Qingmin Liao

Statistical Structure Analysis in MRI Brain Tumor Segmentation

Automated MRI (Magnetic Resonance Imaging) brain tumor segmentation is a difficult task due to the variance and complexity of tumors. In this paper, a statistical structure analysis based tumor segmentation scheme is presented, which focuses on the structural analysis on both tumorous and normal tissues. Firstly, 3 kinds of features including intensity-based, symmetry-based and texture-based are extracted from structural elements. Then a classification technique using AdaBoost that learns by selecting the most discriminative features is proposed to classify the structural elements into normal tissues and abnormal tissues. Experimental results on 140 tumor-contained brain MR images achieve an average accuracy of 96.82% on tumor segmentation.

Part template: 3D representation for multiview human pose estimation

We present a system for human pose estimation from synchronized multiview images. The system uses an analysis-by-synthesis approach with a skeleton model. This approach is powerful, but may present issues with its potentially huge search space. We adopt a hierarchical method where the head and torso are found first based on template fitting. The detection of the other parts then proceeds with the shoulders and hips to locate the anchor points of the limbs. Subsequently, a hierarchical fitting technique is used to estimate the location of the limbs. The parameter space is then partitioned, which dramatically reduces the complexity of pose estimation. Another difficulty of this system is to find adequate measurements which are used to fit the skeleton model. A multi-cue 3D fusion method is proposed for this purpose. It starts with extracting a set of cues from synchronized multiview images which exploit geometric and color information, and they are then integrated into a 3D representation, called a part template. The experiments show that this system reliably performs on sequences that include unconstrained motions, such as those that are fast or unpredictable, and is also robust to several common issues associated with input data, such as image noise and self-contact.

Fuzzy information fusion scheme used to segment brain tumor from MR images

A fuzzy information fusion scheme is proposed in this paper to automatically segment tumor areas of human brain from multispectral magnetic resonance images such as T1-weighted, T2-weighted and Proton Density (PD) feature images. The proposed scheme consists of four stages: data-level fusion, space creation of fuzzy features, fusion of fuzzy features and fuzzy decision. Several fuzzy operators are proposed to create the feature-level fusion. The fuzzy information models describing the characteristics of tumor areas in human brain are also established. A fuzzy region growing based on fuzzy connecting is presented to obtain the final segmentation result. The comparison between the result of our method and the hand-labeled segmentation of a radiology expert shows that this scheme is efficient. The experimental results (based on 4 patients studied) show an average probability of correct detection equal to 96% and an average probability of false detection equal to 5%.

Knowledge based fuzzy information fusion applied to classification of abnormal brain tissues from MRI

A fuzzy information fusion method is proposed in this paper. It can automatically classify abnormal tissues in human brain in a three dimension space from multispectral magnetic resonance images such as T1-weighted, T2-weighted and proton density feature images. It consists of four steps: data matching, information modelling, information fusion and fuzzy classification. Several fuzzy set definitions are proposed to describe the specific observation universal. The fuzzy information models of tumor area in human brain and the particular fuzzy relations that contribute to information fusion and classification are also established. Three MR image sequences of a patient are utilized as an example to show the method performances. The results are appreciated by experts in radiology.

A Fast and Accurate Iris Segmentation Approach

Iris segmentation is a vital forepart module in iris recognition because it isolates the valid image region used for subsequent processing such as feature extraction. Traditional iris segmentation methods often involve an exhaustive search in a certain large parameter space, which is time consuming and sensitive to noise. Compared to traditional methods, this paper presents a novel algorithm for accurate and fast iris segmentation. A gray histogram-based adaptive threshold is used to generate a binary image, followed by connected component analysis, and rough pupil is separated. Then a strategy of RANSAC (Random sample consensus) is adopted to refine the pupil boundary. We present Valley Location of Radius-Gray Distribution (VLRGD) to detect the weak iris outer boundary and fit the edge. Experimental results on the popular iris database CASIA-Iris V4-Lamp demonstrate that the proposed approach is accurate and efficient.

Automatic brain tumor extraction using fuzzy information fusion

This paper presents a fuzzy information fusion method to automatically extract tumor areas of human brain from multispectral magnetic resonance (MR) images. The multispectral images consist of T1 -weighted (T1), proton density (PD), and 12-weighted (T2) feature images, in which signal intensities of a tumor are different. Some tissue is more visible in one image type than the others. The fusion of information is therefore necessary. Our method, based on the fusion of information, model the fuzzy information about the tumor by membership functions. Thismodelisation is based on the a priori knowledge of radiology experts and the MR signals of the brain tissues. Three membership functions related to the three images types are proposed according to their characteristics. The brain extraction is then carried out by using the fusion of all three fuzzy information. The experimental results (based on 5 patients studied) show a mean false-negative of 2% and a mean false-positive of 1 .3%, comparing to the results obtained by a radiology using manual tracing.

Frame Frequency Multiplier System for Stereo Video on Programmable Hardware

A frame frequency multiplier system based on Field Programmable Gate Array (FPGA) for time-sequential stereo video is proposed in this paper. The system converts two standard 60 fields/sec interlaced NTSC videos captured by two cameras in different perspective views to a 120 frames/sec time– sequential progressive stereo video. Video synchronization signals are generated based on Look-Up Tables according to the timing of stereo video and a novel ping-pong approach realized by First-in First-out (FIFO) memories is applied to control video data acquisition and transmission in the system. It can provide high quality and flicker-free 3-D stereo images and thus will bring the stereo video system wide applications Keywordsstereo video; synchronization signal; FPGA;FIFO

An Effective Method for Foreground Segmentation of Video

In this paper, we propose a novel foreground segmentation approach for applications using static cameras. The foreground segmentation is modeled as an energy function optimum process, where energy function is based on Markov Random Field (MRF) and efficiently optimized by Gibbs sampling. The essence of our method is that we fuse four foreground/background models based on color and texture. This allows composing a robust likelihood term that not only reflects the appearance of foreground/background, but also models the shadow removal process, together with a spatial contrast term and a better temporal persistence term, which achieves a more accurate segmentation. This method has been run on both indoor and outdoor sequences, and the results have proved its effectiveness.

Run-Based Connected Components Labeling Using Double-Row Scan

This paper presents a novel run-based connected components labeling algorithm which uses double-row scan. In this algorithm, the run is defined in double rows and the binary image is scanned twice. In the first scan, provisional labels are assigned to runs according to the connectivity between the current run and runs in the last two rows. Simultaneously, equivalent provisional labels are recorded. Then the adjacent matrix of the provisional labels is generated and decomposed with the Dulmage-Mendelsohn decomposition, to search for the equivalent-label sets in linear time. In the second scan, each equivalent-label set is labeled with a number from 1, which can be efficiently accomplished in parallel. The proposed algorithm is compared with the state-of-the-art algorithms both on synthetic images and real image datasets. Results show that the proposed algorithm outperforms the other algorithms on images with low density of foreground pixels and small amount of connected components.

A Space Carving Based Reconstruction Method Using Discrete Viewing Edges

In this paper, we consider the problem of reconstructing a 3D model from a set of pictures taken from calibrated and arbitrarily placed cameras. Our method is based on existing space carving algorithm which considers photo hull as the final result. Our goal is to solve the visibility problem during carving the visual hull. A new concept Discrete Viewing Edge (DVE) is proposed to represent the visual hull instead of a 3D array. DVE is based on voxels and is simple but effective. With models represented by DVEs, we present a surface extraction algorithm and a carve procedure, during which the visibility of a voxel can be determined rapidly and easily. Our way of determining the visibility of a voxel is global, i.e., we take all possible cameras to which this voxel is visible into account. We apply our method to a set of synthetic pictures and provide arbitrary views of target model which are different from existing cameras.