Graph Cut Research Articles

Graph based method for cell segmentation and detection in live-cell fluorescence microscope imaging

Live-cell fluorescence image segmentation is an essential step in many studies, including in drug research and other contexts where keeping cells alive is crucial. Several segmentation algorithms and programs have been previously proposed; however, they do not work sufficiently well on top-down pictures with overlapping cells. Our proposed algorithm, called GRABaCELL, utilizes Graph Cut, Watershed segmentation and Hough Circular Transform to improve automatic segmentation and counting living cells. We also introduce a modified accuracy metric to determine the quality of segmentation in terms of the number of cells detected in the image. The GRABaCELL method results are vastly better in visual assessment, by both Dice index and modified accuracy metric, than all other compared methods maintaining not only a high value of these indices but also a relatively small spread.

Water Extraction in SAR Images Using Features Analysis and Dual-Threshold Graph Cut Model

Timely identifying and detecting water bodies from SAR images are significant for flood monitoring and water resources management. In recent decades, deep learning has been applied to water extraction but is subject to the large difficulty of acquiring SAR dataset of various water bodies types, as well as heavy labeling work. In addition, the traditional methods mostly occur over the large, open lakes and rivers, rarely focusing on complex areas such as the urban water, and cannot automatically acquire the classification threshold. To address these issues, a novel water extraction method is proposed with high accuracy in this paper. Firstly, a multiscale feature extraction using a Gabor filter is conducted to reduce the noise and roughly identify water feature. Secondly, we apply the Otsu algorithm as well as a voting strategy to initially extract the homogeneous regions and for subsequent Gaussian mixture model (GMM). Finally, the dual threshold is obtained from the fitted Gaussian distribution of water and non-water, which is integrated into the graph cut model to redefine the weights of the edges, then constructing the energy function of the water map. The dual-threshold graph cut (DTGC) model precisely pinpoints the water location by minimizing the energy function. To verify the efficiency and robustness, our method and comparison methods, including the IGC method and IACM method, are tested on six different types of water bodies, by performing the accuracy assessment via comparing outcomes with the manually labeled ground truth. The qualitative and quantitative results show that the overall accuracy of our method for the whole dataset all surpasses 99%, along with an obvious improvement of the Kappa, F1-score, and IoU indicators. Therefore, DTGC method has the absolute advantage of automatically capturing water maps in different scenes of SAR images without specific prior knowledge and can also determine the optimal threshold range.

A novel k-mean clustering based graph cut for brain MR image segmentation

Image Segmentation is an influential method to detect and distinguish the diseased and normal sections of an image. Image segmentation extracts the regions of interest for precise diagnosis of tumours and scheduling appropriate line of treatment. The distinct tumours in brain have varied outlies, position and intensity values. Consequently, it is difficult to develop a common technique for brain MRI segmentation. Moreover, the extraction of anomalies from the brain MRI turns out to be a challenging task. In this research, we have developed a self-regulating method for selection of seed points for partitioning the graph of MR images with tumor to attain graph cut segmentation. The proposes method overcomes the key problem of primary seed point selection by utilizing the balanced brain layout and combines k - mean clustering into graph cut for segmenting an image. The outcomes attained by the proposed technique facilitates improved segmentation of the diseased region.

Sensor-based image manipulation localization with Discriminative Random fields and Graph Cut

We present PRNU-based image manipulation localization as a probabilistic labeling task in a flexible discriminative random field (DRF) setup. Instead of reaching local decisions independent of each other, discriminative random fields incorporate local inter-label dependencies while keeping the formulation general enough to make label assignments depend on both local and non-local image characteristics. With an improved form of association potential combining normalized correlation and the deviation of the measured correlation from the expected correlation and an interaction potential defined as the weighted L2 norm squared between intensities of neighboring pixels, we were able to localize even considerably small manipulations on realistic tampered images. We experimented with different combinations of window sizes to capture features to predict the correlation more accurately than already existing algorithms. Experimental results indicate that our algorithm outperforms recent state of the art methods based on multiscale analysis strategies. We also found that for inspecting manipulated images which are JPEG compressed, it helps to train the predictor with JPEG images rather than with uncompressed images and for all quality factors, it is possible to work with two predictors, one trained for images with lower quality factors and another for higher quality factors.

Efficient image segmentation performance of gray-level image using normalized graph cut based neutrosophic membership function

The study of image segmentation is a crucial impression in image processing and computer vision appliances, which segments an input image into distinct non-overlapping homogenous divisions and helps to depict the image more conveniently. To improve the performance of the segmentation of gray-level images by introducing a normalized graph cut measure as a thresholding principle to separate an object from the background based on the neutrosophic membership function. We proposed an innovative neutrosophic approach combining a set of features of some efficient algorithms. The implementation of the proposed algorithm is known as the neutrosophic normalized graph cut (NNGC) method. In the gray image segmentation, the problem of wrongly segmentation and segmentation with low accuracy can identify by using this approach. This proposed algorithm is compared with the fuzzy entropy method, neutrosophic graph cut (NGC), classical graphcut, Otsu, and Kittler method. Moreover, we examine that in most cases, our algorithm gives the lowest absolute error, misclassification error, and higher values of signal to noise ratio values that improve the segmentation process of gray images. Finally, we analyze the change of different parameter values in the NNGC and the effect of the substitutes. Also, we discuss the computational complexity of neutrosophic weight matrix results with a weight matrix (classical) results.

Robust Real Time Multiple Human Detection and Tracking for Automatic Visual Surveillance System

Detection of human for visual surveillance system provides most important rule for advancement in the design of future automation systems. Human detection and tracking are important for future automatic visual surveillance system (AVSS). In this paper we have proposed a flexible technique for proper human detection and tracking for the design of AVSS. We used graph cut for segment human as a foreground image by eliminating background, extract some feature points by using HOG, SVM classifier for proper classification and finally we used particle filter for tracking those of detected human. Our system can easily detect and track humans in poor lightening conditions, color, size, shape, and clothing due to the use of HOG feature descriptor and particle filter. We use graph cut based segmentation technique, therefore our system can handle occlusion at about 88%. Due to the use of HOG to extract features our system can properly work in indoor as well as outdoor environments with 97.61% automatic human detection and 92% automatic human detection and tracking accuracy of multiple human

Scalable Surface Reconstruction with Delaunay‐Graph Neural Networks

AbstractWe introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real‐life Multi‐View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line‐of‐sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real‐life acquisitions. Combining the efficiency of deep learning methods and the scalability of energy‐based models, our approach outperforms both learning and non learning‐based reconstruction algorithms on two publicly available reconstruction benchmarks.

An improved graph cut algorithm in stereo matching

In stereo matching tasks, the matching effect is often very poor when the texture of the region is weak or repeated. To solve this problem, an improved Graph Cut stereo matching algorithm based on Census transform is proposed. The Hamming distance of the corresponding pixels in the left and right images after Census transform is introduced as the similarity measure in the data term of the energy function. In this way, the dependence on the pixel value is reduced. The stereo matching experiments are implemented on the standard images of Middlebury stereo benchmark and the real scene images, and it demonstrates that our algorithm is robust and can obtain better performance in weak texture or repeated texture region.

Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network.

Purpose: The purpose of this study was to develop and evaluate lung cancer segmentation with a pretrained model and transfer learning. The pretrained model was constructed from an artificial dataset generated using a generative adversarial network (GAN). Materials and Methods: Three public datasets containing images of lung nodules/lung cancers were used: LUNA16 dataset, Decathlon lung dataset, and NSCLC radiogenomics. The LUNA16 dataset was used to generate an artificial dataset for lung cancer segmentation with the help of the GAN and 3D graph cut. Pretrained models were then constructed from the artificial dataset. Subsequently, the main segmentation model was constructed from the pretrained models and the Decathlon lung dataset. Finally, the NSCLC radiogenomics dataset was used to evaluate the main segmentation model. The Dice similarity coefficient (DSC) was used as a metric to evaluate the segmentation performance. Results: The mean DSC for the NSCLC radiogenomics dataset improved overall when using the pretrained models. At maximum, the mean DSC was 0.09 higher with the pretrained model than that without it. Conclusion: The proposed method comprising an artificial dataset and a pretrained model can improve lung cancer segmentation as confirmed in terms of the DSC metric. Moreover, the construction of the artificial dataset for the segmentation using the GAN and 3D graph cut was found to be feasible.

Multi-class medical image segmentation using one-vs-rest graph cuts and majority voting.

Purpose: Semi-automatic image segmentation is still a valuable tool in clinical applications since it retains the expert oversights legally required. However, semi-automatic methods for simultaneous multi-class segmentation are difficult to be clinically implemented due to the complexity of underlining algorithms. We purpose an efficient one-vs-rest graph cut approach of which the complexity only grows linearly as the number of classes increases. Approach: Given an image slice, we construct multiple one-vs-rest graphs, each for a tissue class, for inference of a conditional random field (CRF). The one-vs-rest graph cut is to minimize the CRF energy derived from regional and boundary class probabilities estimated from random forests to obtain a one-vs-rest segmentation. The final segmentation is obtained by fusing from those one-vs-rest segmentations based on majority voting. We compare our method to a well-used multi-class graph cut method, alpha-beta swap, and a fully connected CRF (FCCRF) method, in brain tumor segmentation of 20 high-grade tumor cases in 2013 MICCAI dataset. Results: Our method achieved mean Dice score of 0.83 for whole tumor, compared to 0.80 by alpha-beta swap and 0.79 by FCCRF. There was a performance improvement over alpha-beta swap by a factor of five. Conclusions: Our method utilizes the probabilistic-based CRF which can be estimated from any machine learning technique. Comparing to traditional multi-class graph cut, the purposed one-vs-rest approach has complexity that grows only linearly as the number of classes increases, therefore, our method can be applicable for both online semi-automatic and offline automatic segmentation in clinical applications.

GoRG: Towards a GPU-Accelerated Multiview Hyperspectral Depth Estimation Tool for Medical Applications.

HyperSpectral (HS) images have been successfully used for brain tumor boundary detection during resection operations. Nowadays, these classification maps coexist with other technologies such as MRI or IOUS that improve a neurosurgeon’s action, with their incorporation being a neurosurgeon’s task. The project in which this work is framed generates an unified and more accurate 3D immersive model using HS, MRI, and IOUS information. To do so, the HS images need to include 3D information and it needs to be generated in real-time operating room conditions, around a few seconds. This work presents Graph cuts Reference depth estimation in GPU (GoRG), a GPU-accelerated multiview depth estimation tool for HS images also able to process YUV images in less than 5.5 s on average. Compared to a high-quality SoA algorithm, MPEG DERS, GoRG YUV obtain quality losses of −0.93 dB, −0.6 dB, and −1.96% for WS-PSNR, IV-PSNR, and VMAF, respectively, using a video synthesis processing chain. For HS test images, GoRG obtains an average RMSE of 7.5 cm, with most of its errors in the background, needing around 850 ms to process one frame and view. These results demonstrate the feasibility of using GoRG during a tumor resection operation.

Fast and robust interactive image segmentation in bilateral space with reliable color modeling and higher order potential

We propose an optimization framework for interactive image segmentation (IIS) that operates in bilateral space to achieve robust object extraction and instant visual feedback. More specifically, we first resample an input image using a regular bilateral grid with a resolution that is typically coarser than the input image to reduce the complexity of subsequent IIS tasks. We then design a Markov random field energy on the vertices of the bilateral grid that can be solved efficiently using a standard graph cut label assignment. To achieve this, we introduce reliable color models to distinguish the foreground and background despite the presence of extremely difficult cases and a higher-order potential to encourage spatial consistency in segmentation. We conduct comprehensive experiments on three standard interactive segmentation datasets, MSRA 10K, IIS, and PASCAL VOC 2012 segmentation validation set. The results show that the proposed method achieves competitive performance compared with state-of-the-art methods while making the current system efficient in terms of speed.

A robust discriminative multi-atlas label fusion method for hippocampus segmentation from MR image

Accurate and automatic segmentation of the hippocampus plays a vital role in the diagnosis and treatment of nervous system diseases. However, due to the anatomical variability of different subjects, the registered atlas images are not always perfectly aligned with the target image. This makes the segmentation of the hippocampus still face great challenges. In this paper, we propose a robust discriminative label fusion method under the multi-atlas framework. It is a patch embedding label fusion method based on conditional random field (CRF) model that integrates the metric learning and the graph cuts by an integrated formulation. Unlike most current label fusion methods with fixed (non-learning) distance metrics, a novel distance metric learning is presented to enhance discriminative observation and embed it into the unary potential function. In particular, Bayesian inference is utilized to extend a classic distance metric learning, in which large margin constraints are instead of pairwise constraints to obtain a more robust distance metric. And the pairwise homogeneity is fully considered in the spatial prior term based on classification labels and voxel intensity. The resulting integrated formulation is globally minimized by the efficient graph cuts algorithm. Further, sparse patch based method is utilized to polish the obtained segmentation results in label space. The proposed method is evaluated on IABA dataset and ADNI dataset for hippocampus segmentation. The Dice scores achieved by our method are 87.2%, 87.8%, 88.2% and 88.9% on left and right hippocampus on both two datasets, while the best Dice scores obtained by other methods are 86.0%, 86.9%, 86.8% and 88.0% on IABA dataset and ADNI dataset respectively. Experiments show that our approach achieves higher accuracy than state-of-the-art methods. We hope the proposed model can be transferred to combine with other promising distance measurement algorithms.

Semi-automatic liver tumor segmentation with adaptive region growing and graph cuts

Segmenting liver tumors from computed tomography (CT) images plays a very important role in computer-aided diagnosis, surgical planning, and treatment monitoring. However, accurate and robust segmentation of the tumors remains a challenging issue, due to low contrast and vague boundaries between the tumors and surrounding tissues as well as the wide variations of the tumors in intensity, shape, and location across patients. In this paper, we developed an effective method for liver tumor segmentation with adaptive region growing and graph cuts. First, initial segmentation results for liver tumors and the regions of interest (ROIs) that contain the tumors are extracted by adaptive region growing with a manual selected seed specified for each tumor region. Then, the ROIs are enhanced by Gaussian fitting based nonlinear mapping according to the intensity distributions of the initially segmented tumor regions. Finally, the enhanced information combined with gradient information is integrated into graph cuts to extract the tumors from the ROIs effectively and accurately. The method is non-sensitive to noise and does not involve a pre-segmentation of liver or a complicated and tedious procedure of training. Results on 3Dircadb dataset demonstrate that the method achieves much better comprehensive performance on liver tumor segmentation compared with many art-of-state methods and has a huge advantage in segmenting the tumors with low contrast, small size, and weak boundaries.

Time series analysis of multispectral satellite images using game theory classifier

Change information of the earth’s surface obtained from time series analysis of remote sensing images becoming more important in monitoring the local and global resources. In this paper, time series analysis of multispectral images by the combinations of hybrid graph cut segmentation (HGCS) and game theory (GT) classifier is proposed. Segmentation in satellite images can be posed as a problem of pixel intensity clustering. The traditional segmentation algorithms suffer from random initialization which may yields local optimum results. To overcome this, HGCS is used for segmentation which provides more stability and improved performance. The performance of traditional classifier depends on size of data set, number of observations and features. The size of the feature space strongly increases when multitemporal images are analyzed, which makes the classifier fail to find the correct solution. To find the optimum solution, game theory classifier is proposed. The proposed method explores and exploits the advantages of both hybrid graph cut segmentation and game theory classifier. The superiority of the approach has been demonstrated over a multitemporal LANDSAT images both visually and numerically with statistical support. The results have been compared with several traditional algorithms, viz. misclassification rate, CPSNR, CMSE and validity index.

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory.

Remarkable progress in the development of modeling methods for indoor spaces has been made in recent years with a focus on the reconstruction of complex environments, such as multi-room and multi-level buildings. Existing methods represent indoor structure models as a combination of several sub-spaces, which are constructed by room segmentation or horizontal slicing approach that divide the multi-room or multi-level building environments into several segments. In this study, we propose an automatic reconstruction method of multi-level indoor spaces with unique models, including inter-room and inter-floor connections from point cloud and trajectory. We construct structural points from registered point cloud and extract piece-wise planar segments from the structural points. Then, a three-dimensional space decomposition is conducted and water-tight meshes are generated with energy minimization using graph cut algorithm. The data term of the energy function is expressed as a difference in visibility between each decomposed space and trajectory. The proposed method allows modeling of indoor spaces in complex environments, such as multi-room, room-less, and multi-level buildings. The performance of the proposed approach is evaluated for seven indoor space datasets.

Automatic brain tumor segmentation for a computer‐aided diagnosis system

AbstractBrain structure segmentation, including tumors, in medical imaging has become a necessity to help neurologists correctly diagnose patients' conditions. The complexity of these structures requires the implementation of automatic segmentation methods, often developed by magnetic resonance imaging. This study aims to design and implement an automatic system for detecting and localizing tumor regions by combining three different methods. Firstly, the region of interest, that is, the pixels belonging to the tumor, is detected using Random Forest's algorithm, while the rest of the pixels of the image are considered to belong to the background. Thus, the tumor and background seeds are obtained, automatically, for segmentation using the Graph Cut method. This segmentation allows to obtain the initial contour, for the level set (LVS) segmentation, which refine the previous segmentation. The proposed method was validated on the Multimodal Brain Tumor Segmentation Challenge (BRATS) database (http://braintumorsegmentation.org; 2015).

Mosaicking of mountain tunnel images guided by laser rangefinder

Routine tunnel inspection is important for timely maintaining tunnels and ensuring traffic safety. Owing to the insufficient field of view of one camera, an array of cameras has been employed to acquire multiple tunnel images simultaneously, which are then stitched together to obtain an overall tunnel lining image (TLI) of the complete defects and facilities on the lining surface. However, due to the features inadequacy on the poorly-textured surface, a traditional feature-based mosaicking of multiple images does not work for most tunnel images. Based on the guidance of a laser rangefinder (LRF), this study proposes stitching tunnel images from a geometric perspective involving three steps: extrinsic calibration, coarse mosaicking, and fine mosaicking. Using a checkerboard, the extrinsic parameters of the cameras relative to the LRF are calibrated. The LRF range profile is used to construct a 3D tunnel model, through which a lookup table (LUT) is generated to stitch the tunnel images geometrically, resulting in a coarse TLI. Finally, to reduce misalignments from inaccurate calibration, optional graph cuts are made to optimise the coarse mosaicking if evident features exist in the overlapped areas between images. The proposed technique is tested on actual images collected from the Dingxi tunnel and the Huang Longshan tunnel in China. The experimental results show that the proposed algorithm can obtain the TLI with little geometrical distortion and ensure structural consistency in the features, even if auxiliary facilities are densely distributed on the inner surface of tunnels. The time required for stitching the tunnel images can be improved by 82×, achieving 0.52 s per TLI, if graph cuts are not required.

Classification of Healthy Control and Abnormal Lung Chest Radiography images using CBIR and Atlas-Based Graph cut Segmentation by Transfer Learning CNNs

The prominent aim of systematic lung pathologies detection is to improve health outcomes among people with pulmonary diseases and decrease thorax diseases disseminating among the peoples through improved lung abnormality detection, reduction in diagnostic delays and early treatment. Today technological breakthroughs have led to the discovery of various invasive clinical imaging methods for the analysis of lung diseases. In this work, an integrated Computer-Aided Diagnoses (CAD) based on Deep Learning (DL) to diagnosis of lung diseases on chest radiographs was proposed. In this paper we have used JSRT datasets it contains 247 images are employed atlas-based graph-cut segmentation algorithm for extract the lung regions and segmented regions are input to the Convolutional Neural Network (CNN) with augmentation techniques that are provides the training accuracy is 97% and 89% for testing accuracy.

PERFORMANCE COMPARISON OF UNSUPERVISED SEGMENTATION ALGORITHMS ON RICE, GROUNDNUT, AND APPLE PLANT LEAF IMAGES

This paper focuses on plant leaf image segmentation by considering the aspects of various unsupervised segmentation techniques for automatic plant leaf disease detection. The segmented plant leaves are crucial in the process of automatic disease detection, quantification, and classification of plant diseases. Accurate and efficient assessment of plant diseases is required to avoid economic, social, and ecological losses. This may not be easy to achieve in practice due to multiple factors. It is challenging to segment out the affected area from the images of complex background. Thus, a robust semantic segmentation for automatic recognition and analysis of plant leaf disease detection is extremely demanded in the area of precision agriculture. This breakthrough is expected to lead towards the demand for an accurate and reliable technique for plant leaf segmentation. We propose a hybrid variant that incorporates Graph Cut (GC) and Multi-Level Otsu (MOTSU) in this paper. We compare the segmentation performance implemented on rice, groundnut, and apple plant leaf images for various unsupervised segmentation algorithms. Boundary Displacement error (BDe), Global Consistency error (GCe), Variation of Information (VoI), and Probability Rand index (PRi), are the index metrics used to evaluate the performance of the proposed model. By comparing the outcomes of the simulation, it demonstrates that our proposed technique, Graph Cut based Multi-level Otsu (GCMO), provides better segmentation results as compared to other existing unsupervised algorithms.