Wanhyun Cho

Segmentation of interest region in medical volume images using geometric deformable model

In this paper, we present a new segmentation method using the level set framework for medical volume images. The method was implemented using the surface evolution principle based on the geometric deformable model and the level set theory. And, the speed function in the level set approach consists of a hybrid combination of three integral measures derived from the calculus of variation principle. The terms are defined as robust alignment, active region, and smoothing. These terms can help to obtain the precise surface of the target object and prevent the boundary leakage problem. The proposed method has been tested on synthetic and various medical volume images with normal tissue and tumor regions in order to evaluate its performance on visual and quantitative data. The quantitative validation of the proposed segmentation is shown with higher Jaccards measure score (72.52%-94.17%) and lower Hausdorff distance (1.2654 mm-3.1527 mm) than the other methods such as mean speed (67.67%-93.36% and 1.3361mm-3.4463 mm), mean-variance speed (63.44%-94.72% and 1.3361 mm-3.4616 mm), and edge-based speed (0.76%-42.44% and 3.8010 mm-6.5389 mm). The experimental results confirm that the effectiveness and performance of our method is excellent compared with traditional approaches.

FPGA implementation of image watermarking algorithm for a digital camera

In this paper, we present an FPGA implementation of a watermarking-based authentication algorithm for a digital camera to authenticate the snapshots in a manner that any changes of contents in the still image will be reflected in the embedded watermark. All components of a digital camera and a watermark algorithm are implemented in VHDL, simulated, synthesized and loaded into an FPGA device. To achieve the semifragile characteristics that survive a certain amount of compression, we employ the property of DCT coefficients quantization proposed by Lin and Chang (2000). The binary watermark bits are generated by exclusive ORing the binary logo with pseudo random binary sequence. Then watermark bits are embedded into the LSBs of DCT coefficients in the medium frequency range. The system consists of three main parts: image capture and LCD controller, watermark embedding part, and camera control unit. The FPGA implemented digital camera is tested to analyze the performance. It is shown that the watermarking algorithm can embed the watermark into the original image coming from a sensor much faster than the software implementation and the embedded image is easily transmitted to the PC by using the USB interface. The quality of the transmitted image is also comparable to the one implemented by a software algorithm.

Segmentation of medical images using a geometric deformable model and its visualization

An automatic segmentation method for medical images that uses a geometric deformable model is presented, and the segmented results are visualized with the help of a modified marching cubes algorithm. The geometric deformable model is based on evolution theory and the level set method. In particular, the level set method utilizes a new derived speed function to improve the segmentation performance. This function is defined by the linear combination of three terms, namely, the alignment term, the minimal-variance term, and the smoothing term. The alignment term makes a level set as close as possible to the boundary of an object. The minimal-variance term best separates the interior and exterior of the contour. The smoothing term renders a segmented boundary less sensitive to noise. The use of the proposed speed function can improve the segmentation accuracy while making the boundaries of each object much smoother. Finally, it is demonstrated that the design of the speed function plays an important role in the reliable segmentation of synthetic and computed tomography (CT) images, and the segmented results are visualized effectively with the help of a modified marching cubes algorithm.

Medical Image Segmentation Using a Geometric Active Contour Model Based on Level Set Method

We present a level set framework for medical image segmentation using a new defined speed function. This function combines the alignment term, which makes a level set as close as possible to a boundary of object, the minimal variance term, which best separates the interior and exterior in the contour and the smoothing term, which makes a segmented boundary become less sensitive to noise. The use of a proposed speed function can improve the segmentation accuracy while making the boundaries of each object much smoother. Finally, we have demonstrated that the design of the speed function plays an important part in segmenting the synthetic and CT images reliably.

Detection and recognition of moving objects using the temporal difference method and the hidden Markov model

This paper proposes a new detection and recognition method for moving objects that uses the temporal difference method (TDM) and the hidden Markov model (HMM). First, we apply the concept of entropy to convert the pixel value in the image domain into the amount of energy change in the entropy domain. Second, we use the temporal difference method to quickly detect the region of moving objects in complex images to address the variation in changing environments. Third, we use the discrete wavelet transformation technique to extract proper feature vectors from the detected mask image. Fourth, we use the hidden Markov model to accurately recognize moving objects. The results indicate that our proposed method can effectively and accurately detect and recognize moving objects in image sequences.

Level-Set Segmentation of Brain Tumors Using a New Hybrid Speed Function

This paper presents a new hybrid speed function needed to perform image segmentation within the level-set framework. This speed function provides a general form that incorporates the alignment term as a part of the driving force for the proper edge direction of an active contour by using the probability term derived from the region partition scheme and, for regularization, the geodesics contour term. First, we use an external force for active contours as the Gradient Vector Flow field. This is computed as the diffusion of gradient vectors of a gray level edge map derived from an image. Second, we partition the image domain by progressively fitting statistical models to the intensity of each region. Here we adopt two Gaussian distributions to model the intensity distribution of the inside and outside of the evolving curve partitioning the image domain. Third, we use the active contour model that has the computation of geodesics or minimal distance curves, which allows stable boundary detection when the model’s gradients suffer from large variations including gaps or noise. Finally, we test the accuracy and robustness of the proposed method for various medical images. Experimental results show that our method can properly segment low contrast, complex images.

Moving Object Detection based on Clausius Entropy

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. However, due to dynamic changes in natural scenes such as sudden illumination and weather changes, repetitive motions that cause clutter, motion detection has been considered a difficult problem to process reliably. Hence, its robustness needs to be improved for applications in complex environments. In this paper, we propose a novel approach for the detection of moving objects that is based on the Claudius entropy method. First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius Entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussian. Experiment results demonstrate that the proposed method can detect moving objects effectively and reliably.

Automatic Images Classification Using HDP-GMM and Local Image Features

In this paper, we propose a new method based on the probability model that can classify automatically various images by subjects without any prior exchange of information with users. First, we introduce the hierarchical Dirichlet processes Gaussian mixture model (HDP-GMM) that can be applied in images classification, and consider the variational Bayesian inference method to estimate the posterior distribution for the hidden variables and parameters required by this model. Second, we examine the extraction method of various local patches features from given image, which can accurately represent the colors and contents of images. Next, we have trained the HDP-GMM using the extracted patch features, and then present a scheme to classify a given image into the appropriate category or topic by using trained model. Finally, we have applied our model to classify various images datasets, and we have showed the superiority of the proposed method using several evaluation measures for classification method.

Detection and tracking of multiple moving objects in video sequence using entropy mask method and fast level set method

In this paper, we propose a novel algorithm for real-time detection and tracking of multiple moving objects, which sequentially integrates the entropy difference method with adaptive threshold and the fast level set method. First, we have applied the Clausius Entropy theory to convert the pixel value in image domain into the amount of energy change in entropy domain. And then we apply the entropy difference detection method to detect the coarse region of the moving objects in this image and we have constructed the mask covering a detected coarse region. Second, taking the initial value of the level set for moving object as the constructed mask region, we have applied the fast level set technique to track rapidly the contour of detected objects. Here, we have used the fast level set method that combines the Fast Marching Method and the Smart Narrow Band. Experiment results demonstrate that our method can detect and track effectively and accurately the motion objects in video sequence.

Human Action Classification Using Multidimensional Functional Data Analysis Method

In this paper, we describe a novel approach that can classify a human action by using a multidimensional functional data analysis (MFDA) and the Cartesian product of reproducing kernel Hilbert spaces (CPRKHSs). The main idea is to represent the human action video dataset into a multidimensional functional data framework, and then apply the mathematical properties of CPRKPHS to classify these datasets. First, we extract the feature vector that can properly describe the shape of the human action from each frame of a given video. Here, a set of features extracted from a given video can be expressed as a multivariate functional data format depending on an order of time. Since a multidimensional functional data belongs to the non-linear manifold, we embed a multidimensional functional data into the CPRKPHS by using the idea of kernel methods. Then, we have shown that the geodesic distance between two human actions on manifold can be approximate with the product Hilbert norm for a difference between two multidimensional functional datasets in RKPHS. Finally, we have applied common classification rules such as the k-NN method based on these distances in order to classify a human action.