Jiafeng Liu

Probability density difference-based active contour for ultrasound image segmentation

Because of its low signal/noise ratio, low contrast and blurry boundaries, ultrasound (US) image segmentation is a difficult task. In this paper, a novel level set-based active contour model is proposed for breast ultrasound (BUS) image segmentation. At first, an energy function is formulated according to the differences between the actual and estimated probability densities of the intensities in different regions. The actual probability densities are calculated directly. For calculating the estimated probability densities, the probability density estimation method and background knowledge are utilized. The energy function is formulated with level set approach, and a partial differential equation is derived for finding the minimum of the energy function. For performing numerical computation, the derived partial differential equation is approximated by the central difference and non-re-initialization approach. The proposed method was operated on both the synthetic images and clinical BUS images for studying its characteristics and evaluating its performance. The experimental results demonstrate that the proposed method can model the BUS images well, be robust to noise, and segment the BUS images accurately and reliably.

Automated Segmentation of Ultrasonic Breast Lesions Using Statistical Texture Classification and Active Contour Based on Probability Distance

Because of its complicated structure, low signal/noise ratio, low contrast and blurry boundaries, fully automated segmentation of a breast ultrasound (BUS) image is a difficult task. In this paper, a novel segmentation method for BUS images without human intervention is proposed. Unlike most published approaches, the proposed method handles the segmentation problem by using a two-step strategy: ROI generation and ROI segmentation. First, a well-trained texture classifier categorizes the tissues into different classes, and the background knowledge rules are used for selecting the regions of interest (ROIs) from them. Second, a novel probability distance-based active contour model is applied for segmenting the ROIs and finding the accurate positions of the breast tumors. The active contour model combines both global statistical information and local edge information, using a level set approach. The proposed segmentation method was performed on 103 BUS images (48 benign and 55 malignant). To validate the performance, the results were compared with the corresponding tumor regions marked by an experienced radiologist. Three error metrics, true-positive ratio (TP), false-negative ratio (FN) and false-positive ratio (FP) were used for measuring the performance of the proposed method. The final results (TP = 91.31%, FN = 8.69% and FP = 7.26%) demonstrate that the proposed method can segment BUS images efficiently, quickly and automatically.

An improved quantitative measurement for thyroid cancer detection based on elastography.

OBJECTIVE To evaluate color thyroid elastograms quantitatively and objectively. MATERIALS AND METHODS 125 cases (56 malignant and 69 benign) were collected with the HITACHI Vision 900 system (Hitachi Medical System, Tokyo, Japan) and a liner-array-transducer of 6-13MHz. Standard of reference was cytology (FNA-fine needle aspiration) or histology (core biopsy). The original color thyroid elastograms were transferred from red, green, blue (RGB) color space to hue, saturation, value (HSV) color space. Then, hard area ratio was defined. Finally, a SVM classifier was used to classify thyroid nodules into benign and malignant. The relation between the performance and hard threshold was fully investigated and studied. RESULTS The classification accuracy changed with the hard threshold, and reached maximum (95.2%) at some values (from 144 to 152). It was higher than strain ratio (87.2%) and color score (83.2%). It was also higher than the one of our previous study (93.6%). CONCLUSION The hard area ratio is an important feature of elastogram, and appropriately selected hard threshold can improve classification accuracy.

Breast Ultrasound Image Classification Based on Multiple-Instance Learning

Breast ultrasound (BUS) image segmentation is a very difficult task due to poor image quality and speckle noise. In this paper, local features extracted from roughly segmented regions of interest (ROIs) are used to describe breast tumors. The roughly segmented ROI is viewed as a bag. And subregions of the ROI are considered as the instances of the bag. Multiple-instance learning (MIL) method is more suitable for classifying breast tumors using BUS images. However, due to the complexity of BUS images, traditional MIL method is not applicable. In this paper, a novel MIL method is proposed for solving such task. First, a self-organizing map is used to map the instance space to the concept space. Then, we use the distribution of the instances of each bag in the concept space to construct the bag feature vector. Finally, a support vector machine is employed for classifying the tumors. The experimental results show that the proposed method can achieve better performance: the accuracy is 0.9107 and the area under receiver operator characteristic curve is 0.96 (p < 0.005).

A novel approach for tracking high speed skaters in sports using a panning camera

This paper presents a computer vision system for tracking high-speed non-rigid skaters over a larger rink in short track speed skating competitions. The outputs of the tracking system are spatio-temporal trajectories of the skaters which can be further processed and analyzed by sports experts. To capture highly complex and dynamic scenes, the camera pans very fast, therefore, tracking amorphous skaters becomes a challenging task. We propose a new method for (1) automatically computing the transformation matrices to map each frame to the globally consistent model of the rink; (2) incorporating the hierarchical model based on the contextual knowledge and multiple cues into the unscented Kalman filter to improve the tracking performance when occlusions occur; (3) evaluating the precision of our practical system objectively. Experimental results show that the proposed algorithm is very efficient and effective on the video recorded in the World Short Track Speed Skating Championships.

Pixel Based Temporal Analysis Using Chromatic Property for Removing Rain from Videos

The raindrops degrade the performance of outdoor vision system, and it brings difficulties for objects detection and analysis in image sequence. In this paper, we propose an algorithm detect moving objects using chromatic based properties in rain-affected videos captured by outdoor vision systems. Thus the raindrop removal algorithm includes two parts that is removal raindrops in background and removal raindrops in moving objects. Since the degradation made by raindrops is complex and appears as various changes. The raindrops detection function considering the chromatic properties of image sequence is induced, which does not need the velocity and time information of raindrops. Therefore, it is suitable for all the blur effects caused by raindrops. The removal raindrops are able to distinguish accurately the raindrops-affected pixels from the immovable or movable objects. Although the objects are moving in the rain, the algorithm is also effectual. The experiment results show that the proposal algorithm is able to remove the raindrops and improve the quality of image sequence remarkable.

Hierarchical Model-Based Human Motion Tracking Via Unscented Kalman Filter

This paper presents a computer vision system for tracking high-speed non-rigid skaters over a large playing area in short track speeding skating competitions. The outputs of the tracking system are spatio-temporal trajectories of the players which can be further processed and analyzed by sport experts. Given very fast and non-smooth camera motions to capture highly complex and dynamic scenes of skating, tracking amorphous skaters should be a challenging task. We propose a new method of (1) automatically computing the transformation matrices to map each frame of the imagery to the globally consistent model of the rink and (2) incorporating the hierarchical model based on the contextual knowledge and multiple cues into the unscented Kalman filter to improve the tracking performance when occlusion occurs. Experimental results show that the proposed algorithm is very efficient and effective on video recorded live by the authors in the world short track speed skating championships.

Paper Currency Recognition using Gaussian Mixture Models Based on Structural Risk Minimization

Gaussian mixture model (GMM) is a popular tool for density estimation. The parameters of the GMM are estimated based on maximum likelihood principle (MLP) in almost all recognition system. However, the number of mixtures used in the model is important for determining the models effectiveness; the general problem of mixture modeling is difficult when the number of components is unknown. This paper presents paper currency recognition using GMM based on structural risk minimization (SRM). By selecting the proper number of the components with SRM, the system can overcome the demerit by the number of the Gaussian components selected artificially. A total number of 8 bill types including 5, 10 (new and old model), 20, 50 (new and old model), 100 (new and old model) are considered as classification categories. The experiments show that GMM which employs SRM is a more flexible alternative and lead to improved results for Chinese paper currency recognition

2D Articulated Pose Tracking Using Particle Filter with Partitioned Sampling and Model Constraints

In this paper, we develop a two-dimensional articulated body tracking algorithm based on the particle filtering method using partitioned sampling and model constraints. Particle filtering has been proven to be an effective approach in the object tracking field, especially when dealing with single-object tracking. However, when applying it to human body tracking, we have to face a “particle-explosion” problem. We then introduce partitioned sampling, applied to a new articulated human body model, to solve this problem. Furthermore, we develop a propagating method originated from belief propagation (BP), which enables a set of particles to carry several constraints. The proposed algorithm is then applied to tracking articulated body motion in several testing scenarios. The experimental results indicate that the proposed algorithm is effective and reliable for 2D articulated pose tracking.

A novel fuzzy wavelet approach to contrast enhancement

This work presents a novel contrast enhancement approach based on wavelet transform and fuzzy logic . We first normalize the low contrast image to reduce the effects of different illuminations. Then we choose a specific wavelet transform to convert the normalized image and obtain wavelet coefficients. The low-pass coefficients are fuzzified by the linear operator, and we use both the global and local information to define and enhance the images global contrast. We utilize nonlinear operator on high-pass coefficients to enhance the details of images. Finally, the inverse wavelet transform is applied to map the result into space domain. The experimental results demonstrate that the approach is very effective in enhancing the low contrast image.