Robust Segmentation Algorithm Research Articles

Structural Analysis of Glazed Tubular Tiles of Oriental Architectures Based on 3D Point Clouds for Cultural Heritage

Abstract. Laser scanning, along with its resultant 3D point clouds, constitutes a prevalent method for the documentation of cultural heritage. This paper introduces a novel workflow for the structural analysis of glazed tubular tiles that adorn the roofs of historical buildings in the Orient, utilizing 3D point clouds. The workflow integrates a robust segmentation algorithm utilizing the maximum principal curvature and normal vectors. Moreover, clustering algorithms, including DBSCAN, are incorporated to refine the clusters and thus increase segmentation accuracy. Structural analysis is enabled by cylindrical model fitting, which allows for the estimation of parameters and residuals. While the results exhibit commendable performance in individual tile segmentation, it is imperative to address the impact of substantial variations in scanning range and incident angles before engaging in the structural analysis fitting process. The results of experiment demonstrate that under conditions of significantly large scanning angles, the root mean square error (RMSE) for inadequately fitted tiles can extend to 0.066 m, surpassing twice the RMSE observed for well-fitted tiles. The proposed workflow proves to be applicable and exhibits significant potential to advance practices in cultural heritage documentation.

Hepatic and portal vein segmentation with dual‐stream deep neural network

AbstractBackgroundLiver lesions mainly occur inside the liver parenchyma, which are difficult to locate and have complicated relationships with essential vessels. Thus, preoperative planning is crucial for the resection of liver lesions. Accurate segmentation of the hepatic and portal veins (PVs) on computed tomography (CT) images is of great importance for preoperative planning. However, manually labeling the mask of vessels is laborious and time‐consuming, and the labeling results of different clinicians are prone to inconsistencies. Hence, developing an automatic segmentation algorithm for hepatic and PVs on CT images has attracted the attention of researchers. Unfortunately, existing deep learning based automatic segmentation methods are prone to misclassifying peripheral vessels into wrong categories.PurposeThis study aims to provide a fully automatic and robust semantic segmentation algorithm for hepatic and PVs, guiding subsequent preoperative planning. In addition, to address the deficiency of the public dataset for hepatic and PV segmentation, we revise the annotations of the Medical Segmentation Decathlon (MSD) hepatic vessel segmentation dataset and add the masks of the hepatic veins (HVs) and PVs.MethodsWe proposed a structure with a dual‐stream encoder combining convolution and Transformer block, named Dual‐stream Hepatic Portal Vein segmentation Network, to extract local features and long‐distance spatial information, thereby extracting anatomical information of hepatic and portal vein, avoiding misdivisions of adjacent peripheral vessels. Besides, a multi‐scale feature fusion block based on dilated convolution is proposed to extract multi‐scale features on expanded perception fields for local features, and a multi‐level fusing attention module is introduced for efficient context information extraction. Paired t‐test is conducted to evaluate the significant difference in dice between the proposed methods and the comparing methods.ResultsTwo datasets are constructed from the original MSD dataset. For each dataset, 50 cases are randomly selected for model evaluation in the scheme of 5‐fold cross‐validation. The results show that our method outperforms the state‐of‐the‐art Convolutional Neural Network‐based and transformer‐based methods. Specifically, for the first dataset, our model reaches 0.815, 0.830, and 0.807 at overall dice, precision, and sensitivity. The dice of the hepatic and PVs are 0.835 and 0.796, which also exceed the numeric result of the comparing methods. Almost all the p‐values of paired t‐tests on the proposed approach and comparing approaches are smaller than 0.05. On the second dataset, the proposed algorithm achieves 0.749, 0.762, 0.726, 0.835, and 0.796 for overall dice, precision, sensitivity, dice for HV, and dice for PV, among which the first four numeric results exceed comparing methods.ConclusionsThe proposed method is effective in solving the problem of misclassifying interlaced peripheral veins for the HV and PV segmentation task and outperforming the comparing methods on the relabeled dataset.

Joint learning framework of superpixel generation and fuzzy sparse subspace clustering for color image segmentation

Sparse subspace clustering (SSC) is an important image segmentation method that constructs a self-representation coefficient matrix to represent the relationships between pixels, and then uses spectral clustering to achieve clustering. Compared with other unsupervised segmentation algorithms, SSC has good segmentation performance. However, SSC has a high computational complexity when processing large-sized image. To improve computational efficiency, many researchers have proposed superpixel-based SSC algorithms, which process superpixels instead of pixels and improve efficiency through preprocessing. Due to the sensitivity of superpixel generation to noise, superpixel-based SSC algorithms still have poor robustness. Additionally, preprocessing increases the complexity of the algorithm. To address these issues, this paper proposes a robust superpixel-based fuzzy sparse subspace clustering algorithm. This algorithm combines fuzzy sparse subspace clustering with superpixel generation, and it constructs a unified optimization learning framework through fuzzy C-multiple-means clustering to improve segmentation performance and reduce complexity. Additionally, this paper introduces additional features of superpixel in sparse subspace clustering to further enhance the segmentation performance of the algorithm. Experiment results indicate that the proposed algorithm not only outperforms existing state-of-the-art robust segmentation algorithms independent of superpixels, but also is superior to the latest superpixel-based segmentation algorithms.

Reconstruction-Aware Kernelized Fuzzy Clustering Framework Incorporating Local Information for Image Segmentation

Kernelized fuzzy C-means clustering with weighted local information is an extensively applied robust segmentation algorithm for noisy image. However, it is difficult to effectively solve the problem of segmenting image polluted by strong noise. To address this issue, a reconstruction-aware kernel fuzzy C-mean clustering with rich local information is proposed in this paper. Firstly, the optimization modeling of guided bilateral filtering is given for noisy image; Secondly, this filtering model is embedded into kernelized fuzzy C-means clustering with local information, and a novel reconstruction-filtering information driven fuzzy clustering model for noise-corrupted image segmentation is presented; Finally, a tri-level alternative and iterative algorithm is derived from optimizing model using optimization theory and its convergence is strictly analyzed. Many Experimental results on noisy synthetic images and actual images indicate that compared with the latest advanced fuzzy clustering-related algorithms, the algorithm presented in this paper has better segmentation performance and stronger robustness to noise, and its PSNR and ACC values increase by about 0.16–3.28 and 0.01–0.08 respectively.

Automatic Segmentation of Abdominal Aortic Aneurysms from Time-Resolved 3D Ultrasound Images Using Deep Learning.

Abdominal aortic aneurysms (AAAs) are rupture-prone dilatations of the aorta. In current clinical practice, the maximal diameter of AAAs is monitored with 2D ultrasound to estimate their rupture risk. Recent studies have shown that 3-dimensional and mechanical AAA parameters might be better predictors for aneurysm growth and rupture than the diameter. These parameters can be obtained with time-resolved 3D ultrasound (3D+t US), which requires robust and automatic segmentation of AAAs from 3D+t US. This study proposes and validates a deep learning (DL) approach for automatic segmentation of AAAs. 500 AAA patients were included for follow-up 3D+t US imaging, resulting in 2495 3D+t US images. Segmentation masks for model training were obtained using a conventional automatic segmentation algorithm ('nonDL'). Four different DL models were trained and validated by (1) comparison to CT and (2) reader scoring. Performance of the nonDL and different DL segmentation strategies were evaluated by comparing Hausdorff distance, Dice scores, accuracy, sensitivity, and specificity with a sign test. All DL models had higher median Dice scores, accuracy, and sensitivity (all p < 0.003) compared to nonDL segmentation. The full image-resolution model without data augmentation showed the highest median Dice score and sensitivity (p < 0.001). Applying the DL model on an independent test group produced fewer poor segmentation scores of 1 to 2 on a five-point scale (8% for DL, 18% for nonDL). This demonstrates that a robust and automatic segmentation algorithm for segmenting abdominal aortic aneurysms from 3D+t US images was developed, showing improved performance compared to conventional segmentation.

Placental vessel segmentation and registration in fetoscopy: Literature review and MICCAI FetReg2021 challenge findings

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon’s side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.

YUTO SEMANTIC: A LARGE SCALE AERIAL LIDAR DATASET FOR SEMANTIC SEGMENTATION

Abstract. Creating virtual duplicates of the real world has garnered significant attention due to its applications in areas such as autonomous driving, urban planning, and urban mapping. One of the critical tasks in the computer vision community is semantic segmentation of outdoor collected point clouds. The development and research of robust semantic segmentation algorithms heavily rely on precise and comprehensive benchmark datasets. In this paper, we present the York University Teledyne Optech 3D Semantic Segmentation Dataset (YUTO Semantic), a multi-mission large-scale aerial LiDAR dataset specifically designed for 3D point cloud semantic segmentation. The dataset comprises approximately 738 million points, covering an area of 9.46 square kilometers, which results in a high point density of 100 points per square meter. Each point in the dataset is annotated with one of nine semantic classes. Additionally, we conducted performance tests of state-of-the-art algorithms to evaluate their effectiveness in semantic segmentation tasks. The YUTO Semantic dataset serves as a valuable resource for advancing research in 3D point cloud semantic segmentation and contributes to the development of more accurate and robust algorithms for real-world applications. The dataset is available at https://github.com/Yacovitch/YUTO_Semantic.

Lung cancer detection using RF-K-means and classification with optimized ANN algorithm

Lung cancer is one of the leading causes of mortality from cancer. Lung cancer is a kind of malignant lung tumor characterized by uncontrolled cell proliferation in lung tissues. Even though CT scans are the most often used imaging technology in medicine, clinicians find it challenging to interpret and diagnose cancer from CT scan pictures. As a result, computer-aided diagnostics can assist clinicians in precisely identifying malignant cells. Many computer-aided approaches were explored and applied, including image processing and machine learning. A comparison of the various classification methodologies will assist in enhancing the accuracy of lung cancer detection systems that employ robust segmentation and classification algorithms presented in this research. This research proposed to enhance existing segmentation and classification-basedmethodsof human lung cancer detection with optimization in techniques. The workflow includes initial preprocessing of medical images, for segmentation a novel hybrid methodology is developed by combining enhanced k-means clustering and random forest and classification with an Artificial neural network enhanced with PSO parameter and feature optimization.

Robust cardiac segmentation corrected with heuristics.

Cardiovascular diseases related to the right side of the heart, such as Pulmonary Hypertension, are some of the leading causes of death among the Mexican (and worldwide) population. To avoid invasive techniques such as catheterizing the heart, improving the segmenting performance of medical echocardiographic systems can be an option to early detect diseases related to the right-side of the heart. While current medical imaging systems perform well segmenting automatically the left side of the heart, they typically struggle segmenting the right-side cavities. This paper presents a robust cardiac segmentation algorithm based on the popular U-NET architecture capable of accurately segmenting the four cavities with a reduced training dataset. Moreover, we propose two additional steps to improve the quality of the results in our machine learning model, 1) a segmentation algorithm capable of accurately detecting cone shapes (as it has been trained and refined with multiple data sources) and 2) a post-processing step which refines the shape and contours of the segmentation based on heuristics provided by the clinicians. Our results demonstrate that the proposed techniques achieve segmentation accuracy comparable to state-of-the-art methods in datasets commonly used for this practice, as well as in datasets compiled by our medical team. Furthermore, we tested the validity of the post-processing correction step within the same sequence of images and demonstrated its consistency with manual segmentations performed by clinicians.

A Grape Dataset for Instance Segmentation and Maturity Estimation

Grape maturity estimation is vital in precise agriculture as it enables informed decision making for disease control, harvest timing, grape quality, and quantity assurance. Despite its importance, there are few large publicly available datasets that can be used to train accurate and robust grape segmentation and maturity estimation algorithms. To this end, this work proposes the CERTH grape dataset, a new sizeable dataset that is designed explicitly for evaluating deep learning algorithms in grape segmentation and maturity estimation. The proposed dataset is one of the largest currently available grape datasets in the literature, consisting of around 2500 images and almost 10 k grape bunches, annotated with masks and maturity levels. The images in the dataset were captured under various illumination conditions and viewing angles and with significant occlusions between grape bunches and leaves, making it a valuable resource for the research community. Thorough experiments were conducted using a plethora of general object detection methods to provide a baseline for the future development of accurate and robust grape segmentation and maturity estimation algorithms that can significantly advance research in the field of viticulture.

Intelligent pixel-level pavement marking detection using 2D laser pavement images

This paper proposes a robust semantic segmentation algorithm named as Marking-DNet to implement pixel-level recognition of pavement markings. The proposed Marking-DNet presents an improved encoder-decoder architecture based on DeepLabV3+. Different from DeepLabv3+, feature maps of four different scales are imported from the encoder into the decoder of Marking-DNet, resulting in more levels of information exchange. Additionally, the Object-Contextual Representation and the Convolutional Block Attention Module are both employed in Marking-DNet to conduct contextual learning more efficiently and implement spatial and channel attention explicitly. The F-measure and Intersection-Over-Union attained by the Marking-DNet on 1500 testing images are 93.59% and 87.96% respectively. Experimental results demonstrate that Marking-DNet outperforms six state-of-the-art semantic segmentation models in detecting pavement markings using both private and public image datasets. According to the performances on 5,506 pavement images, it is found that Marking-DNet can detect various complex pavement markings accurately, except for some heavily-worn markings.

Robust and Accurate Iris Segmentation Algorithm for Color and Noisy Eye Images

Efficient and robust segmentation of iris images captured in the uncontrolled environments is one of the challenges of non-cooperative iris recognition systems. We address this problem by proposing a novel iris segmentation algorithm, which is suitable both for monochrome and color eye images. The method presented use modified Hough transform to roughly localize the possible iris and pupil boundaries, approximating them by circles. A voting mechanisms is applied to select a candidate iris regions. The detailed iris boundary is approximated by the spline curve. Its shape is determined by minimizing introduced boundary energy function. The described algorithm was submitted to the NICE.I iris image segmentation contest, when it was ranked 11th and 10th out of total 97.

A knee point driven Kriging-assisted multi-objective robust fuzzy clustering algorithm for image segmentation

To enhance the segmentation performance and optimization efficiency of multi-objective evolutionary clustering algorithms for noisy images, this study presents a knee point driven Kriging-assisted multi-objective robust fuzzy clustering algorithm for image segmentation (K2 MORFC). First, pixel and region-level fitness functions are developed to comprehensively consider the spatial constraints and region consistency in an image. In the pixel-level fitness function, a Kullback–Leibler (KL) divergence-based spatial constraint term is employed and combined with intra-class compactness to preserve the membership similarity between an arbitrary image pixel and its non-local neighbors. In the region-level fitness function, image edge information is utilized to evaluate the regional consistency of the partition. Moreover, an adaptive determination mechanism of the weight factor for the spatial constraint term is designed in the pixel-level fitness function to control the influence of the spatial constraint for each pixel. Furthermore, considering that the preference toward knee points can effectively improve the convergence performance, a knee point driven Kriging-assisted evolutionary algorithm (K2EA) is proposed to efficiently optimize these two fitness functions, including a dynamic subspace knee point searching strategy, a knee point guided environmental selection strategy, and a Kriging model management mechanism. Finally, we construct a fuzzy clustering validity index with a KL divergence-based non-local spatial constraint term to select the optimal solution from the nondominated solution set. Competitive experimental results on the DTLZ benchmark verify the effectiveness of K2EA. Segmentation results on color images from the Berkeley dataset and magnetic resonance images from the BrainWeb and IBSR datasets confirm the performance of K2MORFC.

Hand Gesture Recognition System for Deaf and Dumb People

Deaf and dumb people communicate using language known as Sign language. There are various sign languages but comparing to other sign languages, Indian Sign Language interpretation has got least mindfulness by researchers. Alphabets in English sign language and various phrases can be recognized using the application. It deals with images of bare hands. Hand-Gesture recognition is the ability to recognize hand-gesture. The hand gesture recognition system is solution to this problem which uses the image of hand gesture and recognize the sign present in the image. These features based on gesture analysis of the hand on which image of sign is shown and it extract slant and slope information. System provides an opportunity for deaf and dumb people to communicate with normal people effortlessly. Our research focuses on recognition of English sign language for vast reach of audience. There have been several upgrades in technology and a lot of research has been done to aid the deaf and dumb people. Aiding the cause, Deep learning along with computer vision is being used to make an impact on this cause. It can help the deaf and dumb people in communicating with others as many of us don’t know what sign language is. In this sign language recognition project, we create an kotlin application, which detects numbers from 1 to 10 and also the English alphabets. The initial step of this system is to build a database of English Sign Language. Hand gesture detection is the most determining step in each hand gesture recognition system since if we get better segmented output, better recognition rates can be achieved. The proposed system also includes efficient and robust hand segmentation and tracking algorithm to achieve finer recognition rates. Various isolated words from the Standard English sign language have been recognized using a large set of samples. In proposed system, we intend to recognize some very basic elements of sign language and to translate them to text .

Segmentation of multiple Organs-at-Risk associated with brain tumors based on coarse-to-fine stratified networks.

Delineation of Organs-at-Risks (OARs) is an important step in radiotherapy treatment planning. As manual delineation is time-consuming, labor-intensive and affected by inter- and intra-observer variability, a robust and efficient automatic segmentation algorithm is highly desirable for improving the efficiency and repeatability of OARdelineation. Automatic segmentation of OARs in medical images is challenged by low contrast, various shapes and imbalanced sizes of different organs. We aim to overcome these challenges and develop a high-performance method for automatic segmentation of 10 OARs required in radiotherapy planning for braintumors. A novel two-stage segmentation framework is proposed, where a coarse and simultaneous localization of all the target organs is obtained in the first stage, and a fine segmentation is achieved for each organ, respectively, in the second stage. To deal with organs with various sizes and shapes, a stratified segmentation strategy is proposed, where a High- and Low-Resolution Residual Network (HLRNet) that consists of a multiresolution branch and a high-resolution branch is introduced to segment medium-sized organs, and a High-Resolution Residual Network (HRRNet) is used to segment small organs. In addition, a label fusion strategy is proposed to better deal with symmetric pairs of organs like the left and right cochleas and lacrimalglands. Our method was validated on the dataset of MICCAI ABCs 2020 challenge for OAR segmentation. It obtained an average Dice of 75.8% for 10 OARs, and significantly outperformed several state-of-the-art models including nnU-Net (71.6%) and FocusNet (72.4%). Our proposed HLRNet and HRRNet improved the segmentation accuracy for medium-sized and small organs, respectively. The label fusion strategy led to higher accuracy for symmetric pairs oforgans. Our proposed method is effective for the segmentation of OARs of brain tumors, with a better performance than existing methods, especially on medium-sized and small organs. It has a potential for improving the efficiency of radiotherapy planning with high segmentationaccuracy.

Deposition path-dependent lightweight support design and its implication to self-support topology optimization

Abstract This paper presents a lightweight support design method for material extrusion-type three-dimensional printed panel structures that innovatively involves the deposition path curvature information for support point determination. Specifically, this support design method provides a robust segmentation algorithm to divide the filament deposition paths into segments based on the curvature sign alternating condition, and then searches for the fewest support points for the filaments counting on the experimentally calibrated relationship between the maximum allowable self-support distance and the local mean curvature. The proposed method features in generating thin-walled skeleton-ray styled support structures that are lightweight while providing firm support for the panels. More importantly, the support design method provides a new type of self-support criterion for structural topology optimization involving non-designable planar panels, i.e., only a sparse point set would be sufficient to support the panel. Consequently, more materials could be spent on enhancing the load-bearing capacity instead of being wasted on oversupporting. The achievable structural performances from self-support topology optimization with this new self-support criterion can improve significantly. Support design and printing tests were conducted on a few panel structures that validated the improved support effect compared with equal-volume supports generated by commercial software. Equidistant and gap-free deposited filaments, no filament collapse due to insufficient support, and no isolated voids reflect the improved support effect. The improved self-support topological design was also validated through a comparative numerical case study, and a compliance reduction of 7.76% was achieved.

Quantification of retinal artery-vein ratio for vascular disease diagnosis using spatial U-Net

The retinal &lt;span&gt;vascular morphological caliber changes reveal the signs of systemic health disorder and life threat diseases such as cardio and cerebral diseases. The quantitative vascular parameters like narrowed arteries, widened venules, reduced artery-vein ratio (AVR) have been associated with aforesaid disorders and diseases. Hence the quantitative biomarker AVR is important parameter in diagnosing variety of diseases. The accurate quantification of AVR be possible if and only if accurate classification of arteries and vein is done. In this paper, we proposed a deep learning based robust vessel segmentation and classification algorithm based on spatial &lt;br /&gt; U-Net and the accuracy of the algorithm is 97.8%. In the quantification process, this algorithm is applied on region of interest (RoI) of a fundus image and measured the AVR values using central retinal artery equivalent (CRAE) and central retinal vein equivalent (CRVE). The experimentation is carried on the digital retinal images for vessel extraction (DRIVE) dataset. The outcome of this work is the AVR observed to be &amp;gt;0.4 in normal retinal case and AVR value &amp;lt;0.4 for unhealthy case.&lt;/span&gt;

PaFSe: A Parameter-Free Segmentation Approach for 3D Fluorescent Images

Confocal fluorescent microscopy is a major tool to investigate the molecular orchestration of biomedical samples. The quality of the image acquisition depends critically on the tissue quality and thickness, the type, and concentration of antibodies used, as well as on microscope parameters. Due to these factors, intra-sample and inter-sample variability inevitably arises. Segmentation and quantification of targeted proteins can thus become a challenging process. Image processing techniques need therefore to address the acquisitions variability to minimize the risk of biases originating from changes in signal intensity, background noise, and parameterization. Here, we introduce PaFSe, a parameter-free segmentation algorithm for 3D fluorescent images. The algorithm is based on our established PRAQA approach, which evaluates the dispersion of several pixel intensity neighborhoods allowing for a statistical assessment whether individual subfields of an image can be considered as positive signal or background. PaFSe extends PRAQA by a fully automatic estimate for the segmentation parameters, and thereby provides a completely parameter-free and robust segmentation algorithm. By comparing PaFSe with Ilastik on synthetic examples, we show that our method achieves similar performances as a supervised approach in low-to-moderate noise environments without the need of tedious training. Furthermore, we validate the efficiency of PaFSe by segmenting and quantifying the abundance of hyperphosphorylated Tau protein in post-mortem human brain samples from Alzheimer’s disease patients and age-matched controls, where we obtain quantification values highly correlated with manual neuropathological segmentation. PaFSe is a parameter-free, fast, and adaptive approach for robust segmentation and quantification of protein abundance from complex 3D fluorescent images and is freely available at https://doi.org/10.17881/j20h-pa27.

Filterable sample consensus based on angle variance for pupil segmentation

Pupil segmentation is a first and important topic of iris recognition, identity recognition and eye movement information extraction for mental analysis. However, due to the negative effects of eyelash occlusion, eyelid occlusion and off-gaze deflection, making a precise pupil segmentation is a difficult task. Therefore, we propose a precise and robust algorithm for pupil segmentation, namely Angle Variance based Filterable Sample Consensus (AVBFSC), which is composed of an outlier filter and a boundary locator. The outlier filter can eliminate negative effects mentioned above, and also a best pupil segmentation is performed with our boundary locator, which learns a circular mathematical equation by selecting sub-samples from pupil edge pixels randomly. Experiment results in comparison with state-of-the-art methods on CASIA-Iris-V4-Interval dataset, indicate that our algorithm achieved best performance, that is, Accuracy of 98.99%, False Acceptance Rate (FAR) of 2.09% and Genuine Acceptance Rate (GAR) of 98.54%. In addition, it also has robust results under the condition of specific non-ideal scenes from CASIA-Iris-V4-Lamp dataset and Indian Institute of Technology Delhi (IITD) dataset including dark light conditions, eyelash occlusion, eyelid occlusion and off-gaze deflection.

Image Processing Based on Fuzzy Mathematics Theory

In order to further improve the problems of poor rationality and weak antinoise ability of existing image processing algorithms and technical algorithms, an image processing research method based on fuzzy mathematical theory is proposed. First, aiming at the ill-posed problem of the PFCM algorithm, the neutrality and rejection degree are used to construct a regular term and embed the algorithm objective function to enhance the correlation between the attribute parameters of the fuzzy set of the sample graph, so as to solve the ill-posed problem of the PFCM algorithm. Secondly, in view of the same noise sensitivity problem of PFCM algorithm as a traditional fuzzy clustering algorithm, combined with the robust ideas of FCM_S1 and FCM_S2 algorithms, the objective function of robust segmentation algorithm for graph fuzzy clustering (RPFCM_s) is constructed. The misclassification rate of the clustering algorithm proposed in this study in image segmentation is reduced by 38%–76%, and the misclassification rate of the corresponding segmentation result of the ATPFCA algorithm is reduced by 5%–77%. Therefore, the algorithm not only improves the effective segmentation efficiency of the fuzzy mathematical theory algorithm for the processing of uneven grayscale images but also enhances the anti-noise robustness of the algorithm.