1 / 15

Se- Hoon Park

Backgrounds for feature extraction. Se- Hoon Park. 26 th August 2014. Table of contents. Edge detection -> Canny edge detector A combined corner and edge detector . C Harris , M Stephens - Alvey vision conference, 1988 (citation : 9984)

wyome
Download Presentation

Se- Hoon Park

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. Backgrounds for feature extraction Se-Hoon Park 26th August 2014

  2. Table of contents • Edge detection -> Canny edge detector • A combined corner and edge detector.C Harris, M Stephens - Alvey vision conference, 1988 (citation : 9984) • Corner detection -> Harris corner detector • A computational approach to edge detection • J Canny - Pattern Analysis and Machine Intelligence, IEEE, 1986 (citation:19512)

  3. Edge detection -> Canny edge detector • Corner detection -> Harris corner detector

  4. Canny edge ● ○ ○ ○ ○ Sobel filtering X , Y = *I, = * I I : intensity of image : :

  5. Canny edge ● ● ○ ○ ○ Sobel filtering Magnitude of gradient :

  6. Canny edge ● ● ● ○ ○ Sobel filtering

  7. Canny edge ● ●● ● ○ Direction of gradient y x Non – maximum suppression Magnitude of gradient Direction of gradient Suppression 수행 후 Suppression 수행 전

  8. Canny edge ● ●● ● ● Double thresholding Strong edge noise Weak edge Double threshold 수행 전 Double threshold 수행 후 Edge tracking by hysteresis

  9. Edge detection -> Canny edge detector • Corner detection -> Harris corner detector

  10. Harris corner ● ○ ○ ○ ○ Canny edge ● ●● ● ● What is corner? “flat” no change in all direction “edge” no change along the edge direction “corner” significant change in all directions

  11. Harris corner ●● ○ ○ ○ Canny edge ● ●● ● ● , : x, y 방향 gradient , 1차 테일러 근사 , ] ,

  12. Harris corner ●●● ○ ○ Canny edge ● ●● ● ● : eigenvalues of Harris corner detection

  13. Harris corner ●●● ● ○ Canny edge ● ●● ● ● properties Rotation invariance Partial intensity invariance

  14. Harris corner ●●● ● ● Canny edge ● ●● ● ● Problem Non-invariant image scale ● Lowe, D.G., "Distinctive image features from scale-invariant keypoints", IJCV 2004.1

  15. Harris corner ●●● ● ● Canny edge ● ●● ● ● Scale space Scale invariance 영상의 특징 점이 scale 축을 따라서 반복 검출될 경우, scale invariant한 특징 점이 된다. SIFT의 경우 스케일 축을 따라서도 Laplacian이 극대, 극소가 되는 점들이 scale invariant 특징 점.

More Related