本文關(guān)鍵詞：脈沖耦合神經(jīng)網(wǎng)絡(luò)在圖像處理中的應(yīng)用研究　出處：《蘭州大學(xué)》2003年碩士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： 脈沖耦合神經(jīng)網(wǎng)絡(luò) 脈沖噪聲 高斯噪聲 分割編碼 圖像分割 中值濾波 塊變換編碼

【摘要】：通過(guò)對(duì)貓等小型哺乳動(dòng)物視覺(jué)皮層的研究而建立的Eckhorn[1]模型是脈沖耦合神經(jīng)網(wǎng)絡(luò)(Pulse Coupled Neural Network,PCNN)的基礎(chǔ),經(jīng)由Johnson和其他研究者[2,3,4,5,6]做了進(jìn)一步變形而最終演化為PCNN。PCNN 不同于傳統(tǒng)的人工神經(jīng)網(wǎng)絡(luò)模型,它是通過(guò)模擬視覺(jué)皮層神經(jīng)細(xì)胞的活動(dòng)而建立的神經(jīng)網(wǎng)絡(luò)模型,是對(duì)真實(shí)神經(jīng)元的簡(jiǎn)化與近似。PCNN網(wǎng)絡(luò)模型所具有的連接域特性和動(dòng)態(tài)閾值衰減特性能夠使?fàn)顟B(tài)相似的神經(jīng)元同步輸出脈沖,這一點(diǎn)充分模擬了哺乳動(dòng)物視覺(jué)皮層神經(jīng)元的生物特性,因而在圖像分割、邊緣提取、目標(biāo)識(shí)別等圖像處理方面獲得了廣泛的應(yīng)用。　 同時(shí),PCNN 是一種多參數(shù)神經(jīng)網(wǎng)絡(luò)模型,其應(yīng)用效果的好壞在很大程度上取決于參數(shù)的設(shè)置,但是到目前為止各參數(shù)對(duì)網(wǎng)絡(luò)模型的影響只存在定性分析,還沒(méi)有一種針對(duì)不同圖像從而自動(dòng)求得各參數(shù)最佳值的算法,只能通過(guò)手動(dòng)實(shí)驗(yàn)分析來(lái)逐步設(shè)置。因此最佳參數(shù)的設(shè)置就成了一項(xiàng)繁瑣但又十分關(guān)鍵的工作。本論文對(duì)原始PCNN 模型作了一定程度的簡(jiǎn)化,在保持PCNN 連接域特性和動(dòng)態(tài)閾值衰減特性的基礎(chǔ)上減少了神經(jīng)元模型輸入域和連接域的一些參數(shù),并將該簡(jiǎn)化模型應(yīng)用到圖像降噪和分割編碼中,對(duì)其實(shí)驗(yàn)結(jié)果進(jìn)行了分析和總結(jié)�！� 本論文第二章對(duì)該簡(jiǎn)化模型在濾除圖像中的脈沖噪聲和高斯噪聲方面的應(yīng)用做了初步探索,在結(jié)合前人研究的基礎(chǔ)上結(jié)合局部中值算法,提出了基于脈沖耦合神經(jīng)網(wǎng)絡(luò)的脈沖噪聲濾波器和高斯噪聲濾波器,并和其他算法相比較,進(jìn)行了分析和總結(jié)。 本論文第三章分析了脈沖耦合神經(jīng)網(wǎng)絡(luò)在圖像分割方面的應(yīng)用,并將該簡(jiǎn)化神經(jīng)網(wǎng)絡(luò)模型作為分割圖像編碼的分割算法,應(yīng)用到圖像編碼中,提出了基于脈沖耦合神經(jīng)網(wǎng)絡(luò)的分割圖像編碼,最后和基于塊變換的編碼方法進(jìn)行了初步比較,分析了各自的優(yōu)缺點(diǎn)�！�
[Abstract]:Eckhorn based on a study of the visual cortex of small mammals such as cats. [Model is the basis of Pulse Coupled Neural Network PCNN, via Johnson and other researchers. [The PCNN.PCNN model is different from the traditional artificial neural network model. It is a neural network model established by simulating the activities of nerve cells in the visual cortex. The simplification and approximation of real neurons. PCNN network model has the characteristics of connection domain and dynamic threshold attenuation, which can synchronize the output pulses of neurons with similar states. This fully simulates the biological characteristics of mammalian visual cortical neurons and has been widely used in image processing such as image segmentation edge extraction target recognition and so on. At the same time, PCNN is a multi-parameter neural network model, the effect of its application depends on the setting of parameters to a great extent, but so far, there is only qualitative analysis of the influence of each parameter on the network model. There is no algorithm for finding the optimal value of each parameter automatically for different images. Only through manual experimental analysis to set up step by step, so the setting of the best parameters has become a tedious but very important work. This paper simplifies the original PCNN model to a certain extent. On the basis of preserving the characteristics of PCNN connection domain and dynamic threshold attenuation, some parameters of input domain and connection domain of neuron model are reduced, and the simplified model is applied to image denoising and segmentation coding. The experimental results are analyzed and summarized. In the second chapter of this paper, the application of the simplified model in filtering impulse noise and Gao Si noise in the image is preliminarily explored, and the local median algorithm is combined with previous studies. The impulse noise filter and Gao Si noise filter based on impulse coupled neural network are proposed and compared with other algorithms. In the third chapter of this paper, the application of impulse coupled neural network in image segmentation is analyzed, and the simplified neural network model is applied to image coding as the segmentation algorithm of segmentation image coding. A segmented image coding method based on impulsive coupled neural network is proposed. Finally, a preliminary comparison is made with the coding method based on block transform, and their advantages and disadvantages are analyzed.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2003
【分類(lèi)號(hào)】：TN911.73

【引證文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 徐月美;多尺度變換的多聚焦圖像融合算法研究[D];中國(guó)礦業(yè)大學(xué);2012年

相關(guān)碩士學(xué)位論文 前9條

1 鄭濤;基于PCNN的航拍絕緣子圖像的分割及定位研究[D];大連海事大學(xué);2011年

2 史楷;基于OMAP3530平臺(tái)的PCNN圖像壓縮編碼技術(shù)研究[D];蘭州大學(xué);2011年

3 李守亮;脈沖神經(jīng)元電路網(wǎng)絡(luò)中的若干問(wèn)題研究[D];蘭州大學(xué);2011年

4 王紹波;超聲醫(yī)學(xué)圖像的去噪及增強(qiáng)研究[D];安徽理工大學(xué);2010年

5 康世華;基于多小波和神經(jīng)網(wǎng)絡(luò)的圖像編碼算法研究[D];蘭州大學(xué);2006年

6 張北斗;PCNN在生物醫(yī)學(xué)圖像處理中的應(yīng)用研究[D];蘭州大學(xué);2007年

7 荀文龍;PCNN在溢油遙感圖像邊緣檢測(cè)中的應(yīng)用研究[D];大連海事大學(xué);2008年

8 程飛燕;生物圖像邊緣檢測(cè)算法的研究[D];蘭州大學(xué);2010年

9 程成;改進(jìn)型脈沖耦合神經(jīng)網(wǎng)絡(luò)在圖像混合噪聲中的應(yīng)用研究[D];云南大學(xué);2012年

，

本文編號(hào)：1437650