper can extract the linear structure of the image processed by the local threshold method. This algorithm provides a new way for the extraction of the linear structure in the noisy binary image. Finally, Because all of the above studies are based on global processing, researchers cannot focus on structures of interest or important structures, that is to say, lack of interactivity. Global processing usually achieves good segmentation results only when the image quality is high. It is necessary to study the tree structure tracking algorithm based on local search. The tracking experiment of neuron tree structure is carried out with the existing tools.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：R338;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 袁澤劍,鄭南寧,張元林,郭震;一種非線性擴(kuò)散濾波器的設(shè)計方法及其應(yīng)用[J];計算機(jī)學(xué)報;2002年10期

相關(guān)博士學(xué)位論文 前2條

1 明星;光學(xué)顯微圖像神經(jīng)元形態(tài)重建和可視化方法研究[D];華中科技大學(xué);2014年

2 楊航;圖像反卷積算法研究[D];吉林大學(xué);2012年

，

本文編號：1657363