圖像梯形退化校正的研究與實現(xiàn)

通信工程論文編號:TX402  論文字數(shù):12616,頁數(shù):34

目錄
摘要 I
ABSTRACT II
緒論 1
第一章 程序開發(fā)工具Microsoft Visual C++6.0 3
1.1  Visual C++ 6．0 簡介 3
1.2  Visual C++ 6．0的特點 3
1.3  Visual C++ 6．0的開發(fā)環(huán)境 4
第二章 數(shù)字圖像處理背景與數(shù)字化實現(xiàn) 6
2.1 數(shù)字圖像處理背景 6
2.2 數(shù)字圖像的數(shù)字化實現(xiàn) 7
第三章 幾何畸變和幾何校正 12
3.1 幾何畸變產(chǎn)生原因 12
3.2 梯形畸變模型 13
3.5 幾何畸變校正模型 14
3.2 空間坐標變換方法歸納 14
3.4 數(shù)字圖像灰度插值 16
3.4.1 數(shù)字圖像灰度插值的定義 16
3.4.2 最近鄰插值法 17
3.4.3 雙線性插值算法 18
3.4.4 三次立方卷積插值算法 19
3.4.5 三種校正方法的比較 21
第四章 程序?qū)崿F(xiàn)和實驗測試 22
4.1 灰度插值方法實現(xiàn)程序 22
4.2 程序?qū)嶒灉y試 24
第五章 全文總結(jié)與展望 27
致謝 30
參考文獻 31

摘要

 圖像幾何失真校正是數(shù)字圖像處理中的一個重要內(nèi)容。對于存在著幾何畸變和失真的圖像進行檢測和數(shù)據(jù)分析前，有必要消除這些失真。梯形失真的校正在現(xiàn)實運用中有較高的實用價值，例如遙感圖像處理，車牌檢測，模擬三維飛行模塊。這些都已經(jīng)在現(xiàn)實生活、訓(xùn)練中有了應(yīng)用。本次畢業(yè)設(shè)計以Visual C++6.0為工作平臺，通過編寫程序來實現(xiàn)相應(yīng)算法。處理過程預(yù)設(shè)了一副原圖像，該圖像通過退化算法得到當前圖像的坐標點及灰度值，并返回該灰度值到預(yù)設(shè)圖像相應(yīng)的坐標點上，從而實現(xiàn)了圖像的還原。在計算灰度值時采用了最近鄰法和雙線性插值法。驗證了梯形退化和校正模型的正確性和可行性。通過實驗分析，最近鄰法的校正計算速度及復(fù)雜度上要優(yōu)于雙線性插值法，但是校正后圖像質(zhì)量還是雙線性插值法好。
關(guān)鍵詞：梯形失真；幾何校正，坐標變換，灰度插值，雙線性插值法
   
ABSTRACT

 Image geometric distortion correction is an important content of digital image processing. It is necessary for the image with geometric distortion and distortion to eliminate these distortions before being carried on detection and data analysis. The correction of the trapezoidal distortion has a higher practical value in the reality using, such as remote sensing image processing, license plate detection, 3D flight simulation module. These have applied in the real life and the training activities. The graduates design takes Visual C++6.0 as the working platform through the compiling procedure to achieve the corresponding algorithm. The treating processes have supposed an original map picture in advance. This picture can obtain the seat punctuation and the gray value of the current picture through the degenerated algorithm, and return to the gray value to the corresponding seat punctuation of the picture supposed in advance. Thus we can realize the picture return to original state. The procedure used the nearest neighbor and bilinear interpolation methods to compute gray value. It has confirmed accuracy and the feasibility of the trapezoid degeneration and the adjustment model. Through analyzing the test, we can know that the nearest neighbor method of correction calculation is faster and less complex than bilinear interpolation. But bilinear interpolation has batter quality than nearest neighbor method after the image having been corrected. 
 
Keywords : Trapezoidal distortion, Geometric Rectification， Coordinate Transformation，   Gray interpolation，   Bilinear interpolation