An Improved Ultrasound Image Segmentation Algorithm for Cattle Follicle Based on Markov Random Field Model
In this paper, we proposed an improved ultrasound image segmentation algorithm for cattle follicle based on Markov random field model. According to the original ultrasound image dataset, we removed the speckle noise in ultrasound images by anisotropic dif
- PDF / 591,899 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 39 Downloads / 183 Views
2
1 College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China [email protected], [email protected]
Abstract. In this paper, we proposed an improved ultrasound image segmentation algorithm for cattle follicle based on Markov random field model. According to the original ultrasound image dataset, we removed the speckle noise in ultrasound images by anisotropic diffusion filtering algorithm on the first step, and used the image enhancement technology to enhance the contrast of target area, then combined with an improved k-means algorithm for initial segmentation to realize basic classification of image pixels. As for the discontinuous over segmentation, we used area rule to remove the discontinuous over-segmentation region. Compared to the traditional MRF algorithm, this new algorithm has more accurate segmentation of the target area, better segmentation effect. The improved k-means algorithm to make initial segmentation for MRF model can also avoid initial clustering center to be selected randomly in comparison with the traditional k-means algorithm. Keywords: Cattle follicle accuracy Stability
Ultrasound image segmentation
Segmentation
1 Introduction In the field of image segmentation, the ultrasound image segmentation has been an important and challenging subject. Based on the analysis of the ultrasound image of cattle follicle, this paper aims to find the exact timing of the ovulation period which will be of great significance to the cattle’s breeding. MRF algorithm is widely used in image segmentation field. Li et al. [1] applied MRF algorithm to extract an infrared target fast and accurately. In the paper of [2], a MRF model was proposed to segment myocardium in Magnetic Resonance Imaging. Yousefi et al. [3] used a hybrid of MRF and social algorithms to segment brain tissue in MR images. Li and Liu [4] developed a multi-resolution MRF model with variable potentials in wavelet domain to segment texture image. Mridula et al. [5] applied combining GLCM (gray level co-occurrence matrix) features and MRF model to segment color textured images. © Springer International Publishing Switzerland 2016 D.-S. Huang and K.-H. Jo (Eds.): ICIC 2016, Part II, LNCS 9772, pp. 613–623, 2016. DOI: 10.1007/978-3-319-42294-7_55
614
J. Liu and B. Guan
In the process of ultrasound image scanning, the effective area of the scanner is often presented as a sector, which increases the difficulty and complexity of the image segmentation. In order to get a better segmentation of the target area, we choose the ROI (region of interest) by hand to do pre-treatment and segmentation, which deduce the degree of complexity. To make sure the accuracy of the experiment, all images in the experiment must be chosen the same ROI randomly, namely, we use the same ROI in the dataset.
2 Background 2.1
Markov Random Field (MRF)
MRF was first applied for image processing field in the mid-1980s (Geman
Data Loading...
