Presentation is loading. Please wait.

Presentation is loading. Please wait.

0 1.1. Motivation 1.2. Why is Computer Vision Difficult? 1.3. Image Representation and Image Analysis 1.4. Summary Chapter 1 - Introduction.

Similar presentations


Presentation on theme: "0 1.1. Motivation 1.2. Why is Computer Vision Difficult? 1.3. Image Representation and Image Analysis 1.4. Summary Chapter 1 - Introduction."— Presentation transcript:

1 0 1.1. Motivation 1.2. Why is Computer Vision Difficult? 1.3. Image Representation and Image Analysis 1.4. Summary Chapter 1 - Introduction

2 1 1.1. Motivation An image is worth thousands of words Objectives of image processing: 1. Human perception 2. Machine interpretation Two principal roles of images: 1.Communication 2. Scene understanding

3 2 Human Perception BeforeAfter

4 Before 3

5 After 4

6 Before 5

7 After 6

8 For you,...not much can be done! 7

9 Machine Interpretation A Z 1 0 Optical Character Recognition (OCR) 8

10 9

11 10

12 11 License Number Identification Location Recognition GG4025 Input image Form Analysis Documentation

13 12 Model-based Object Recognition

14 13 Object Models

15 14 Model Matching

16 15 (ii) What are their spatial relationships? (i)How many people, adults, and children are there in the picture? (v) What are they doing? (iii) Who are they? (iv) Where are they? Image Understanding

17 16 Machine interpretation of images requires diverse methods of Mathematical Engineering Biological disciplines Psycho-physiological Intelligent Scientific

18 17 Low-level processing: e.g., noise removal, deblurring, and contrast enhancement Mid-level processing: e.g., edge, region, corner, and texture detections High-level processing: e.g., object, function, relationship, event, and activity recognitions Image Analysis ===== CV I P

19 18 1.2. Why is Computer Vision Difficult? (1) Loss of information in 3D  2D

20 19 (2) Local window vs. global view

21 20 (3) Sequential vs. parallel processing

22 21 Sequential processing (5) Noise (4) Too much data

23 22 Image F(x,y): a 2-D continuous function 1.3. Image Representation Origin Scene G(x,y,z): a 3-D continuous function Discrete image D(r,c): a 2-D discrete function N M ○ M × N : Image size Digital image I(r,c): an array of discrete values

24 Dynamic range (or color depth) : number of bits for a single pixel (a) 1 - bit: black and white (binary image) (b) 8 - bit: gray-scale (gray scale image) (c) 24 - bit: true color (color image) 23

25 An image file is a binary file, which can be dump. Physically, 24

26 Types of file formats: BMP : Microsoft Bitmap formal JPEG : Joint Photographics Experts Group PNG : Portable Network Graphics TIFF : Tagged Image File Format GIF : Graphics Interchange Format HDF : Hierarchical Data Format PCX : PC Paintbrush XWD : X Window Dump ICO : ICOns CUR : CURsor 25

27 (a) Header: Characteristics of image Image size Color map Compression method (b) Image data: Pixel values, Index values An image file contains 26

28 Example: BMP header 27

29 Example: 28

30 C/C++ Program http://www.cs.ucsd.edu/classes/sp03/cse190-b/hw1/ Read header information 29

31 Read image data 30

32 GIF header 31

33 Example: 32

34 TIFF header 33

35 34 Summary Two major roles of images played: (i) Communication, (ii) scene understanding Two main objectives of IP: (i) Human perception, (ii) machine interpretation Three levels of IP: Low-, mid-, and high- levels (1) Loss of information in 3D  2D (2) Noise (3) Too much data (4) Local window vs. global view (5) Sequential vs. parallel processing Difficulties of computer vision:

36 35 Summary Two main objectives of IP: Human perception, Machine interpretation Machine interpretation

37 36 Three levels of IP: Low-, mid-, and high- levels (1) Loss of information in 3D  2D (2) Noise (3) Too much data (4) Local window vs. global view (5) Sequential vs. parallel processing Dynamic range (or color depth) : # bits per pixel Difficulties of computer vision:

38 OpenCV && Matlab 37

39 Opencv 安裝 通常使用 Visual studio C++ 搭配 openCV 也可以使用 Dev C++ 搭配 (http://yester-place.blogspot.tw/2008/06/http://yester-place.blogspot.tw/2008/06/ dev-copencv.html) 38

40 Visual C++ 2010 Express Visual express 下載 http://www.visualstudio.com/downloads/download- visual-studio-vs 39

41 OpenCV 安裝 http://opencv.org/downloads.html 40

42 安裝 OpenCV 這邊以 OpenCV 246 為例 將 opencv 解壓縮至 C 槽 (C:\OpenCV246) 設定環境變數 ( 我的電腦右鍵 > 內容 > 進階系 統設定 > 環境變數 在環境變數 PATH 加上 C:\OpenCV246\build; C:\OpenCV246\build\x86\vc10\bin; 切記 !!! 設定完環 境變數要 重新開機 才會生效 !!! 41

43 設定 Visual C++ 42

44 對專案點右鍵 > 屬性 VC++ 目錄 > Include 目錄加上 –C:\OpenCV246\build\include –C:\OpenCV246\build\include\opencv 程式庫目錄加上 –C:\OpenCV246\build\x86\vc10\lib 43

45 連結器 > 輸入 > 其他相依性 > –opencv_core246d.lib –opencv_calib3d246d.lib –opencv_contrib246d.lib –opencv_features2d246d.lib –opencv_highgui246d.lib –opencv_imgproc246d.lib –opencv_ml246d.lib –opencv_objdetect246d.lib –opencv_video246d.lib –opencv_videostab246d.lib –opencv_nonfree246d.lib –opencv_flann246d.lib 44

46 OpenCV 範例 - 讀取圖片 (Mat) Include 函式庫 imread( 檔案名稱, 讀取參數 ) 參數 ”1” 為彩色影像 imshow( 視窗名稱, 變數名稱 ) imwrite( 檔案名稱, 變數名稱 ) 45

47 OpenCV 範例 - 讀取圖片 (Iplimage) cvLoadImage( 檔案名稱, 參數 ) cvNamedWindow( 視窗名稱, 參數 ) 參數 1 為視窗自動縮放大小 cvShowImage( 視窗名稱, 變數名稱 ) cvSaveImage( 檔案名稱, 變數名稱 ) 46

48 OpenCV 函式 讀取圖片 –Imread() –cvLoadImage() 輸出圖片 –Imwrite() –cvSaveImage() 讀取影片 –VideoCapture 改變圖片大小 –cvResize() 其餘的可以上 OpenCV 官網查詢 –http://docs.opencv.org/modules/refman.html 47

49 Matlab 軟體安裝 師大校園軟體服務 (http://www.itc.ntnu.edu.tw/sw/index.html)http://www.itc.ntnu.edu.tw/sw/index.html 48

50 Matlab 安裝 解開壓縮檔後,內有一份安裝說明文件, 照著文件步驟安裝即可 記得啟動時必須要用校內 IP 49

51 Matlab 讀圖範例 讀取圖片 >> A = imread('C:\lena.bmp'); 顯示圖片 >> imshow(A); 輸出圖片 >> imwrite(A,'C:\test.bmp'); 50

52 Matlab 好處 方便監控變數狀態 畫圖時很方便 51


Download ppt "0 1.1. Motivation 1.2. Why is Computer Vision Difficult? 1.3. Image Representation and Image Analysis 1.4. Summary Chapter 1 - Introduction."

Similar presentations


Ads by Google