Abstract—Segmentation of Ultrasound (US) Images is quite challenging as the images are of poor quality, contains strong speckle noise and so are not of that high quality as CT or MRI images. Both supervised and unsupervised segmentation techniques are used for segmentation. Unsupervised segmentation approaches mainly rely on subjective assessment. We propose an unsupervised segmentation technique based on conventional Expectation Maximization (EM) algorithm applied on texture features extracted by a bank of Gabor filters. The approach includes three steps: decomposition of image using Gabor filters, texture feature extraction and segmentation. The segmentation results are compared with the work done using K-means clustering. K-means being a basic technique results in over-segmentation and converges in local minima. EM technique used after texture feature extraction is tested on many US images and results were quite satisfactory.
Index Terms—Expectation maximization, feature extraction, gabor filter, multi-resolution analysis.
A. Khanna is with Guru Ghasidas Vishwavidyalaya, Bilaspur (C.G), India (e-mail: email@example.com).
M. Sood is with National Institute of Technology, Hamirpur (H.P), India (e-mail: firstname.lastname@example.org).
S. Devi is with NITTTR, Chandigarh, India (e-mail: email@example.com).
Cite: Anita Khanna, Meenakshi Sood, and Swapna Devi, "US Image Segmentation Based on Expectation Maximization and Gabor Filter," International Journal of Modeling and Optimization vol. 2, no. 3, pp. 230-233, 2012.