Asian Pacific Journal of Health Sciences

Yazarlar: Nookala Venu, Asiya Sulthana

Konular:-

DOI:10.21276/apjhs.2018.5.1.29

Anahtar Kelimeler:Local binary patterns,Medical image segmentation,Texture

Özet: In this paper, local mesh patterns (LMeP) feature extractor is proposed for medical image segmentation. The local region of image is represented by LMeP, which are evaluated by taking into consideration the magnitude of the local difference between the center pixel and its neighbors. First, image split into subblocks and LMeP features are extracted from each subblock. Once the image has been split into blocks of roughly homogeneous texture, we apply an agglomerative procedure to merge similar adjacent regions until one of the two stopping criteria is satis1ed. At each stage, we merge the pair of adjacent regions which have the largest merger importance (MI) value. Based on MI the regions are merged and then form the segmented regions for medical image segmentation application. Experimental results are tested on benchmark magnetic resonance image database for medical image segmentation application. Results after being investigated, proposed method shows a significant improvement for segmentation of images.

---