The original infomax is only applied in the instantaneous mixture and in the single channel blind deconvolution . this thesis applies the idea to blind sources separation in multiple channel convolutive mixture . through simulation , we can show that the algorithm has good performance Infomax算法適用于瞬時(shí)混合情況下的盲分離和單通道盲解卷積問題,本文將infomax算法推廣到多通道卷積混合,對算法進(jìn)行仿真,取得了不錯(cuò)的效果。
One is the bss based on kernel density estimation ( kde ) and genetic algorithm ( ga ) , the other is the blind deconvolution based on high order cross cumulants and ga . without nlf , the performance of separation in both algorithms is independent with the kurtosis of the sources 兩種算法的實(shí)現(xiàn)無需引入非線性函數(shù),因此都與源信號的峭度性質(zhì)無關(guān);另外,選取全局搜索的遺傳算法進(jìn)行尋優(yōu),避免了梯度法搜索的局部性,使得算法均能收斂到問題的全局最優(yōu)解。
The problem discussed in this paper is to separate two ( or more ) input signals from observed signals which are generated by passing input signals through diffrent unknown multi - input multi - output linear systems . it is proved that the input signals can be separated when they are independent identitically distributed ( i . i . d ) signals . a new algorithm for multi - input multi - output blind deconvolution via maximum entropy is presented which needs no information about the input signals and mixing filters 本文研究的問題是從觀察信號中分離出兩個(gè)(或者更多個(gè))輸入信號,其中每一組信號分別通過不同的未知多輸入多輸出線性系統(tǒng).本文證明了當(dāng)輸入信號是兩兩相互獨(dú)立的獨(dú)立同分布信號時(shí)可以分離出輸入信號,并導(dǎo)出了基于最大熵的多輸入多輸出盲解卷新算法.這個(gè)算法不需要任何關(guān)于輸入信號和混合濾波器的先驗(yàn)知識(shí)
Finally , this chapter emphasizes the importance of auxiliary processing in sar imaging , indicates that autofocusing is essentially a problem of blind deconvolution , and that speckle reduction is a problem of imagery restoration . no additional assumption and limitation , the inverse problem on autofocusing or speckle reduction can not be solution 同時(shí),介紹了sar圖像自聚焦和相干斑抑制處理及其發(fā)展現(xiàn)狀,指出自聚焦過程實(shí)際上是一個(gè)盲解卷積問題,而相干斑抑制是一個(gè)圖像復(fù)原問題,對這類逆問題的求解需要附加假設(shè)或限定。
百科解釋
In image processing and applied mathematics, blind deconvolution is a deconvolution technique that permits recovery of the target scene from a single or set of "blurred" images in the presence of a poorly determined or unknown point spread function (PSF).