A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Canny Edge Detection Enhancement by Scale Multiplication
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Non-Maximum Suppression
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
An Improved Region Growing Algorithm for Image Segmentation
CSSE '08 Proceedings of the 2008 International Conference on Computer Science and Software Engineering - Volume 06
| Hi-index | 0.00 |
The objective of segmentation of medical image is to extract and characterize anatomical structures from the images. Segmentation of medical is quiet difficult task because most images contain large noise. Canny operator has decent anti-noise ability. However Edge based canny operator is not consecutive and applying the canny operator on total image make reduces the performance of the system. In this paper, a new method of segmentation by the integration of 2D Otsu method with Canny edge detector and Region Growing is proposed. Here the first the low pass filter to reduce the noise and then Otsu thresholding method is used to extract the region of interest. In this system, Region Growing and Edge detection algorithm are executed parallel. This parallel executing system is used to get the edge map of image. This system is used to identify the Brain tumor. It is also used for Bone Fracture identification and Classification of Blood Cells. Experiments have shown that this system gives best segmentation results for brain tumor identification.