Automatic localization and segmentation of the ventricles in magnetic resonance (MR) images is important for clinical applications. In this paper, we propose a new ventricle localization method based on slope difference distribution (SDD) clustering and threshold selection to calculate the positions of the left ventricle (LV) and the right ventricle (RV) automatically. Then, we utilize the SDD threshold selection to segment the LV and the RV in the automatically localized region of interest (ROI). To calculate the optimal threshold, we propose a coarse-to-fine SDD threshold selection method. Experimental results verified that both the proposed automatic ventricle localization method and the proposed coarse-to-fine SDD threshold selection method are more robust than state of the art methods.

Despite the great prosperity and fast development of image segmentation technology, threshold selection method is still the best choice in many practical applications. The state-of-the-art threshold selection methods perform poorly in segmenting many images with different modalities, such as the magnetic resonance images, cell images, and laser line images. Thus, it is desirable to come up with a more robust method that could segment images with different modalities with the optimum accuracy. To this end, the method should be flexible and its parameters should be adjustable for different types of images. In this paper, we propose to compute the threshold based on the slope difference distribution, which is computed from the image histogram with adjustable parameters. First, the pixels are clustered based on the peaks of the slope difference distribution into different pixel classes. Second, the threshold is selected based on the valleys of the slope difference distribution to separate the pixel classes. The robustness of this threshold selection method relies on the adjustable parameters that could be calibrated to achieve the optimum segmentation accuracy for each specific type of images. The proposed threshold selection method is tested on both the synthesized images and the real images. Experimental results show that the proposed method outperforms the state-of-the-art methods as a whole.

In this paper, a method is proposed to measure the shapes of specular surfaces with one-shot-projection of structured laser patterns. By intercepting the reflection of the reflected laser pattern twice with two diffusive planes, the closed form solution is achieved for each reflected ray. The points on the specular surface are reconstructed by computing the intersections of the incident rays and the reflected rays. The proposed method can measure both static and dynamic specular shapes due to its one-shot-projection, which is beyond the capability of most of state of art methods that need multiple projections. To our knowledge, the proposed method is the only method so far that could yield the closed form solutions for the dynamic and specular surfaces.

In recent years, the microscopy technology for imaging cells has developed greatly and rapidly. The accompanying requirements for automatic segmentation and quantification of the imaged cells are becoming more and more. After studied widely in both scientific research and industrial applications for many decades, cell segmentation has achieved great progress, especially in segmenting some specific types of cells, e.g. muscle cells. However, it lacks a framework to address the cell segmentation problems generally. On the contrary, different segmentation methods were proposed to address the different types of cells, which makes the research work divergent. In addition, most of the popular segmentation and quantification tools usually require a great part of manual work. To make the cell segmentation work more convergent, we propose a framework that is able to segment different kinds of cells automatically and robustly in this paper. This framework evolves the previously proposed method in segmenting the muscle cells and generalizes it to be suitable for segmenting and quantifying a variety of cell images by adding more union cases. Compared to the previous methods, the segmentation and quantification accuracy of the proposed framework is also improved by three novel procedures: (1) a simplified calibration method is proposed and added for the threshold selection process; (2) a noise blob filter is proposed to get rid of the noise blobs. (3) a boundary smoothing filter is proposed to reduce the false seeds produced by the iterative erosion. As it turned out, the quantification accuracy of the proposed framework increases from 93.4 to 96.8% compared to the previous method. In addition, the accuracy of the proposed framework is also better in quantifying the muscle cells than two available state-of-the-art methods. The proposed framework is able to automatically segment and quantify more types of cells than state-of-the-art methods.