Image Registration of Medical Images Using Ripplet Transform
For image fusion of geometrically distorted images, registration is the prerequisite step. Intensity-based image registration methods are preferred due to higher accuracy than that of feature-based methods. But, perfect registered image using intensity ba
- PDF / 265,847 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 4 Downloads / 250 Views
Abstract For image fusion of geometrically distorted images, registration is the prerequisite step. Intensity-based image registration methods are preferred due to higher accuracy than that of feature-based methods. But, perfect registered image using intensity based method leads towards improvements in computational complexity. Conventional transform like wavelet transform based image registration reduces the computational complexity, but suffers from discontinuities such as curved edges in the medical images. In this paper, a new registration algorithm is proposed that uses the approximate-level coefficients of the ripplet transform, which allows arbitrary support and degree as compared to curvelet transform. The entropybased objective function is developed for registration using ripplet coefficients of the images. The computations are carried out with 6 sets of CT and MRI brain images to validate the performance of the proposed registration technique. The quantitative approach such as standard deviation, mutual information, peak signal to noise ratio and root mean square error are used as performance measure. Keywords Image registration ⋅ Ripplet transform ⋅ Standard deviation information ⋅ Root mean square error ⋅ Peak signal noise ratio
⋅ Mutual
S. Pradhan (✉) ⋅ D. Patra ⋅ A. Singh IPCV Lab, Department of Electrical Engineering, National Institute of Technology, Rourkela, India e-mail: [email protected] D. Patra e-mail: [email protected] A. Singh e-mail: [email protected] © Springer Science+Business Media Singapore 2017 B. Raman et al. (eds.), Proceedings of International Conference on Computer Vision and Image Processing, Advances in Intelligent Systems and Computing 460, DOI 10.1007/978-981-10-2107-7_44
487
488
S. Pradhan et al.
1 Introduction Now a days, in medical imaging applications, high spatial and spectral information from a single image is required to monitor and diagnose during treatment process. These informations can be achieved by multimodal image registration. Different modalities of imaging techniques gives several information about the tissues and organ of human body. According to their application range, the imaging techniques mostly used are CT, MRI, FMRI, SPECT, and PET. A Computed tomography (CT) image detects the bone injuries, whereas MRI defines the soft tissues of an organ such as brain and lungs. CT and MRI provide high resolution image with biological information. The functional imaging technique such as PET, SPECT, and fMRI gives low spatial resolution with basic information. To get the complete and detailed information from single modality is a challenging task, which necessitates the registration task to combine multimodal images [1]. The registered image is more suitable for radiologist for further image analysis task. Image registration has several applications such as remote sensing and machine vision etc. Several researchers have been discussed and proposed different registration techniques in literature [2]. Image registration technique can be divided into inte
Data Loading...
