Minimum Spanning Tree Algorithm and Connected Components for Skin Cancer Image Object Detection

Abstract

In the present paper, a Skin Cancer Image Object Detection method based on Minimum Spanning Tree Algorithm and Connected Components is proposed. we propose minimum spanning tree algorithm which that capable of Segment with Extraction of connected boundaries for Skin Cancer Image Segmentation . The algorithm is proposed to create a graph using the local features minutiae points in skin cancer as objects image ,one can draw a map connect these point so the work will be able to segment any part of the skin cancer image by finding the map of the part by minimum spanning tree algorithm. The performance of the proposed detector compares favorably both computationally and qualitatively, in comparison Object Detection with Connected Components which are also based on surround influence .The last stage contains Extraction of connected components skin image edge detection . The proposed scheme can serve as a low cost preprocessing step for high level tasks such shape based recognition and image retrieval. The experimental results confirm the effectiveness of the proposed algorithm.