invariant processing 中文意思是什麼
-
3 wang l, healey g. using zernike moments for the illumination andgeometry invariant classification of multispectral texture. ieeetrans. image processing
三維紋理的光照不變性識別通過構建zernike矩不變因子矩陣，然後利用奇異值分解方法來計算區分因子解決。 -
Based on the analysis and processing of the digital speckle pattern, the translation and rotation invariant features are discovered, and a one - step feed - forward neural network is creatively proposed which makes it possible to realize the intelligent recognition of interface defects
通過對數學散斑條紋的分析與處理，找出了能代表條紋信息的移位不變與旋轉不變特徵值? ?最大斜率，進而構造一種新的網路模型，即單步前饋式三層網路系統.率先實現了把神經網路系統用在數字散斑無損檢測之中，完成了神經網路系統對粘接界面缺陷的智能辨識 -
Firstly, a new joint filterbank precoders and decision feedback equalizers structure is proposed, and the corresponding optimization result based on the maximal mutual information criterion is derived. secondly, the concept of dt canonical model is proposed, which is very suitable for the task of blind signal processing based on the second - order statistical of the observations. thirdly, the methods of blind equalization and identification of the tv dispersive channels are researched systematically based on the proposed dt canonical model, and a subspace blind identification algorithm of the time - invariant channel matrix is developed
本文創新性的成果在於：提出了預編碼-判決反饋聯合均衡系統結構，並從理論推導得出了對應的最大互信息量最優化設計結果；首次提出了時變色散通道的離散正則模型概念，該模型適宜於利用觀察數據的二階統計量進行盲信號處理；基於離散正則模型對時變色散通道進行了系統的盲均衡和盲辨識方法研究，提出了對時不變通道矩陣的子空間盲辨識演算法；針對誤差傳播效應問題，提出了可以消除誤差傳播效應的兩級盲辨識演算法；提出了基於離散正則模型的直接盲均衡演算法；提出了基於特徵恢復思想的神經網路直接自適應盲均衡演算法。 -
We propose the joint filterbank precoders and decision feedback equalizers structure at first, by which the dispersive channel is equivallent into parallel independent flat fading subchannels such that the diversity gain of the receiver is increased. then we adopt the discrete - time ( dt ) canonical model to convert the problem of blind signal processing of tv dispersive channels into processing the time - invariant multi - channels model blindly, and discuss the problem of blind equalization and identification of tv dispersive channels based on this new model
第一種是採用濾波器組聯合均衡方法將色散通道等價為一組獨立的平坦衰落子通道，以提高接收機的分集增益；另外一種是提出採用離散正則模型將時變色散通道的盲信號處理轉化為時不變多通道模型的盲信號處理，並針對該模型對時變色散通道的盲均衡與盲辨識方法進行了詳細討論。 -
Image processing system is a very important part of mini unmanned helicopter, which mainly dealing with how to detect the object and supply the navigation computer with location information of the object. however, the varied background and the moving of the camera make the image processing become difficult. to solve these problems, this thesis introduces an object detection algorithm based on contour retrieving, template match and hu moments invariant
硬體組成詳細探討了系統結構，並對所採用的ccd攝像機、視頻採集卡等硬體單元作了描述；在軟體設計中，首先對不同操作系統環境下的視頻捕獲做了討論；接著，重點研究了針對機載攝像機拍攝圖像的目標檢測方法，提出並實現了基於模板匹配和不變矩的目標檢測演算法，以及基於機器學習的目標檢測演算法。 -
By comparing the image - preprocessing results of different processing algorithms, an optimized algorithm was decided to ensure satisfying correlation snr and preprocessing rate to be obtained. synthetic discriminant function ( sdf ) filters of the 3 - d targets were designed and the reference filter libs ( rfl ) were constructed to provide high correlation snr. real - time distortion - invariant optical correlation was realized by temporal - spatial multiplexing technique
為了保證opr系統有高的相關信噪比（ snr ）及良好的實時性能，本文對不同圖像預處理演算法的處理性能及效果進行了比較分析，為opr系統選取恰當的圖像預處理演算法提供了依據；將時間多重化技術與空間多重化技術相結合，設計製作了三維目標的可實時刷新的sdf參考濾波器庫，為opr系統提供了高snr的相關輸出，從而實現了opr系統對目標的實時畸變不變光學相關；將人工神經網路（ ann技術）用於相關信號后處理，有效提高了opr系統的識別效率。 -
And the researches of the article have been done as follows : firstly, about the adjustment of rotation, a method, based on susan corner detection algorithm, is presented in the thesis. and the rotated image is rectified exactly by the symmetry of the portrait image and the invariant to rotation of shoulder corner. then the detail of images is preserved by the approximately geometrical processing based on the bicubic interpolation algorithm
具體工作如下:第一，在旋轉調整方面，本文採用了一種基於susan角點檢測的演算法，利用了人像所具有的對稱性以及肩部拐點旋轉不變特性比較準確的實現旋轉校正;並採用了雙三次插值方法對圖像作幾何近似處理，很好的保持原圖像的細節。 -
Therefore, based on the ann correlation signal post - processing technique, we designed a kind of sdf performed in spatial domain, and a two - step recognition technique was introduced to perform real - time distortion - invariant recognition by combining frequency domain filtering of sdf with spatial domain filtering of sdf
為此，本文在ann相關信號后處理技術的基礎上引入了二次識別技術，設計製作了一種空域執行的sdf濾波器，採用頻域sdf濾波與空域sdf濾波相結合的方法，對目標進行實時畸變不變識別。 -
Simulative and experimental results show that this image - processed method can realize the distortion - invariant processing of the scaled and rotated image and improve the recognized capability of optical - electrical hybrid correlator system
最後給出了模擬和實驗的相關結果，結果表明，該方法能實現存在旋轉和比例變化的圖像的畸變不變處理，從而提高了系統的識別能力。 -
Abstract : geometric moment, the simplest moment function whose characteristics are invariant with respect to image plant transformations, finds many applications to object identification, object pose estimation ( image processing, image recognition and computer vision )
文摘:幾何矩是一種最簡單的矩函數，當圖像在平面上變動時它具有不變的特性.在目標識別、目標姿態的計算和其它領域（如圖像處理、圖像識別和計算機視覺等）有廣泛的應用 -
6 ruanaidh j, pun t. rotation, scale, and translation invariant digital image watermarking. signal processing, 1998, 66 : 303 - 317. 7 lin c, wu m, bloom j, cox i, miller m, lui y. rotation, scale, and translation resilient watermarking for images
本文提出了一種數字圖像水印中的新技術，其特點是：在圖像數字水印的檢測中具有較強的識別能力避免了計算逆的對數極坐標仿射ilpm ，保證了嵌入數字水印后圖像的質量同時也避免了窮舉的搜索，減少了計算時間和誤檢率。
分享友人