450 likes | 713 Views
Computer Vision – Overview. Hanyang University Jong-Il Park. Digital Image Processing. Sampling & Quantization Image Enhancement Image Restoration Image Coding( or Image Data Compression) Image Understanding( or Computer Vision). Image formation. Sampling & Quantization.
E N D
Computer Vision – Overview Hanyang University Jong-Il Park
Digital Image Processing • Sampling & Quantization • Image Enhancement • Image Restoration • Image Coding( or Image Data Compression) • Image Understanding( or Computer Vision)
Subsampling & aliasing aliasing
Sub-Nyquist sampling Circular Zone Plate H ½, v ½ Org. aliasing
Image Enhancement • Goal • to accentuate certain image features for subsequent analysis or for image display Input : image Output : image
Image Enhancement • Techniques • contrast/edge enhancement • histogram equalization • pseudo coloring • noise filtering • edge sharpening • smoothing • Applications • processing of remote-sensed image via satellite • radar, SAR, Ultrasonic image processing
Image Restoration • Goal • to remove or minimize known/unknown degradations in image
Blur model estimate or recover f(x,y) from g(x,y) deconvolution problem
Image Restoration • Techniques • deblurring • noise filtering • correction of geometric distortion • inverse filtering • Least mean square(Wiener) filtering • Applications • remote-sensed image processing • noise cancellation
Image Data Compression • Goal • to reduce the amount of data required to represent images Input : image Output : bit-stream data “010100101100110101001 . . . .” moving image: 1,0001,0008(bits/sample)330 frame/sec = 72107 bit/sec
2-D Image Compression, JPEG • Image quality by JPEG (a) 27.9 dB at 0.125 bpp (b) 31.5 dB at 0.25 bpp (c) 34.8 dB at 0.5 bpp
3D Mesh Compression Original ‘Bunny’ 12 bpc 10 bpc 8 bpc
Image Data Compression • Techniques • Error-free coding( or lossless coding) • Lossy compression • Image Compression Standard • JPEG, H.261, H.263, MPEG-1,2,4 etc • Applications • Transmission • teleconferencing ,TV system, remote sensing via satellite • Storage • VOD(video on demand), Video CD, DVD(digital video disk), medical imaging, educational and business documents
MPEG • MPEG-1 • 1992 • Video CD • Includes Audio Layer III (MP3) • MPEG-4 • Part 1: 1998 • Part 2: 1999 (addition still under development) • Audio visual object • Mobile telephony (IMT-2000) • Interactivity • Content –Based Interactivity
MPEG-7 • 2001 (addition still under development) • Content Description Interface • Metadata language and schemes for search & retrieval
Content-based Image Retrieval • Image retrieval • Find similar images from image database • Used features • Color • Texture • Shape Query Retrieved
Query Image Retrieval Results Image Data List Texture Option
Content-based Video Retrieval • Video retrieval • Scene change detection and key frame extraction • Extracted key frame from a movie clip
Content-based Video Retrieval • Video retrieval • Automatic indexing • Index from a news sequence
Media Framework Tech. • MPEG-21 • All electronic creation, delivery and trade of digital multimedia content • Transparent usage of various content types on various devices connected through various network
Watermarking • the process of embedding information into a host signal without changing perceived characteristics of the host
Image Understanding • Goal • to interpret or describe the meaning contained in the image Input : image Output : interpretation(description) “KAISION” “circle”
Stereo Vision (disparity map) 기준 영상(좌) 기준 영상(우) 구한 변위 지도(검은색: 가리워짐) 변위 참 값(붉은색: 가리워짐)
Model image Model Input scene Scene Matching (1) Scene matching result
Model Scene matching result Input image Edge image Scene Matching (2)
Fruit Classifier • Apple • Orange • Water Mellon –크기, 반지름
Segmentation (a) Aerial Original Image (b) Segmented Image
There are a lot of interesting topics to explore in image processing and computer vision.