Beiji Zou

Selective color transfer with multi-source images

A novel method is proposed to transfer selective colors from a set of source images to a target image. An improved EM method is presented to model regional color distribution of the target image by Gaussian Mixture Model (GMM), then, trained by this model, appropriate reference colors are automatically selected from the given source images to color each target region. The generated compelling results prove that our proposed method is applicable to colorize grayscale images and color transfer between chromatic images. A new objective metric considering colorfulness and structural similarity is also proposed to evaluate the quality of the transferred image, which verifies good performance of our method.

Retinal vessel segmentation in colour fundus images using Extreme Learning Machine.

Attributes of the retinal vessel play important role in systemic conditions and ophthalmic diagnosis. In this paper, a supervised method based on Extreme Learning Machine (ELM) is proposed to segment retinal vessel. Firstly, a set of 39-D discriminative feature vectors, consisting of local features, morphological features, phase congruency, Hessian and divergence of vector fields, is extracted for each pixel of the fundus image. Then a matrix is constructed for pixel of the training set based on the feature vector and the manual labels, and acts as the input of the ELM classifier. The output of classifier is the binary retinal vascular segmentation. Finally, an optimization processing is implemented to remove the region less than 30 pixels which is isolated from the retinal vascilar. The experimental results testing on the public Digital Retinal Images for Vessel Extraction (DRIVE) database demonstrate that the proposed method is much faster than the other methods in segmenting the retinal vessels. Meanwhile the average accuracy, sensitivity, and specificity are 0.9607, 0.7140 and 0.9868, respectively. Moreover the proposed method exhibits high speed and robustness on a new Retinal Images for Screening (RIS) database. Therefore it has potential applications for real-time computer-aided diagnosis and disease screening.

Multi-task GLOH feature selection for human age estimation

In this paper, we propose a novel age estimation method based on gradient location and orientation histogram (GLOH) descriptor and multi-task learning (MTL). The GLOH, one of the state-of-the-art local descriptor, is used to capture the age-related local and spatial information of face image. As the extracted GLOH features are often redundant, MTL is designed to select the most informative GLOH bins for age estimation problem, while the corresponding weights are determined by ridge regression. This approach largely reduces the dimensions of feature, which can not only improve performance but also decrease the computational burden. Experiments on the public available FG-NET database show that the proposed method can achieve comparable performance over previous approaches while using much fewer features.

Physical modeling with orthotropic material based on harmonic fields

Although it is well known that human bone tissues have obvious orthotropic material properties, most works in the physical modeling field adopted oversimplified isotropic or approximated transversely isotropic elasticity due to the simplicity. This paper presents a convenient methodology based on harmonic fields, to construct volumetric finite element mesh integrated with complete orthotropic material. The basic idea is taking advantage of the fact that the longitudinal axis direction indicated by the shape configuration of most bone tissues is compatible with the trajectory of the maximum material stiffness. First, surface harmonic fields of the longitudinal axis direction for individual bone models were generated, whose scalar distribution pattern tends to conform very well to the object shape. The scalar iso-contours were extracted and sampled adaptively to construct volumetric meshes of high quality. Following, the surface harmonic fields were expanded over the whole volumetric domain to create longitudinal and radial volumetric harmonic fields, from which the gradient vector fields were calculated and employed as the orthotropic principal axes vector fields. Contrastive finite element analyses demonstrated that elastic orthotropy has significant effect on simulating stresses and strains, including the value as well as distribution pattern, which underlines the relevance of our orthotropic modeling scheme.

A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images.

The automatic exudate segmentation in colour retinal fundus images is an important task in computer aided diagnosis and screening systems for diabetic retinopathy. In this paper, we present a location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images, which includes three stages: anatomic structure removal, exudate location and exudate segmentation. In anatomic structure removal stage, matched filters based main vessels segmentation method and a saliency based optic disk segmentation method are proposed. The main vessel and optic disk are then removed to eliminate the adverse affects that they bring to the second stage. In the location stage, we learn a random forest classifier to classify patches into two classes: exudate patches and exudate-free patches, in which the histograms of completed local binary patterns are extracted to describe the texture structures of the patches. Finally, the local variance, the size prior about the exudate regions and the local contrast prior are used to segment the exudate regions out from patches which are classified as exudate patches in the location stage. We evaluate our method both at exudate-level and image-level. For exudate-level evaluation, we test our method on e-ophtha EX dataset, which provides pixel level annotation from the specialists. The experimental results show that our method achieves 76% in sensitivity and 75% in positive prediction value (PPV), which both outperform the state of the art methods significantly. For image-level evaluation, we test our method on DiaRetDB1, and achieve competitive performance compared to the state of the art methods.

Interactive tooth partition of dental mesh base on tooth-target harmonic field

The accurate tooth partition of dental mesh is a crucial step in computer-aided orthodontics. However, tooth boundary identification is not a trivial task for tooth partition, since different shapes and their arrangements vary substantially among common clinical cases. Though curvature field is traditionally used for identifying boundaries, it is normally not reliable enough. Other methods may improve the accuracy, but require intensive user interaction. Motivated by state-of-the-art general interactive mesh segmentation methods, this paper proposes a novel tooth-target partition framework that employs harmonic fields to partition teeth accurately and effectively. In addition, a refining strategy is introduced to successfully segment teeth from the complicated dental model with indistinctive tooth boundaries on its lingual side surface, addressing an issue that had not been solved properly before. To utilise high-level information provided by the user, smart and intuitive user interfaces are also proposed with minimum interaction. In fact, most published interactive methods specifically designed for tooth partition are lacking efficient user interfaces. Extensive experiments and quantitative analyses show that our tooth partition method outperforms the state-of-the-art approaches in terms of accuracy, robustness and efficiency.

Exploring regularized feature selection for person specific face verification

In this paper, we explore the regularized feature selection method for person specific face verification in unconstrained environments. We reformulate the generalization of the single-task sparsity-enforced feature selection method to multi-task cases as a simultaneous sparse approximation problem. We also investigate two feature selection strategies in the multi-task generalization based on the positive and negative feature correlation assumptions across different persons. Simultaneous orthogonal matching pursuit (SOMP) is adopted and modified to solve the corresponding optimization problems. We further proposed a named simultaneous subspace pursuit (SSP) methods which generalize the subspace pursuit method to solve the corresponding optimization problems. The performance of different feature selection strategies and different solvers for face verification are compared on the challenging LFW face database. Our experimental results show that 1) the selected subsets based on positive correlation assumption are more effective than those based on the negative correlation assumption; 2) the OMP-based solvers outperform SP-based solvers in terms of feature selection and 3) the regularized methods with OMP-based solvers can outperform state-of-the-art feature selection methods.

Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching

BACKGROUND AND OBJECTIVE Identifying liver regions from abdominal computed tomography (CT) volumes is an important task for computer-aided liver disease diagnosis and surgical planning. This paper presents a fully automatic method for liver segmentation from CT volumes based on graph cuts and border marching. METHODS An initial slice is segmented by density peak clustering. Based on pixel- and patch-wise features, an intensity model and a PCA-based regional appearance model are developed to enhance the contrast between liver and background. Then, these models as well as the location constraint estimated iteratively are integrated into graph cuts in order to segment the liver in each slice automatically. Finally, a vessel compensation method based on the border marching is used to increase the segmentation accuracy. RESULTS Experiments are conducted on a clinical data set we created and also on the MICCAI2007 Grand Challenge liver data. The results show that the proposed intensity, appearance models, and the location constraint are significantly effective for liver recognition, and the undersegmented vessels can be compensated by the border marching based method. The segmentation performances in terms of VOE, RVD, ASD, RMSD, and MSD as well as the average running time achieved by our method on the SLIVER07 public database are 5.8 ± 3.2%, -0.1 ± 4.1%, 1.0 ± 0.5mm, 2.0 ± 1.2mm, 21.2 ± 9.3mm, and 4.7 minutes, respectively, which are superior to those of existing methods. CONCLUSIONS The proposed method does not require time-consuming training process and statistical model construction, and is capable of dealing with complicated shapes and intensity variations successfully.

Liver vessel segmentation and identification based on oriented flux symmetry and graph cuts

BACKGROUND AND OBJECTIVE Accurate segmentation of liver vessels from abdominal computer tomography angiography (CTA) volume is very important for liver-vessel analysis and living-related liver transplants. This paper presents a novel liver-vessel segmentation and identification method. METHODS Firstly, an anisotropic diffusion filter is used to smooth noise while preserving vessel boundaries. Then, based on the gradient symmetry and antisymmetry pattern of vessel structures, optimal oriented flux (OOF) and oriented flux antisymmetry (OFA) measures are respectively applied to detect liver vessels and their boundaries, and further to slenderize vessels. Next, according to vessel geometrical structure, a centerline extraction measure based on height ridge traversal and leaf node line-growing (LNLG) is proposed for the extraction of liver-vessel centerlines, and an intensity model based on fast marching is integrated into graph cuts (GCs) for effective segmentation of liver vessels. Finally, a distance voting mechanism is applied to separate the hepatic vein and portal vein. RESULTS The experiment results on abdominal CTA images show that the proposed method can effectively segment liver vessels, achieving an average accuracy, sensitivity, and specificity of 97.7%, 79.8%, and 98.6%, respectively, and has a good performance on thin-vessel extraction. CONCLUSIONS The proposed method does not require manual selection of the centerlines and vessel seeds, and can effectively segment liver vessels and identify hepatic vein and portal vein.

Saliency detection using boundary information

Efficient and robust saliency detection is a fundamental problem in computer vision field for its wide applications, such as image segmentation and image retargeting, etc. In this paper, with the aim of uniformly highlighting the salient objects and suppressing the saliency of the background in images, we propose an efficient three-stage saliency detection method. First, boundary prior and connectivity prior are used to generate coarse saliency maps. To suppress the saliency value of the cluttered background, two supergraphs together with the adjacent graph are created so that the saliency of the background regions with similar appearances which are separated by other regions can be reduced effectively. Second, a local context-based saliency propagation is proposed to refine the saliency such that regions with similar features hold similar saliency. Finally, a logistic regressor is learned to combine the three refined saliency maps into the final saliency map automatically. The proposed method improves saliency detection on many cluttered images. The experimental results on two widely used public datasets with pixel accurate salient region annotations show that our method outperforms the state-of-the-art methods.