Boundaries Object Detection for Skin Cancer Image using Gray-Level Co-Occurrence Matrix (GLCM) and features points

Abstract

             In the present paper, boundaries object detection(BOD) for skin cancer image using connected components is proposed. We propose connected components algorithm which that capable of Segment with Extraction of connected  boundaries for skin cancer image segmentation  . The algorithm is proposed to create a color label image  using the local features e points in skin cancer as objects image . A new boundaries object detection(BOD) technique is introduced based on the gray-level co-occurrence matrix (GLCM). GLCM represents the distributions of the intensities and the information about relative positions of neighboring pixels of an image.

              Database consists of 120 images (60 image for satisfactory skin cancer ,60 image for unsatisfactory skin),types for image .jpg , .png and .bmp image formats.
database prepared in our conditions ,images obtained from in Al-Seder Hospital(30 image for satisfactory skin cancer ,30 image for unsatisfactory skin), other images obtained from internet(30 image for satisfactory skin cancer ,30 image for unsatisfactory skin).

            Training stage consists of 80 images(20 image for satisfactory skin cancer ,20 image for unsatisfactory skin cancer) from in Al-Seder Hospital and(20 image for satisfactory skin cancer ,20 image for unsatisfactory skin cancer) from internet. Testing stage consists of 40 images(10 image for satisfactory skin cancer ,10 image for unsatisfactory skin cancer) from in Al-Seder Hospital and(10 image for satisfactory skin cancer ,10 image for unsatisfactory skin cancer) from internet.

            The performance of object detection with Connected components which are surround influence . The proposed scheme can serve as a easy preprocessing for high level tasks such shape based recognition and image retrieval. The experimental results confirm the effectiveness of the proposed algorithm.