ABSTRACT
Image segmentation is the process of partitioning an image to meaningful segments. There are many segmentation algorithms available, but nothing works perfect in all the cases. In computer vision, Image segmentation algorithms available either as interactive or automated approaches. In medical imagine, interactive segmentation techniques are mostly used due to the high precision requirement of medical applications. But some applications like semantic indexing of images may require fully automated segmentation method.Automated segmentation methods can be divided into two categories namely supervised and unsupervised segmentation. In supervised segmentation the method use a machine learning technique to provide the knowledge of objects (or ground truth segments) in images to the segmentation algorithm.Unsupervised segmentation may use basic image processing techniques to complex optimization algorithms. Hence these segmentation methods take much more time when we ask for better results.
IMPLEMENTATION
Algorithm : OpenCV 2.4 and Visual C++code to work: C++.
An implementation of unsupervised watershed algorithm for image segmentation with a histogram matching technique to reduce over-segmentation occurred by the segmentation algorithm.
CONCEPTS
- Otsu Thresholding
- Morphology - Opening
- Distance Transformation
- Watershed Segmentation Algorithm
- Hue-Saturation Histogram
- Histogram comparison.
SCREENSHOTS
Original image
After applying otsu's threshold
After Morphology
After distance transformation
After Applying the Threshold to Distance Transformed Image
After Applying Watershed Segmentation
Image in HSV Color Space
The Segmentation after Merging
When the Merged Segmentation Mapped to Image
