Automatic image segmentation for large collections

---

Junaid Baber

University of Balochistan, Pakistan

: J Comput Eng Inf Technol

Abstract

---

Image segmentation is one of the most significant tasks in computer vision. Since automatic techniques are hard for this purpose, a number of interactive techniques are used for image segmentation. The result of these techniques largely depends on user’s feedback. It is difficult toget good interactions for large databases. On the other hand, automatic image segmentation isbecoming a significant objective in computer vision and image analysis. We propose anautomatic approach to detect foreground. We are applying Maximal Similarity Based RegionMerging (MSRM) technique for region merging and using image boundary to identifyforeground regions. The results confirm the effectiveness of the approach. This approach revealsits effectiveness especially to extract multiple objects from background.

Biography

---