- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
An Efficient and Robust Iris Segmentation Algorithm Using Deep Learning
摘要： Iris segmentation is a critical step in the entire iris recognition procedure. Most of the state-of-the-art iris segmentation algorithms are based on edge information. However, a large number of noisy edge points detected by a normal edge-based detector in an image with specular reflection or other obstacles will mislead the pupillary boundary and limbus boundary localization. In this paper, we present a combination method of learning-based and edge-based algorithms for iris segmentation. A well-designed Faster R-CNN with only six layers is built to locate and classify the eye. With the bounding box found by Faster R-CNN, the pupillary region is located using a Gaussian mixture model. Then, the circular boundary of the pupillary region is fit according to five key boundary points. A boundary point selection algorithm is used to find the boundary points of the limbus, and the circular boundary of the limbus is constructed using these boundary points. Experimental results showed that the proposed iris segmentation method achieved 95.49% accuracy on the challenging CASIA-Iris-Thousand database.
关键词： Iris segmentation,Faster R-CNN,Gaussian mixture model,Boundary point selection,Deep learning
更新于2025-09-23 15:22:29
-
3D surface reconstruction of retinal vascular structures
摘要： We propose in this paper, a three-dimensional surface reconstruction of a retinal vascular network from a pair of 2D retinal images. Our approach attempts to address the above challenges by incorporating an epipolar geometry estimation and adaptive surface modelling in a 3D reconstruction, using three steps: segmentation, 3D skeleton reconstruction and 3D surface modelling of vascular structures. The intrinsic calibration matrices are found via the solution of simplified Kruppa equations. A simple essential matrix based on a self-calibration method has been used for the ‘fundus camera-eye’ system. The used method has eventually produced vessel surfaces that could be fit for various applications, such as applications for computational fluid dynamics simulations and applications for real-time virtual interventional.
关键词： Kruppa equations,curvature-dependent subdivision,surface reconstruction,epipolar geometry,segmentation,retinal vascular network,self-calibration
更新于2025-09-23 15:22:29
-
Automatic optic disc localization and segmentation in retinal images by a line operator and level sets
摘要： BACKGROUND: Existing methods may fail to locate and segment the optic disc (OD) due to imprecise boundaries, inconsistent image contrast and deceptive edge features in retinal images. OBJECTIVE: To locate the OD and detect the OD boundary accurately. METHODS: The method exploits a multi-stage strategy in the detection procedure. Firstly, OD location candidate regions are identi?ed based on high-intensity feature and vessels convergence property. Secondly, a line operator ?lter for circular brightness feature detection is designed to locate the OD accurately on candidates. Thirdly, an initialized contour is obtained by iterative thresholding and ellipse ?tting based on the detected OD position. Finally, a region-based active contour model in a variational level set formulation and ellipse ?tting are employed to estimate the OD boundary. RESULTS: The proposed methodology achieves an accuracy of 98.67% for OD identi?cation and a mean distance to the closest point of 2 pixels in detecting the OD boundary. CONCLUSION: The results illuminate that the proposed method is effective in the fast, automatic, and accurate localization and boundary detection of the OD. The present work contributes to the more effective evaluation of the OD and realizing automatic screening system for early eye diseases to a large extent.
关键词： optic disc segmentation,level set method,retinal images,Optic disc localization
更新于2025-09-23 15:22:29
-
Online Mutual Foreground Segmentation for Multispectral Stereo Videos
摘要： The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications. Using a multispectral camera setup can improve this process by providing more diverse data to help identify objects despite adverse imaging conditions. The registration of several data sources is however not trivial if the appearance of objects produced by each sensor differs substantially. This problem is further complicated when parallax effects cannot be ignored when using close-range stereo pairs. In this work, we present a new method to simultaneously tackle multispectral segmentation and stereo registration. Using an iterative procedure, we estimate the labeling result for one problem using the provisional result of the other. Our approach is based on the alternating minimization of two energy functions that are linked through the use of dynamic priors. We rely on the integration of shape and appearance cues to find proper multispectral correspondences, and to properly segment objects in low contrast regions. We also formulate our model as a frame processing pipeline using higher order terms to improve the temporal coherence of our results. Our method is evaluated under different configurations on multiple multispectral datasets, and our implementation is available online.
关键词： Multispectral imagery,Energy minimization,Cosegmentation,Video signal processing,Video object segmentation
更新于2025-09-23 15:22:29
-
Semi-supervised Automatic Segmentation of Layer and fluid region in Retinal Optical Coherence Tomography Images Using Adversarial Learning
摘要： Optical coherence tomography (OCT) is a primary imaging technique for ophthalmic diagnosis due to its advantages in high resolution and non-invasiveness. Diabetes is a chronic disease, which could cause retinal layer deformation and fluid accumulation. It might increase the risk of blindness, and thus, it is important to monitor the morphology change of the retinal layer and fluid accumulation for diabetes patients. Due to the existence of deformation and fluid accumulation, the retinal layer and fluid region segmentation in the OCT image is a challenging task. Machine learning-based segmentation methods have been proposed, but they depend on a significant number of pixel-level annotated data, which is often unavailable. In this paper, we proposed a new semi-supervised fully convolutional deep learning method for segmenting retinal layers and fluid regions in retinal OCT B-scans. The proposed semi-supervised method leverages the unlabeled data through an adversarial learning strategy. The segmentation method includes a segmentation network and a discriminator network, and both the networks are with U-Net alike fully convolutional architecture. The objective function of the segmentation network is a joint loss function, including multi-class cross entropy loss, dice overlap loss, adversarial loss, and semi-supervised loss. We show that the discriminator network and the use of unlabeled data can improve the performance of segmentation. The proposed method is investigated on the duke Diabetic Macular Edema dataset and the POne dataset, and the experiment results demonstrate that our method is more effective than the other state-of-the-art methods for layers and fluid segmentation in the OCT images.
关键词： image processing,optical coherence tomography,layer segmentation,Adversarial learning,convolutional neural networks
更新于2025-09-23 15:22:29
-
[IEEE ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, AB (2018.4.15-2018.4.20)] 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - A New Proximal Method for Joint Image Restoration and Edge Detection with the Mumford-Shah Model
摘要： In this paper, we propose an adaptation of the PAM algorithm to the minimization of a nonconvex functional designed for joint image denoising and contour detection. This new functional is based on the Ambrosio–Tortorelli approximation of the well-known Mumford–Shah functional. We motivate the proposed approximation, offering flexibility in the choice of the possibly non-smooth penalization, and we derive closed form expression for the proximal steps involved in the algorithm. We focus our attention on two types of penalization: ?1-norm and a proposed quadratic-?1 function. Numerical experiments show that the proposed method is able to detect sharp contours and to reconstruct piecewise smooth approximations with low computational cost and convergence guarantees. We also compare the results with state-of-the-art relaxations of the Mumford–Shah functional and a recent discrete formulation of the Ambrosio–Tortorelli functional.
关键词： Ambrosio–Tortorelli,non-smooth optimization,Segmentation,proximal algorithm,restoration
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Colour Constancy for Image of Non-Uniformly Lit Scenes
摘要： This paper presents a colour constancy algorithm for images of scenes lit by non-uniform light sources. The proposed method determines number of colour regions within the image using a histogram-based algorithm. It then applies the K-means++ algorithm on the input image, dividing the image into its segments. The proposed algorithm computes the normalized average absolute difference (NAAD) for each segment’s coefficients and uses it as a measure to determine if the segment’s coefficients have sufficient colour variations. The initial colour constancy adjustment factors for each segment with sufficient colour variation is calculated based on the principle that the average values of colour components of the image are achromatic. The colour constancy adjustment weighting factors (CCAWF) for each pixel of image are determined by fusing the CCAWFs of the segments’ with sufficient colour variations, weighted by their normalized Euclidian distance of the pixel from the center of the segments. Experimental results were generated using both indoor and outdoor benchmark images from the scene illuminated by single or multiple illuminants. Results show that the proposed method outperforms the state of the art techniques subjectively and objectively.
关键词： multi-illuminants,fusion,k-means segmentation,colour constancy
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Main Aortic Segmentation from CTA with Deep Feature Aggregation Network
摘要： In this study, we propose a Deep Feature Aggregation network (DFA-Net) for main aortic segmentation from CTA(Computed Tomography Angiography) by aggregating features from forwarding layers to leverage more visual information. To practically verify the effectiveness of our method, we collect 90 CTA volumes from Beijing AnZhen Hospital up to over 60 thousands 2-D slices. First, we use a level-set based algorithm to efficiently generate the dataset for training and validating the deep model. Then the dataset is divided into three parts, 70 instances are used for training and 5 instances are used for validating the best parameters, and the rest 15 instances are used for testing the generalization of the model. Finally, the testing result shows that mIoU(mean Intersection-over-Union) of the segmentation result is 0.943, which indicates that by properly aggregating more visual features in a deep network the segmentation model can achieve state-of-the-art performance.
关键词： CTA,feature aggregation,level set,main aortic segmentation
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - A Novel MRA-Based Framework For Detecting Correlation Between Cerebrovascular Changes and Mean Arterial Pressure
摘要： Systemic hypertension is a signi?cant contributor for strokes and cognitive impairment and is a leading cause of mortality in the USA. Changes in cerebral vascular diameter and cerebral perfusion pressure have been reported to precede elevation of systemic blood pressures. A novel, non-invasive Time-of-Flight - Magnetic Resonance Angiography (TOF-MRA) based framework for detection of cerebrovascular changes is presented. The proposed framework analyzes brain TOF-MRA data to quantify changes in cerebral vascular diameter and cerebral perfusion pressure. The framework has three major steps: 1) Adaptive segmentation to extract large and small diameter cerebral vessels from TOF-MRA images using both appearance and 3-D spatial information of the vascular system; 2) Estimation of the Cumulative Distribution Function (CDF) of the 3-D distance map of the cerebral vascular system, which represents the changes in diameter of the 3-D vascular system ; and 3) Statistical and correlation analysis that measured the effect of Mean Arterial Pressure (MAP) on blood vessels’ diameter changes. The ef?cacy of the framework was evaluated using MRA images and blood pressure (BP) measurements obtained from 15 patients (M=8, F=7, Age=49.2±7.3 years) on Day 0 and Day 700. The framework had a dice similarity coef?cient of 92.23%, a sensitivity of 94.8% and a speci?city of ～ 99% in detecting elevated vascular pressures compared to ground truth. Statistical analysis demonstrated an inverse relationship between blood vessels diameters and MAP. This correlation was valid for both upper (above the circle of Willis) and lower (circle of Willis and below) sections of the brain. The proposed methodology may be used to quantify changes in cerebral vasculature and cerebral perfusion pressure non-invasively through MRA image analysis, which may be a useful tool for clinicians to optimize medical management of pre-hypertension and hypertension.
关键词： Vessel Diameter,Skull Stripping,CDF,Automatic Segmentation,Mean Arterial Pressure,Blood Vessels,MRA,Hypertension,Median Vascular Radius
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - An RGB-D video-based wire detection tool to aid robotic arms during machine alignment measurement
摘要： Industrial equipment may require precise alignment of components in order to function properly. In this work, we consider the machine alignment of a beamline in a research facility where an autonomous measurement system is used to execute these machine alignment procedures. The system consists of two robotic arms equipped with laser sensors placed at their ends which with the help of fiducial markers, are used by a camera system to calculate the position of the machine with respect to a stretched wire installed on top of the machines. In this work we propose a wire detection tool that assists the measurement process by detecting the line automatically through RGB-D images. Although the system was implemented for the specific application of beam line component alignment in the LHC tunnel, the same principle can be used in various other applications requiring detection of fine lines at a close distance.
关键词： robotics,depth segmentation,image processing
更新于2025-09-23 15:22:29