Download as PDF, PPTX
From Image Processing To Computer Vision
- 1.
- 2. Introduction toDigital Images. What is Digital Image Processing? Why study Digital Image Processing? Digital Image Processing Steps. Computer Vision. Outline By Joud Khattab 2
- 3. Why do weneed Digital Images? It help us to see invisible objects due to: Opaqueness (e.g., see through human body). Far distance (e.g., remote sensing). Small size (e.g., light microscopy). Other signals (e.g., seismic) can also be translated into images to facilitate the analysis. A picture is worth a thousand words! Digital Image By Joud Khattab 3
- 4. What isa Digital Image? A digital image is an array of numbers. Digital Image 45 51 88 89 94 100 98 103 104 104 47 146 102 100 118 183 125 101 99 100 34 135 33 32 53 88 73 34 29 30 48 84 39 63 55 25 33 32 31 31 151 43 114 151 152 135 134 129 134 165 208 115 35 33 36 39 39 72 93 176 210 171 39 34 39 40 109 86 77 208 209 175 40 39 37 53 90 39 80 222 200 185 49 38 35 75 72 45 90 197 66 85 39 35 33 52 86 49 49 83 By Joud Khattab 4
- 5. An imageis a two-dimensional function: f(x,y). x and y are the spatial coordinates. f(x,y) is the intensity of the image at the point (x,y). In a digital image, x, y, and f(x,y) are finite, discrete quantities. These elements are called picture elements. Digital Image By Joud Khattab 5
- 6. Digital ImageTypes: 1. Black and White image. 2. Gray scale image. 3. Colored image. Digital Image By Joud Khattab 6
- 7. Digital Image Types Binary Image (0-1) By Joud Khattab 7
- 8. Digital Image Types Gray Scale Image (0-255) By Joud Khattab 8
- 9. Color RGBRepresentation Digital Image Types By Joud Khattab 9
- 10. DIP isthe use of computer algorithms to perform image processing on digital images. Three types of processes from image processing to computer vision: Low-level processes: Input and output are images. such as noise reduction, contrast enhancement, image sharpening. Mid-level processes: input are images. outputs are attributes extracted from those images. such as segmentation. High-level processes: understanding, recognition. What is DIP? By Joud Khattab 10
- 11. Image &video become a major communication media. Image data need to be accessed at a different time or location: Limited storage space and transmission bandwidth. Image data might experience no ideal acquisition, transmission or display Fight against various noise (errors). Image data need to be analyzed automatically Reduce the burden of human operators by teaching a computer to see. Why DIP? By Joud Khattab 11
- 12. Image datamight contain sensitive content Fight against piracy, counterfeit and forgery. Enhance and restore images Remove scratches from an old movie. Improve visibility of tumor in a radiograph. Extract information from images Read the ZIP code on a letter. To produce images with artistic effect. Why DIP? By Joud Khattab 12
- 13. From IP ToCV By Joud Khattab 13
- 14. 1. Image Acquisition. 2.Image Enhancement. 3. Image Restoration. 4. Color Image Processing. 5. Image Compression. 6. Image Segmentation. 7. Representation & Description. 8. Object Recognition. From IP To CV By Joud Khattab 14
- 15. Image Acquisition Tocreate a digital image, we need to convert the continuous sensed data into digital form By Joud Khattab 15
- 16. The principalobjective of enhancement is to process an image so that the result is more suitable than the original image. Image Enhancement techniques are very much problem oriented: A method that is quite useful for enhancing X-ray images may not necessarily be the best approach for enhancing pictures of Mars transmitted by a space probe. Image Enhancement By Joud Khattab 16
- 17. Image Enhancementapproaches fall into two broad categories : Spatial domain methods. Frequency domain methods. Spatial domain processing techniques are based on direct manipulation of pixels in an image. Frequency domain processing techniques are based on modifying the Fourier transform of an image. Image Enhancement By Joud Khattab 17
- 18. Image Enhancement By JoudKhattab 18
- 19. Image restorationis an area that also deals with improving the appearance of an image Enhancement which is subjective. Image Restoration is objective, its techniques tend to be based on mathematical or probabilistic models of image degradation. Enhancement, on the other hand, is based on human subjective preferences regarding what constitutes a "good" enhancement result. Image Restoration By Joud Khattab 19
- 20. Restoration attemptsto reconstruct or recover an image that has been degraded. Thus restoration techniques are oriented toward modeling the degradation and applying the inverse process in order to recover the original image. Image Restoration By Joud Khattab 20
- 21. Image Restoration ImageDe-noising By Joud Khattab 21
- 22. Image Restoration ImageDe-blurring By Joud Khattab 22
- 23. The useof color in image processing is motivated by two principal factors. First, color is a powerful descriptor that often simplifies object identification and extraction from a scene. Second, humans can discern thousands of color shades and intensities, compared to about only two dozen shades of gray. This second factor is particularly important in manual image analysis. Color Image Processing By Joud Khattab 23
- 24. Color Image Processing FlatCorrected By Joud Khattab 24
- 25. Color Image Processing LightCorrected By Joud Khattab 25
- 26. Color Image Processing DarkCorrected By Joud Khattab 26
- 27. Image Compressiondeals with techniques for reducing the storage required to save an image, or the bandwidth required to transmit it. Although storage technology has improved significantly over the past decade, the same cannot be said for transmission capacity. This is true particularly in uses of the Internet. Image Compression is familiar to most users of computers in the form of image file extensions, such as the jpg file extension used in the JPEG image compression standard. Image Compression By Joud Khattab 27
- 28. Image Compressionaddresses the problem of reducing the amount of data required to represent a digital image. The underlying basis of the reduction process is the removal of redundant data. From a mathematical viewpoint, this amounts to transforming a 2-D pixel array into a statistically uncorrelated data set. The transformation is applied to storage of the image. Then the compressed image is decompressed to reconstruct the original image or an approximation of it. Image Compression By Joud Khattab 28
- 29. Image Compression Original: 100KBJPEG: 9KB JPEG: 5KB By Joud Khattab 29
- 30. Segmentation procedurespartition an image into its constituent parts or objects. That is, segmentation should stop when the objects of interest in an application have been isolated. Autonomous segmentation is one of the most difficult tasks in digital image processing. A rugged segmentation procedure brings the process a long way toward successful solution of imaging problems that require objects to be identified individually. On the other hand, weak segmentation algorithms almost always guarantee eventual failure. Image Segmentation By Joud Khattab 30
- 31. 1. In thefirst category, the approach is to partition an image based on abrupt changes in intensity, such as edges in an image. Image Segmentation By Joud Khattab 31
- 32. Image Segmentation 2. Theprincipal approach, in the second category are based on partitioning an image into regions that are similar according to a set of predefined criteria. By Joud Khattab 32
- 33. Representation andDescription almost always follow the output of a segmentation stage, which usually is raw pixel data that represent image to regions, the resulting aggregate of segmented pixels usually is represented and described in a form suitable for further computer processing. Basically, representing a region involves two choices: We can represent the region in terms of it external characteristics (its boundary). We can represent it in terms of its internal characteristics (the pixels comprising the region). Representation & Description By Joud Khattab 33
- 34. Image recognitionwas already good but it's getting way, way better. A research collaboration is producing software that increasingly describes the entire scene portrayed in a picture, not just individual objects. That algorithms attempt to explain what's happening in images in language that actually makes sense. It spits out sentences like: A group of young people playing a game of Frisbee. A person riding a motorcycle on a dirt road. Image Recognition By Joud Khattab 34
- 35. It doesthat using two neural networks: one deals with image recognition, the other with natural language processing. The system uses computer learning, so it's fed a series of captioned images and it gradually learns how sentences relate to what the image shows. It often makes small mistakes and, occasionally, it gets things completely wrong. Clearly there's room for improvement. Image Recognition By Joud Khattab 35
- 36. Image Recognition By JoudKhattab 36
- 37. Image Recognition By JoudKhattab 37
- 38. Image Recognition By JoudKhattab 38
- 39. Image Recognition By JoudKhattab 39
- 40. Face Detectionand Recognition Image Recognition “Sally” By Joud Khattab 40
- 41. Image Recognition FaceDetection and Recognition By Joud Khattab 41
- 42. Image Recognition FaceDetection and Recognition By Joud Khattab 42
- 43. Image Recognition FaceDetection and Recognition By Joud Khattab 43
- 44. Find theblack dot HVS: Visual Illusion By Joud Khattab 44
- 45. What isthis? HVS: Visual Illusion By Joud Khattab 45
- 46. Which linesare straight? HVS: Visual Illusion By Joud Khattab 46
- 47. HVS: Visual Illusion ByJoud Khattab 47
- 48. HVS: Visual Illusion ByJoud Khattab 48
- 49. Computer Vision Makecomputers understand images and video. By Joud Khattab 49
- 50. Scene Completion: ComputerVision By Joud Khattab 50
- 51. Scene Completion: ComputerVision By Joud Khattab 51
- 52. Nearest neighbor scenes from databaseof 2.3 million photos Computer Vision By Joud Khattab 52
- 53. Specific RecognitionTasks Computer Vision By Joud Khattab 53
- 54. 1. Scene Categorizationor Classification: Outdoor, indoor. City, forest, factory. Computer Vision By Joud Khattab 54
- 55. 2. Image Annotation: street, people, building, mountain, tourism, cloudy, brick. Computer Vision By Joud Khattab 55
- 56. Object Detection: find pedestrians. Computer Vision By Joud Khattab 56
- 57. 3. Image Segmentation ComputerVision By Joud Khattab 57
- 58. Vision isreally hard Vision is an amazing feat of natural intelligence Computer Vision By Joud Khattab 58
- 59. Why ComputerVision matters? Computer Vision Safety Health Security Comfort AccessFun By Joud Khattab 59
- 60. Computer Vision Scope ByJoud Khattab 60
- 61. 1. Optical CharacterRecognition (OCR): Technology to convert scanned docs to text. If you have a scanner, it probably came with OCR software. Computer Vision Field By Joud Khattab 61
- 62. 2. Face Detection: Many new digital cameras now detect faces Computer Vision Field By Joud Khattab 62
- 63. Computer Vision Field 3.Smile Detection: By Joud Khattab 63
- 64. 4. Vision-based biometrics: How the Afghan Girl was Identified by Her Iris Patterns Computer Vision Field By Joud Khattab 64
- 65. Computer Vision Field 5.Login without Password: By Joud Khattab 65
- 66. 6. Object Recognition: In mobile phones point and find, Google goggles Computer Vision Field By Joud Khattab 66
- 67. 6. Object Recognition: In supermarkets a smart camera is flush-mounted in the checkout lane, watching for items. When an item is detected and recognized, the cashier verifies the quantity of items that were found under the basket, and continues to close the transaction. Computer Vision Field By Joud Khattab 67
- 68. Computer Vision Field 7.Smart Cars: By Joud Khattab 68
- 69. Computer Vision Field 8.Interactive Games (Kinect): By Joud Khattab 69
- 70. Computer Vision Field 9.Industrial Robots: By Joud Khattab 70
- 71. Computer Vision Field 10.Medical Imaging: By Joud Khattab 71
- 72.
- 73.
- 74.
- 75.
- 76. Thank You By JoudKhattab 76