the achievements of this thesis can be summarized as follows : it offers a new way to study parallel image restoration by combining the architectures with the image restoration . a new sequence algorithm based on median filter, named wmf ( weighted median filter ), is proposed, then a parallel and optimal algorithm is discussed on smp clusters 考慮到每個(gè)像素點(diǎn)的權(quán)值可根據(jù)鄰域中的像素求出,其操作相同,只是操作過程中涉及的數(shù)據(jù)不同,接著設(shè)計(jì)了并行算法pwmf(parallelweightedmedianfilter),并討論了其在smpcluster上的優(yōu)化問題。
the second is a fuzzy neuron network based hybrid filter, which comprises four basic components : plus-shaped center weighted median filter, cross-shaped center weighted median filter, nine pixels median filter, and a fusion center with fuzzy-neuron network . the proposed filter is able to effectively inherit the merits of the used three filters . the third is a fuzzy reasoning filter based on neural network 第二種是基于模糊神經(jīng)網(wǎng)絡(luò)的混合濾波器,主要濾波器模塊有十字型中心加權(quán)中值濾波器、交叉型中心加權(quán)中值濾波器和9點(diǎn)中值濾波器,信號(hào)經(jīng)過三種濾波器處理后送入一個(gè)訓(xùn)練好的模糊神經(jīng)網(wǎng)絡(luò)進(jìn)行融合處理,得到最終的濾波結(jié)果。
the second is a fuzzy neuron network based hybrid filter, which comprises four basic components : plus-shaped center weighted median filter, cross-shaped center weighted median filter, nine pixels median filter, and a fusion center with fuzzy-neuron network . the proposed filter is able to effectively inherit the merits of the used three filters . the third is a fuzzy reasoning filter based on neural network 第二種是基于模糊神經(jīng)網(wǎng)絡(luò)的混合濾波器,主要濾波器模塊有十字型中心加權(quán)中值濾波器、交叉型中心加權(quán)中值濾波器和9點(diǎn)中值濾波器,信號(hào)經(jīng)過三種濾波器處理后送入一個(gè)訓(xùn)練好的模糊神經(jīng)網(wǎng)絡(luò)進(jìn)行融合處理,得到最終的濾波結(jié)果。
in the pretreatment of these images, the speckle noise model has been improved in this dissertation . on the basis of traditional methods of neighborhood averaging and low-pass filtering, the methods of adaptive histogram enhancement and the improved adaptive weighted median filter have been presented, and the noise has been reduced greatly 在圖像的預(yù)處理的過程中,論文首先改進(jìn)了超聲圖像的speckle噪聲模型,其次在借鑒傳統(tǒng)的方法的基礎(chǔ)上,提出并實(shí)現(xiàn)了自適應(yīng)圖像增強(qiáng)和自適應(yīng)濾波處理方法,較好地抑制了噪聲。