Separating and counting number of touching object using image segmentation technique / Ahmad Afif Azmi

• Main Author: Azmi, Ahmad Afif
• Format: Student Project
• Language: English
• Published: 2008
• Subjects: Applied optics. Photonics; Optical data processing; Image processing
• Online Access: http://ir.uitm.edu.my/id/eprint/43061/1/43061.PDF; http://ir.uitm.edu.my/id/eprint/43061/

Image segmentation is the fundamentals process in digital image processing. It is a process of partitioning a digital image into something more meaningful for easier analysis in practical application. Separating and counting number of touching object is one of the practical applications. The sample objects taken are oval, circle and rectangular. The image sample of each of the objects is captured on 3 different images. Those images would be an image of single object, multiple touching object and image consist both single and multiple touching objects. Each image will contain 7 quantities of objects. The images are first segmented using marker-controlled watershed segmentation technique. Then information pertaining to orientation and pixels in the segmented image is extracted and plotted in a graph. Next the range of the objects pixel is determined and finally the number of objects in an image can be counted. The results shows that using this algorithm can accurately separate and counting the number of touching object if correct parameter is applied.