邊緣概率 的英文怎麼說
中文拼音 [biānyuángàilǜ]
邊緣概率
英文
conditional probability- 邊 : 邊Ⅰ名詞1 (幾何圖形上夾成角的直線或圍成多邊形的線段) side; section 2 (邊緣) edge; margin; oute...
- 緣 : Ⅰ名詞1 (緣故) reason 2 (緣分) predestined relationship 3 (邊) edge; fringe; brink Ⅱ動詞(攀...
- 概 : Ⅰ名詞1 (大略) general outline 2 (神氣) manner of carrying and conducting oneself; deportment ...
- 率 : 率名詞(比值) rate; ratio; proportion
- 邊緣 : 1 (沿邊的部分) border; edge; fringe; margin; rim; limb; skirt; verge; brink; periphery 2 (靠近...
- 概率 : [數學] probability; chance概率論 probability theory; theory of chances; 概率曲線 probability curv...
-
An efficient implementation of this framework is presented, for segmenting two motions ( foreground and background ) using two frames. the expectation - maximization algorithm is used to determine the two motions and calculate the label probability for each edge. the best motion labeling for these regions is determined using simulated annealing
針對前景和背景兩種運動分割的情況,本文給出了一種基於貝葉斯分割框架的有效實現,它使用最大期望( em )演算法來估算邊緣的標定概率,並通過模擬退火演算法來完成這些分割區域的最佳運動標定。Then the exisiting algorithms on iris location are studied and the disadvantages are pointed. a new approach based on edge detection, mathematic morphology and probability statistic is put forward. after studing the means of daugman ’ s encode of iris texture and w. w. boles ’ extraction the unique features by the zero - crossings of the wavelet transform, we adopted wavelet multi - resolution analysis that extract the feature
在研究和分析了前人的虹膜定位演算法以及daugman對虹膜紋理的編碼方法、 w . w . boles的小波過零點分析提取虹膜特徵識別演算法的基礎上,研究了基於邊緣檢測和數學形態學以及概率統計等理論的一種新的虹膜定位方法;研究了虹膜圖像的歸一化和圖像增強;研究了基於db4小波的多分辯率分析的虹膜特徵提取演算法;研究了相關系數匹配識別。The thesis also gives the concept of the electromagnetic density of modes ( edom ). the distribution features of edom in the band - edge of 1d photonic crystal are studied according to the computational results. the dispersive properties of 1d photonic crystal are discussed by introducing the concept of complex effective refractive index
闡述了一維光子晶體中電磁模密度的概念,由計算結果分析了電磁模密度在禁帶邊緣的分佈特點;用復有效折射率討論了一維光子晶體的色散特性。We divide the fire sample image into several levels vertically and the synthesis process is carried out by searching candidates on the corresponding levels. textures on the central and boundary parts are synthesized separately, and natural transition between them is achieved by use of markov probability interpolation
火焰邊緣附近的紋理單獨進行合成,把紋理樣本邊緣部分的紋理繪制到目標火焰邊緣,火焰中間部位紋理和邊緣紋理則採用馬爾科夫概率插值進行過渡。Firstly, sp supposed to be generated by point curl source which is the border of dipole layer rather than the line dipole layer in section view, then, curl source scanning function is given, and image is retrieved by probability tomography approach
首先把剖面上偶極層的線分佈產生的場看作是偶極層的邊緣旋度源的點分佈產生的場;然後給出旋度源的掃描函數,用概率成像方法對旋度源進行成像。Two spatially registered images with different focuses are decomposed into several blocks. then, three features reflecting the clear level of every block, i. e., spatial frequency, visibility, and edge, are calculated. finally, artificial neural networks, i. e., multilayer - perceptron, radial - basis function, probabilistic neural network, are used to recognize the clear level of the corresponding blocks to decide which blocks should be used to construct the fusion result
具體實現過程概述如下:首先將兩幅(或多幅)配準圖象進行分塊處理,提取兩幅圖象中對應塊的能反映圖象清晰度的三種特徵,即空間頻率、可見度和邊緣,將特徵歸一化後送入訓練好的神經網路進行識別,根據得到的結果依據「誰清晰誰保留」的原則構成融合的圖象。The results show that ( 1 ) the " prediction & cancellation " method can successfully smooth the reverberation and sharpen edges of the echo, so may detect echoes which power are great than the reverberation background by odb in one channel, ( 2 ) the scaled probabilities method can effectually separate a echo which power is great than the background by 6db, while the reverberation is cancelled dr astically
果。計算結果表明, 「預測一抵消」演算法對混響有平滑作用,對回波則有突出信號邊緣的作用,單通道情況下的最小可檢測信號干擾背景功率比約為odb 。概率凈化演算法在信號干擾背景功率比大於6db的情況下能有效分離回波、抑制混響。Markov chain monte carlo simulation ( mcmc ) was taken to sample the posterior distribution to get the marginal posterior probability function of the parameters, and the statistical quantities such as the mathematic expectation were calculated
通過馬爾科夫鏈蒙特卡羅模擬對后驗分佈進行了采樣,獲得了參數的后驗邊緣概率密度,並在此基礎上獲得了參數的數學期望等統計量。Edges of the image are detected out firstly, labeled according to the motion that they obey then and the areas of the frame between edges are divided into regions. at last, using the bayesian framework presented determines the most likely region labeling and depth ordering with the labeled edges
首先使用經典的canny運算元檢測出一幀圖像的邊緣,然後對其進行運動估計、邊緣和區域標定,再應用最大后驗概率的貝葉斯方法搜索出不同區域的極大似然分割,給出不同運動層的相對深度標定。Marginal probability distribution
邊緣概率分佈分享友人