基于局部熵的量子衍生醫(yī)學(xué)超聲圖像去斑
doi: 10.11999/JEIT140587 cstr: 32379.14.JEIT140587
基金項目:
國家自然科學(xué)基金(61201423, 61375017, 61105010)和智能信息處理與實時工業(yè)系統(tǒng)湖北省重點實驗室開放基金子項目(znss2013B016)資助課題
Quantum-inspired Despeckling of Medical Ultrasound Images Based on Local Entropy
-
摘要: 針對現(xiàn)有醫(yī)學(xué)超聲圖像去斑方法的不足，該文提出一種基于局部熵的量子衍生醫(yī)學(xué)超聲圖像去斑新方法。首先，將對數(shù)變換后的圖像進行雙樹復(fù)小波變換(DTCWT)，并對信號與噪聲分別建模；然后，提取復(fù)小波中子代與父代小波系數(shù)的實部，計算其局部熵并進行歸一化乘積，結(jié)合量子衍生理論得到用來調(diào)整信號與噪聲出現(xiàn)概率的可調(diào)參數(shù)；最后，利用改進的雙變量收縮函數(shù)獲得去斑后的圖像。通過實驗，結(jié)果表明該方法與已有方法相比能夠更有效地濾除醫(yī)學(xué)超聲圖像中的斑點噪聲并保留細節(jié)信息。
-
關(guān)鍵詞:
- 圖像處理 /
- 局部熵 /
- 量子衍生 /
- 雙樹復(fù)小波變換 /
- 雙變量收縮
Abstract: Aiming at the limitation of existing methods for the medical ultrasound images despeckling, a novel quantum-inspired despeckling method based on the local entropy is proposed for the medical ultrasound images. Firstly, the log-transformed images are decomposed by the Dual-tree Complex Wavelet Transform (DTCWT), and the signal and speckle noise are modeled separately. Then, considering the normalized products of the local entropy of the real components extracted from coefficients and their parents, the adjustable parameter is obtained by the quantum inspired theory to adjust the probability of signal and noise. Finally, the modified bivariate shrinkage function is exploited to obtain the despeckled image. The experimental results show that the proposed method can preserve detail information effectively and reduce the speckle noise of medical ultrasound image at the same time. -
計量
- 文章訪問數(shù): 1909
- HTML全文瀏覽量: 196
- PDF下載量: 484
- 被引次數(shù): 0
下載:
