摘要

區域性二元化圖形(Local Binary Pattern, LBP)，為傳統的材質分析方法，但其統計直方圖(Histogram)資料不隨影像灰階值改變和影像旋轉影響的特性使此方法成為一理想的影像辨識演算法，並陸續發展出不同的LBP運算子，所以使其成為近年來被使用在影像辨識的演算法之ㄧ。
一般的影像處理系統在進行影像定位或辨識之前，會先將影像資料透過特徵擷取處理得到可用的特徵資料，此即所謂的前端運算。通常前端運算都會耗費大量的時間及系統資源，故本篇論文主要是提出一硬體架構來輔助影像處理的嵌入式系統，使系統在使用LBP演算法時能夠更快速的得到LBP的直方圖特徵資料而做下一步的影像辨識或定位，並使大部分的嵌入式系統資源可以用在後端的處理上。
本論文規劃的系統主要包含記憶體控制單元及LBP運算單元兩大部分，電路設計每10個clock可以完成一筆LBP資料的運算，利用Design Compiler進行電路合成，電路最高工作頻率可達500MHZ，經由軟體程式及FPGA測試板的雙重驗證後，論文所提出之硬體架構確實可以提供正確的LBP統計資料?後端相關系統進行後續的處理，達到影像處理的目的。

關鍵詞：區域性二元化圖形、材質分析、影像處理。

Abstract

The Local Binary Pattern (LBP) algorithm is one of the major traditional texture analysis methods. It is both rotation and gray-scale invariant. These characteristics make it an ideal method for image recognition.
In most image processing systems, certain features are often extracted first from the image before performing any further analysis. This is called front-end processing. For many embedded image processing systems, the front-end processing is both very time-consuming and resource-demanding. To facilitate embedded systems with limited resources to process the front-end data more efficiently, we have designed and implemented a digital circuit for the computation of LBP statistical values. Our design consists of two major parts: an LBP computing unit and a memory controller. It outputs a set of LBP data every ten clock cycles. The circuit synthesized by Design Compiler operates at a maximum clock rate of 500 MHz. We verify the correctness of the circuit by running simulations with ModelSim. The results, also confirmed by an FPGA verification board, show that our design calculates the LBP values accurately.

Keywords: Local binary pattern, texture analysis, image processing.

目錄

摘要…………………………………………………………………………Ⅰ
Abstract……………………………………………………………………Ⅱ
目錄…………………………………………………………………………Ⅲ
圖目錄………………………………………………………………………Ⅴ
表目錄………………………………………………………………………Ⅶ
第一章 緒論…………………………………………………………………1
1.1 前言……………………………………………………………………1
1.2 研究動機與目的………………………………………………………2
1.3 驗證方法………………………………………………………………2
1.4 論文架構………………………………………………………………3
第二章 材質分析……………………………………………………………4
2.1人類視覺和材質分析演算法……………………………………………7
2.2 材質描述方法…………………………………………………………9
2.3 材質分析的應用………………………………………………………11
第三章 LBP演算法介紹……………………………………………………16
3.1 發展歷史………………………………………………………………16
3.2 LBP演算法……………………………………………………………17
3.2.1 基礎LBP演算法介紹…………………………………18
3.2.2 進階LBP演算法介紹…………………………………23
3.2.3 LBP統計資料判別方法………………………………28
第四章 硬體電路介紹……………………………………………………31
4.1 硬體架構………………………………………………………31
4.1.1 記憶體控制模組介紹…………………………………32
4.1.2 LBP運算模組介紹……………………………………38
4.2 LBP硬體系統介紹……………………………………………42
第五章 實驗結果…………………………………………………………43
5.1 硬體描述語言程式模擬結果………………………………44
5.1.1 記憶體控制器部份…………………………………45
5.1.2 LBP運算模組部份…………………………………47
5.2 FPGA驗證部份……………………………………………51
5.3效能評估……………………………………………………54
第六章 結論與未來展望…………………………………………………55
參考文獻…………………………………………………………………56

[1]A. Hadid, M. Pietikainen, and T. Ahonen, “A Discriminative Feature Space for Detecting and Recognizing Faces,” Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp.797-804, June 2004.
[2]T. Ahonen, A. Hadid, and M. Pietikainen, “Face Recognition with Local Binary Patterns,” Proc. 8th European Conference on Computer Vision, pp. 469-481, 2004.
[3]T. Ahonen, A. Hadid, and M. Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, issue 12, 2037-2041, Dec. 2006.
[4]M. Laiho, O. Lahdenoja, and A. Paasio, “Dedicated Hardware for Parallel Extraction of Local Binary Pattern Feature Vectors,” 9th IEEE International Workshop on Cellular Neural Networks and Their Applications, pp.27-30, May 2005.
[5]O. Lahdenoja, J. Maunu, M. Laiho, and A. Paasio, “A Massively Parallel Algorithm for Local Binary Pattern Based Face Recognition,” Proc. IEEE International Symposium on Circuits and Systems, pp. 3730-3733, May. 2006
[6]M. Petrou and P. G. Sevilla, Image Processing Dealing with Texture, John Wiley & Sons, 2006.
[7]M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, Cengage-Learning, 2008.
[8]C.H. Chen, L.F. Pau, P.S.P. Wang, The Handbook of Pattern Recognition and Computer Vision, World Scientific Publishing, 1998.
[9]R. Sutton and E. L. Hall, “Texture Measures for Automatic Classification of Pulmonary Disease,” IEEE Trans. Computers, vol. C-21, pp. 667-676, July 1972.
[10]H. Harms, U. Gunzer, and H. M. Aus, “Combined Local Color and Texture Analysis of Stained Cells,” Computer Vision, Graphics, and Image Processing, vol. 33, pp.364-376, Mar. 1986.
[11]賴鼎宇,“使用嵌入式Linux發展電腦視覺系統之研究”, 義守大學資訊工程研究所碩士論文,民國95年1月
[12]P. Dewaele, P.V. Gool, and A. Oosterlinck, “Texture Inspection with Self-Adaptive Convolution Filters,” Proc. 9th International Conference on Pattern Recognition, vol.1, pp. 56-60, Nov. 1988.
[13]D. Chetverikov, “Detecting Defects in Texture,” Proc. 9th International Conference on Pattern Recognition, vol.1, pp. 61-63, Nov. 1988.
[14]R.W. Conners, C.W. McMillin, K. Lin, and R. E. Vasquez-Espinosa, “Identifying and Locating Surface Defects in Wood: Part of an Automated Lumber Processing System,” IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-5（6）, pp. 573-583, 1983.
[15]R.M. Haralick, “Statistical and Structural Approaches to Texture,” Proc. IEEE, vol.67, issue 5, pp.786-804, May 1979.
[16]L. Kirvida and G. Johnson, “Automatic interpretation of ERTS data for forest management,” NASA Goddard Space Flight Center Symposium. on Significant Results, ERTS-1, Vol. 1, Sect. A and B, pp. 1075-1082, 1973
[17]T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, issue 7, pp. 971-987, July 2002.
[18]林清山,心理與教育統計學, pp.277-309,東華書局,1992
[19]Integrated Silicon Solution, Inc., “IS63LV1024 IS63LV1024L 128K x 8 High-speed CMOS SRAM ”, http://www.issi.com/index.html
[20]http://www.ee.oulu.fi/mvg/page/downloads
[21]Centers for Disease Control and Prevention, http://www.cdc.gov/
[22]F. Tajeripour, E. Kabir, and A. Sheikhi, “Fabric Detection Using Modified Local Binary Patterns,” EURASIP Journal Advances in Signal Processing, vol. 2008, Article ID 783898, 12 pages.