120 likes | 286 Views
Image Segmentation. Chin-Ya Huang Mon-Ju Wu ECE 533 Final Project, Fall 2006 University of Wisconsin – Madison. Methodology. Acquire the color information and the edge information separately. Use hue, saturation and intensity to get color information.
E N D
Image Segmentation Chin-Ya Huang Mon-Ju Wu ECE 533 Final Project, Fall 2006 University of Wisconsin – Madison
Methodology • Acquire the color information and the edge information separately. • Use hue, saturation and intensity to get color information. • Use the Matlab “edge” command to extract the image boundary. • Combine the above result by getting the union of (2) and (3). • Final modification.
Example Target: Extract the image of the soccer player out from the entire image.
Step 1 : Using HSI as a threshold • Cut partial images to compute the HSI values. • Set the threshold value. • Examine through the image to acquire the color information.
Step 2 : Using Matlab “edge” command • Use Matlab “edge” command to extract the course edges. • Use Matlab “imfill” command to fill the area whose surrounding course edges make a closure.
edge imfill(edge)
Step 3 : Combine the above images • Get the union of the images from Step 1 and Step 2. • Combine the color information and the edge.
Step 4 : Final modification • Perform dilate on “edge” make sure all the separate line segments are connected. • Use “imfill” command to fill the area inside the boundary.
Step 4 : Final modification (cont.) • Intersect the image from (B) with the image from Step 3 to remove the noise. • Image from (C) is the final result.
Final Result Original Image
Future Work • Develop a more powerful algorithm to perform interpolation in order to connect the disconnected line segment. • Find other ways to segment image other than using HSI. • Develop a more powerful algorithm for noise removal.