Papers by Author: Miao Ma

Paper TitlePage

Authors: Miao Ma, Jiao He, Min Guo
Abstract: Due to the large amount of calculation and high time-consuming in traditional grayscale matching, this paper combines artificial fish algorithm of swarm intelligence with edge detection and the operation of bitwise exclusive or, and presents a fast method on feature matching. The method regards the problem of image matching as a process of searching the optimal solution. In order to provide artificial fish swarm algorithm with an appropriate fitness function, the operation of bitwise exclusive or and addition is employed to deal with the edge information extracted from the template image and the searching image. Then the best matching position is gradually approaching by swarming, following and other behaviors of artificial fish. Experimental results show that the proposed method not only significantly shortens the matching time and guarantees the matching accuracy, but also is robust to noise disturbance.
Authors: Miao Ma, Yan Li Liu, Xiao Fei Dang
Abstract: To improve the overall performance of image fusion, this paper proposes a Bacterial Foraging Algorithm (BFA) based method. First, this method selects several objective standards to construct an index representing the overall performance of fused images. Second, after the source images were decomposed by Contourlet transform, we obtain the coefficients of low-frequency and high-frequency in Contourlet domain. Then, the swarm intelligence of BFA is introduced to determine the proportions of high-frequency coefficients, i.e. the optimal weights. Finally, we use the high-frequency coefficients fused by the optimal weights and the average of low-frequency coefficients to reconstruct the optimal fused image. Experimental results show that the method not only can provide with good visual effects, but also is superior to eight widely-used methods.
Authors: Li Sun, Yan Ning Zhang, Miao Ma, Guang Jian Tian
Abstract: The plasma time-activity curve is often required as the input function for dynamic quantitative FDG PET studies to estimate the metabolic rate of glucose. The invasive gold standard arterial blood sampling has been suggested, however, it has many inconveniences and challenges in clinical and pre-clinical settings. Thus, the image-derived input function has been proposed to obtain the input function from dynamic images non-invasively. This method often needs a manual drawing of one or two regions of interest (ROIs), which is an operator-dependent and time-consuming task. The aim of the presented study was to capture the spatial and temporal patterns of dynamic PET images for automatic ROI extraction. Our proposed approach tries to overcome the main limitation of image clustering methods: the loss of temporal information for dynamic PET ROI definition. The experiments showed that the proposed automatic ROI method can be used for dynamic PET parameter estimation.
Showing 1 to 3 of 3 Paper Titles