| 研究生: |
蔡孟頎 Meng-chi Tsai |
|---|---|
| 論文名稱: |
倒傳遞類神經網路於多腳位元件影像對位最佳化之研究 Multi-Pin Optimization of Image Registration using Back Propagation Neural Network |
| 指導教授: |
黃衍任
Yean-ren Hwang |
| 口試委員: | |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 機械工程學系在職專班 Executive Master of Mechanical Engineering |
| 畢業學年度: | 96 |
| 語文別: | 中文 |
| 論文頁數: | 105 |
| 中文關鍵詞: | 倒傳遞類神經網路 、影像對位 、最佳化 |
| 外文關鍵詞: | Registration, Opt, Back Propagation Neural Network |
| 相關次數: | 點閱:13 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
機器視覺應用於影像對位已屬於成熟技術,產業界大多採用商業化套裝模組,由軟體或硬體供應商出售專用擷取設備或賣出軟體程式碼與資料庫資及輔助開發服務,廠商各自擁有專門代理權或影像技術,由於處理影像基礎原理存有差異,以致不同軟體系統特性各有優劣,整體來說商業化系統使用者僅就業者所提供之限制功能範圍內開發銜接程式碼,並無從知悉系統核心,且軟體本身屬於線性結構,不能針對因多重影像物件組合造成非線性狀態求最佳化對位補正位置進行處理。本研究收集類神經相關應用文獻,選擇倒傳遞類神經網路進行多腳位元件影像對位最佳化找尋,分析理論原理後將其編寫為程式碼導入自製影像對位系統,並以隨機拍攝三腳位電子元件影像二百張,涵蓋90%腳位座落之整體與個別腳位座標,以平均差統計較佳之學習速率0.1與慣性因子0.1,以此組合教導系統學習最佳化,經過2000次學習與收斂,得到元件樣本影像對位最佳化非線性模擬函數,此函數即網路由經驗訓練而得之加權值與偏權值(閥值),倒傳遞類神經網路將無法量化與公式化處理的問題以非線性曲線表示,自此不論輸入允許範圍內之元件座標為何,網路皆得以直接進行正向傳遞將結果輸出。廣意言之,倒傳遞類神經網路為一經驗值策略輔助系統。
Image registration are skillful of machine vision, the commerce service package was adopted as the drawing of equipment most of the time , software source code library and database or image capture hardware and research assistant sold by professional vendor , they have unique authority of agency or own vision technique, there are differences as the basis principles of image processing, characteristics of different software systems that have merit and demerit , the system are linear programming could not to process non-linear problem of multi-pin interlace location optimizated .This research method combine Back Propagation Neural Network to image alignment software we design for multi-pin alignment optimization and capture two hundred pieces of sample image with random , that could be mantle over 90% whole and each of pin location , using MSE to find the best speed learn rate 0.1 and momentum coefficient 0.1 . During 2000 times training for BPNN , network showing convergence , than promote bias and weight , these could be drawing curve approach truely , the cruve solve non-linear phenomenon , input any grid in range the Neural network running forward counting and directly to output result with optimization .
[1] 連國珍,“ 數位影像處理”,儒林圖書有限公司,台北,2001.
[2] 葉怡成,“ 類神經網路模式應用與實作”,儒林圖書有限公司,台北,2003。
[3] 周政宏,“ 神經網路-理論與實務”,松崗電腦圖書資料股份有限公司,台北,1995。
[4] 張斐章、張麗秋、黃浩倫,“ 類神經網路理論與實務”,東華書局,台北,2003。
[5] Tonny.Espeset, “ Kick ass Java Programming”,The Coriolis Group,Inc.1996.
[6] C.A.Lindley, “ Practical image processing in C”,Big Apple Tuttle-Mori,1994.
[7] R.C.Gonzales,R.E.Woods, “ Digital image processing”,Addison-Wesley,1992.
[8] W.S.McCulloch,W.Pitts, “ A logical calculus of the ideas immanent in nervous activity”,Bulletin of Mathematical Biophysics,Vol.5 pp.115-133,1943.
[9] F.Rosenblatt, “ the perception:Aprobabilistic model for information storage and organization in the brain”,Psychological Review,Vol.65,pp.386-408,1958.
[10] J.J.Hopfielf,D.W.Tank, “ Neural Compotation of Decisions in Optimization Problem”,Biological Cybernetiv,Vol.33,pp.533-543,1986.
[11] David.E.Rumelhart,J.L.McClelland, “ Parallel Distribute processing:Exploration in the Microstructure of Cognition”,Cambridge,MA:MIT Press Cambridge,MA,USA,Vol.1,1986.
[12] M.D.Powell, “ Radial Basis functions for multivariable interpolation:A review”,In Algorithms for Approximation.Oxford University Press,pp.143-167,1987.
[13] R.A.Jacobs, “ Increased Rates of Convergence Through Learning Rate Adaptation”,Neural Network,Vol.1,pp.295-307.
[14] N.Baba, “ A New Approach for Finding the Global Minimum of Error Function of Neural Networks”,Neural Network,Vol.2,pp.367-373.
[15] D.Nguyen,B.Widrow, “ Improving the Learning Speed of 2-Layer Neural Network by Choosing Initial Values of the Adaptive Weights”,Proc.of IJCNN,San Diego,California,Vol.3,pp.22-26.
[16] Yolanda.M.Pirez,Dilip.Sarkar, “ Back-Propagation Algorithm with Controlled Oscillation of Weights”,Neural Networks,IEEE International Conference on,Vol.1,pp.21-26.
[17] F.Stager,M.Agarwal, “ Three Methods to Speed Up the Training of Feedforward and Feedback Perceptrons”,Neural Networks,Vol.10,no.8,pp.1435-1443,1997.
[18] J.Liang,X.Wen,S.Li, “ Optimum Cutting Parameter Selection Strategy Based on Neural Network and Artificial Intelligence”SPIE,Vol.2620,pp.458-462,1995.
[19] E.Nikolaids,M.Zhu, “ Design of Automotive Joints:Using Neural Networks and Optmization To Phsical Design Parameters”,Computer and Structure,Vol.60,No.6,pp.989-1001,1996.
[20] L.Berk,P.Hajela, “ Applications of Artificial Neural Nets in Structural Mechanics”,Structural Optimization,Vol.4,pp.90- 98,1992.
[21] G.C.Huang,S.C.Lin, “ A Stability Approach to Fuzzy Control Design for Nonlinear System”,Fuzzy Set and System.,Vol.48,Issue.3,pp.279-287,1992.
[22] C.Y.Chang,et al., “ Using a two-layer competitive hopfield neural network for semiconductor wafer defect detection. Paper presented”,International Conference on Automation Science and Engineering, Edmonton, Canada,2005.
[23] David.E.Goldberg, “ Genetic algorithms in Search Optimization & Machine learning”, Addison-Wesley Publishing Co,1989.