1 / 88

מערכות ראיה ממוחשבות

מערכות ראיה ממוחשבות. Overview. Image Acquisition. Image Generation. Image Compression. Image Manipulation. Image Analysis. Image Display. Image Perception. האור הנראה. גלים ואור נראה. Human Vision. Perception. Gestalt Principles. Proximity. Gestalt Principles.

Download Presentation

מערכות ראיה ממוחשבות

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. מערכות ראיה ממוחשבות

  2. Overview Image Acquisition Image Generation Image Compression Image Manipulation Image Analysis Image Display Image Perception

  3. האור הנראה

  4. גלים ואור נראה

  5. Human Vision

  6. Perception

  7. Gestalt Principles • Proximity

  8. Gestalt Principles • Proximity • Similarity

  9. Gestalt Principles • Proximity • Similarity • Continuity

  10. Gestalt Principles • Proximity • Similarity • Continuity • Closure

  11. Gestalt Principles • Proximity • Similarity • Continuity • Closure • Common Fate

  12. Gestalt Principles • Proximity • Similarity • Continuity • Closure • Common Fate • Simplicity • Closure • Common Fate

  13. Mona Lisa

  14. Mona Lisa

  15. Digital cameras

  16. 0 10 10 15 50 70 80 0 0 100 120 125 130 130 0 35 100 150 150 80 50 0 15 70 100 10 20 20 0 15 70 0 0 0 15 5 15 50 120 110 130 110 5 10 20 50 50 20 250 PIXEL (picture element) Typically: 0 = black 255 = white Digital Images World Camera Digitizer Digital Image

  17. צילום דיגיטלי

  18. ייצוג תמונה במחשב

  19. Types of images • Gray-scale images I(x,y)  [0..255] • Binary images I(x,y)  {0 , 1} • Color images IR(x,y) IG(x,y) IB(x,y) • HSL images

  20. Grayscale Image x = 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 210 209 204 202 197 247 143 71 64 80 84 54 54 57 58 206 196 203 197 195 210 207 56 63 58 53 53 61 62 51 201 207 192 201 198 213 156 69 65 57 55 52 53 60 50 216 206 211 193 202 207 208 57 69 60 55 77 49 62 61 221 206 211 194 196 197 220 56 63 60 55 46 97 58 106 209 214 224 199 194 193 204 173 64 60 59 51 62 56 48 204 212 213 208 191 190 191 214 60 62 66 76 51 49 55 214 215 215 207 208 180 172 188 69 72 55 49 56 52 56 209 205 214 205 204 196 187 196 86 62 66 87 57 60 48 208 209 205 203 202 186 174 185 149 71 63 55 55 45 56 207 210 211 199 217 194 183 177 209 90 62 64 52 93 52 208 205 209 209 197 194 183 187 187 239 58 68 61 51 56 204 206 203 209 195 203 188 185 183 221 75 61 58 60 60 200 203 199 236 188 197 183 190 183 196 122 63 58 64 66 205 210 202 203 199 197 196 181 173 186 105 62 57 64 63 y =

  21. Binary images H

  22. תמונת RGB R G B

  23. תמונת HSL גָּוֶן רְוָיָה בְּהִירוּת Similarities to the way humans tend to perceive color: What color is it? How vibrant is it? How light or dark is it?

  24. בינריזציה • הפיכת תמונת רמות אפור לבינארית ע”י קביעת ערך סף – Threshold. גוונים מעל ערך הסף נרשמים כלבן, מתחת לערך סף כשחורים. • עבור ערך סף 30:

  25. רזולוציה מרחבית 256*256 512*512 128*128 64*64 32*32 16*16

  26. רזולוציית הצבע Color depth is term describing the number of bits used to represent the color of a single pixel in a bitmapped image( Bits/pixel ) • 1-bit color (21 = 2 colors) • 2-bit color (2² = 4 colors) • 3-bit color (2³ = 8 colors) • 5-bit color (25 = 32 colors) • 6-bit color (26 = 64 colors) • 8-bit color (28 = 256 colors) • 12-bit color (212 = 4096 colors) • 16-bit color (216 = 65536 colors) 256 gray levels (8 bits/pixel) 2 gray levels (1 bit/pixel) BINARY IMAGE 8 gray levels (3 bits/pixel)

  27. במחשב שלך רזולוציית הצבע רזולוציה מרחבית

  28. אחסון התמונה בזיכרון לכל פיקסל מוקצה מרחב זיכרון בהתאם לרזולציית הצבע. גודל התמונה נקבע ע”פ רזולוציית הצבע והרזולוציה המרחבית. דוגמה: תמונה של 64 גווני אפור בגודל 512*512 פיקסלים צורכת 512*512*6/8 = 196,608 [bytes] (אם ניתן לשמור מידע באופן רציף).

  29. Image manipulationsusing histogram

  30. Effects of down-sampling (reducing number of pixels) 128 x 128 64 x 64 32 x 32 16 x 16 8 x 8 4 x 4

  31. Effects of reducing number of gray levels 256 gray levels (8 bits/pixel) 16 gray levels (4 bits/pixel) 8 gray levels (3 bits/pixel) 4 gray levels (2 bits/pixel) 2 gray levels (1 bit/pixel) BINARY IMAGE

  32. דחיסה "Ask not what your country can do for you -- ask what you can do for your country." 17 words, 61 letters, 16 spaces, one dash, one period. "ask" - two times "what" - two times "your" - two times "country" - two times "can" - two times "do" - two times "for" - two times "you" - two times 1 0

  33. JPEG Joint Photographic Experts Group

  34. Advanced Approaches • Area based approach • Image resizing

  35. Continuous probability density function: The Image Histogram Occurrence (# of pixels) Gray Level Histogram = The gray-level distribution: H(k) = #pixels with gray-level k Normalized histogram: Hnorm(k)=H(k)/N (N = # pixels in the image)

  36. The Image Histogram (Cont.) PI(k) 1 k PI(k) 1 0.5 k PI(k) 0.1 k

  37. Image Enhancement • Histogram stretching • Histogram equalization • Histogram specification • etc...

  38. PI(k) 0.1 k 0.5 PI(k) 0.1 k Histogram Stretching

  39. Histogram Equalization k k

  40. Histogram Equalization Original Equalized

  41. Histogram Equalization 3000 3000 2500 2500 2000 2000 1500 1500 1000 1000 500 500 0 0 0 50 100 150 200 250 0 50 100 150 200 250 Original Equalized

  42. Histogram Specification Transforms an image so that its histogram matches that of another image (e.g., for comparing two images of the same scene acquired under different lighting condition) Aa Ab k k

  43. Image manipulation: filtering

  44. שיפור התמונה/סינון חידוד החלקה Luminance Hue Saturation

  45. סינון צבע

  46. תשליל • d(x,y)=255-d(x,y)

  47. הבהרה/החשכה • d(x,y)=d(x,y)+constantif new value > MAX new value =MAX if new value < 0 new value =0 +30 -30

  48. ניגודיות (קונטרסט) • d(x,y)=d(x,y)*+constantif new value > MAX new value =MAX if new value < 0 new value =0 • ככל ש-  גדול יותר הניגודיות עולה

  49. מסננים לניקוי רעשים • ממוצע • חציון • הגבלת ערך

  50. g(x,y) = 1/M S f(n,m) (n,m) inS Spatial Operations Replace center pixel with average/median gray level: (averaging mask; weighted mask; median filter…) Examples of neighborhoods S: S = neighborhood of pixel (x,y) M = number of pixels in neighborhood S e.g., 3 x 3 5 x 5

More Related