Kỹ thuật làm mảnh đường biên ảnh

Thinning Algorithms Thick images Thin images Color images Character Recognition (OCR) Thinning: from many pixels width to Thinning: from many pixels width to just one just one • Much work has been done on the thinning of ``thick'' binary images, • where attempts are made to reduce shape outlines which are many pixels thick to outlines which are only one pixel thick. • Skeletonization Thinning of thick binary images Thinning of thick binary images Thinning using Thinning using Zhang and Suen algorithm [1984].) results of the first pass results of the second pass final results Point just removed 8 7 26 25 (b) is slightly increased image Example of Thinning algorithm from Example of Thinning algorithm from Zhang and Suen 1984 Zhang and Suen 1984 Example 1 of Rules for Thinning Example 1 of Rules for Thinning Algorithm Algorithm Don’t care Old one New and old one Rule 1 Rule 2 Rule 3 Rule 4 Rule 1 All four rules can be illustrated like that Applying thinning to fault Applying thinning to fault detection in PCB detection in PCB All lines are thinned to one pixel width Now you can check connectivity Thinning Algorithm Thinning Algorithm • Thinning algorithm is sensitive to corrupted image segments image Correct background shows desired shape of letter T Noise leads to lack of connectivity. BAD Thinning Thinning applied after applied after Edge Detection Edge Detection Rules of binary thinning Rules of binary thinning • We will present the rules used for the ``binary thinning'' which is applied to the edge images (found using the edge detector). • The rules are simple and quick to carry out, requiring only one pass through the image. Thinning of thin binary images Thinning of thin binary images The SUSAN Thinning Algorithm The SUSAN Thinning Algorithm • It follows a few simple rules – remove spurious or unwanted edge points – add in edge points where they should be reported but have not been. • The rules fall into three categories; – removing spurious or unwanted edge points – adding new edge points – shifting edge points to new positions. • Note that the new edge points will only be created if the edge response allows this. These all can be called “local improving” rules . outlines which are only one pixel thick. • Skeletonization Thinning of thick binary images Thinning of thick binary images Thinning using Thinning using Zhang and Suen algorithm [1984].) results. image Example of Thinning algorithm from Example of Thinning algorithm from Zhang and Suen 1984 Zhang and Suen 1984 Example 1 of Rules for Thinning Example 1 of Rules for Thinning Algorithm Algorithm Don’t. Applying thinning to fault Applying thinning to fault detection in PCB detection in PCB All lines are thinned to one pixel width Now you can check connectivity Thinning Algorithm Thinning