Segmentation Quality Of Images Research Articles

DDFL: Dual-Domain Feature Learning for nighttime semantic segmentation

Nighttime semantic segmentation has been playing a critical role in intelligent transportation, building safety and urban management. However, nighttime scenes present some challenges such as complex structures, multiple light sources, uneven lighting and blurry image noise, which severely degrade the segmentation quality of nighttime images. To address these challenges, we propose a Dual-Domain Feature Learning (DDFL) model for nighttime semantic segmentation. Our approach introduces three innovative ideas. First, we establish an exposure correction module to address the impact of lighting differences on the model’s learning, so as to maximally restore the pixel distortion and blurry areas caused by artificial light in nighttime scenes. Second, we incorporate frequency domain information into the nighttime segmentation task to give the model stronger discrimination ability. Finally, we introduce a dual-domain fusion module to complement the information of learning from the spatial and frequency domains in a cross-fusion manner, enabling the network to perceive semantic information while preserving details. The proposed model was experimentally tested on the Nightcity, Nightcity+ and BDD100k datasets. Our results demonstrate that our model outperforms mainstream models, achieving mIoU scores of 56.73%, 57.41% and 28.97%, respectively, under different lighting, image exposure levels, and resolutions. These results show that our model is capable of segmenting nighttime scenes efficiently in a high-quality way.

Development of lung segmentation method in x-ray images of children based on TransResUNet.

Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems. In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images. The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation. Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822. This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Semi-Supervised Medical Image Segmentation Guided by Bi-Directional Constrained Dual-Task Consistency

Medical image processing tasks represented by multi-object segmentation are of great significance for surgical planning, robot-assisted surgery, and surgical safety. However, the exceptionally low contrast among tissues and limited available annotated data makes developing an automatic segmentation algorithm for pelvic CT challenging. A bi-direction constrained dual-task consistency model named PICT is proposed to improve segmentation quality by leveraging free unlabeled data. First, to learn more unmarked data features, it encourages the model prediction of the interpolated image to be consistent with the interpolation of the model prediction at the pixel, model, and data levels. Moreover, to constrain the error prediction of interpolation interference, PICT designs an auxiliary pseudo-supervision task that focuses on the underlying information of non-interpolation data. Finally, an effective loss algorithm for both consistency tasks is designed to ensure the complementary manner and produce more reliable predictions. Quantitative experiments show that the proposed PICT achieves 87.18%, 96.42%, and 79.41% mean DSC score on ACDC, CTPelvic1k, and the individual Multi-tissue Pelvis dataset with gains of around 0.8%, 0.5%, and 1% compared to the state-of-the-art semi-supervised method. Compared to the baseline supervised method, the PICT brings over 3-9% improvements. The developed PICT model can effectively leverage unlabeled data to improve segmentation quality of low contrast medical images. The segmentation result could improve the precision of surgical path planning and provide input for robot-assisted surgery.

A New Cutset-type Kernelled Possibilistic C-means Clustering Segmentation Algorithm Based on SLIC Super-pixels

: The kernelled possibilistic C-means clustering algorithm (KPCM) can effectively cluster hyper-sphere data with noise and outliers by introducing the kernelled method to the possibilistic C-means clustering (PCM) algorithm. However, the KPCM still suffers from the same coincident clustering problem as the PCM algorithm due to the lack of between-class relationships. Therefore, this paper introduces the cut-set theory into the KPCM and modifies the possibilistic memberships in the iterative process. Then a cutset-type kernelled possibilistic C-means clustering (CKPCM) algorithm is proposed to overcome the coincident clustering problem of the KPCM. Simultaneously a adaptive method of estimating the cut-set threshold is also given by averaging inter-class distances. Additionally, a cutset-type kernelled possibilistic C-means clustering segmentation algorithm based on the SLIC super-pixels (SS-C-KPCM) is also proposed to improve the segmentation quality and efficiency of the color images. Several experimental results on artificial data sets and image segmentation simulation results prove the excellent performance of the proposed algorithms in this paper.

An efficient multilevel thresholding based satellite image segmentation approach using a new adaptive cuckoo search algorithm

It is the most challenging and difficult task to segment a satellite image because of its complete randomness, multiple regions of interest, weak correlation with pixels, and regions of ambiguity. There are several Nature-inspired algorithms available, which are used to overcome these difficulties and those are more efficient to generate the best threshold value for the segmentation of satellite images. Though various modern methodologies opt for better results but methods have some drawbacks too like techniques are computationally expensive and time-consuming. In this paper, we have proposed a more effective satellite image segmentation approach using a new adaptive cuckoo search (ACS) algorithm. The result obtained from the projected technique is compared with CSMcCulloch incorporating McCulloch’s method for levy flight generation in Cuckoo Search (CS) algorithm by using two different objective functions namely Otsu’s method and Tsallis entropy function. The measurement techniques such as PSNR, MSE, FSIM, SSIM, UIQI, and computational time in term of CPU running time have been considered for validating and evaluating the proposed method. This proposed algorithm technique has resulted in improve segmentation quality of satellite images and reduced computational time. The analysis of the convergence rate proves that ACS is superior to the CSMcCulloch algorithm for reaching the global convergence rate. These experimental outcomes help to encourage researchers in different domains such as computer vision, application of medical image analysis, machine learning as well as deep learning.

Multilevel Color Image Segmentation Based on GLCM and Improved Salp Swarm Algorithm

The grayscale co-occurrence matrix (GLCM) can be adapted to segment the image according to the pixels, but the segmentation effect becomes worse as the number of threshold increases. To solve this problem, we propose an improved salp swarm algorithm (LSSA) to optimize GLCM, with the novel diagonal class entropy (DCE) as the fitness function of the GLCM algorithm. At the same time, in order to increase the optimization ability of traditional SSA algorithm, Levy flight (LF) strategy should be improved. Through experiments on the LSSA algorithm of the color natural images, the satellite images, and the Berkeley images, the segmentation quality of the segmented images is evaluated by peak signal-to-noise ratio, feature similarity, probability rand index, variation of information, global consistency error, and boundary displacement error. The experimental results show that the segmentation ability of the GLCM-LSSA algorithm is superior to other comparison algorithms and has a good segmentation ability.

A Method to Assessing the Segmentation Quality of High-spatial Resolution Remote Sensing Images by Considering Area and Position Discrepancies

A Method to Assessing the Segmentation Quality of High-spatial Resolution Remote Sensing Images by Considering Area and Position Discrepancies

Towards efficient support relation extraction from RGBD images

To extract reasonable support relations from “RGB+depth” (RGBD) images, it is very important to achieve good scene understanding. This paper proposes a novel approach to extracting accurate support relationships by analyzing the RGBD images of indoor scenes. Noting that the support relations and structure classes of indoor images are inherently related to physical stability, we construct an improved energy function that embodies this stability. We then infer the support relations and structure classes from indoor RGBD images by minimizing this energy function. Moreover, the authors succeed in improving the segmentation quality of RGBD images using the inferred results as input. Compared with previous methods, our approach produces more reasonable support relations and structure classes, where physical stability function is taken into account for resolving the optimization problem. We use the NYU-Depth2 dataset as the training data, and experimental results show that the proposed RGBD image segmentation method based on support relation abstraction produces more accurate results than segmentation methods based on ground-truth support relations.

SVMMAP Modeling of SAR Imagery for Unsupervised Segmentation with Bootstrap Sampling

A spatially variant mixture multiscale autoregressive prediction (SVMMAP) model is present, which was applied to segmentation of SAR imagery. General process is as follow: at first, by Bootstrap sampling technique a small representative set of pixels is selected; then, expectation maximization (EM) algorithm and least square (LS) estimation were used to estimate the model, and minimum description length (MDL) rule was employed to choose classification number; at last, Bayes classifier was used to segment image. For a simulated image of size 256×256, a segmentation accuracy of 99.76% was achieved. Besides, quantitative assessment was also presented about segmentation quality of images.

A novel method for assessing the segmentation quality of high-spatial resolution remote-sensing images

Image segmentation quality significantly affects subsequent image classification accuracy. It is necessary to develop effective methods for assessing image segmentation quality. In this paper, we present a novel method for assessing the segmentation quality of high-spatial resolution remote-sensing images by measuring both area and position discrepancies between the delineated image region (DIR) and the actual image region (AIR) of a scene object. In comparison with the most frequently used area coincidence-based methods, our method can assess the segmentation quality more objectively in that it takes into consideration all image objects intersecting with the AIR of a scene object. Moreover, the proposed method is more convenient to use than the existing boundary coincidence-based methods in that the calculation of the distance between the boundary of the image object and that of the corresponding AIR of the scene object is not required. Another benefit of this method over the two types of method above is that the assessment procedure of the segmentation quality can be conducted with less human intervention. The obtained optimal segmentation result can ensure maximal delineation of the extent of scene objects and can be beneficial to subsequent classification operations. The experimental results have shown the effectiveness of this new method for both segmentation quality assessment and optimal segmentation parameter selection.

FEATURE MODELLING OF HIGH RESOLUTION REMOTE SENSING IMAGES CONSIDERING SPATIAL AUTOCORRELATION

Abstract. To deal with the problem of spectral variability in high resolution satellite images, this paper focuses on the analysis and modelling of spatial autocorrelation feature. The semivariograms are used to model spatial variability of typical object classes while Getis statistic is used for the analysis of local spatial autocorrelation within the neighbourhood window determined by the range information of the semivariograms. Two segmentation experiments are conducted via the Fuzzy C-Means (FCM) algorithm which incorporates both spatial autocorrelation features and spectral features, and the experimental results show that spatial autocorrelation features can effectively improve the segmentation quality of high resolution satellite images.

Coupled Parameter Optimization of PCNN Model and Vehicle Image Segmentation

The pulse coupled neural network (PCNN) has good properties for image segmentation. While the segmentation effect significantly depends on the parameter selection of PCNN. Thus, the adaptive parameter choice is important for the PCNN application research. The coupled parameter optimization algorithm based on the coupling characteristics is proposed, which combines the neural calculation principle and characteristics of gray-scale in the image local area. First, the connection weight matrix of the PCNN model is updated in terms of the Hebb rule. Then the correlation strength factor between different regions is adaptively determined by local mean square deviation. Finally, the vehicle images are segmented by the PCNN model with optimized parameters. Compared with traditional PCNN image segmentation, the proposed method increases the coupling strength between neurons and avoids over-segmentation and under-segmentation. The segmentation quality of license plate images on the moving vehicles is improved, which lays a good foundation for the subsequent feature extraction.

Inspecting pizza topping percentage and distribution by a computer vision method

Topping percentage and distribution are two major features in the quality inspection of pizzas. The extraction of these features highly depends on the segmentation quality of pizza images. However, complex visual features and wide varieties of pizzas make the segmentation task difficult. Traditional segmentation methods are found only partly suitable for most pizza images. Therefore, a new segmentation method was developed by using the region-based segmentation as a dominant method and combining the strengths of both thresholding and edge-based segmentation methods. For evaluating the evenness of topping distribution, a practical method of dividing a pizza image into several equal-area partitions was developed. The experimental results show that the computer vision method developed is suitable for many different types of pizzas with an accuracy of over 90% for measuring topping exposure percentage and distribution.

CORRECTION EFFECTS OF MACHINE DEPENDENCY ON THE TEXTURAL PARAMETERS OF ULTRASOUND IMAGES

In this paper we presented the effect of correction of machine dependency such as LookUpTable (LUT) correction , Time-Gain-Control(TGC) correction, Diffraction and Focusing correction on the textural parameters of ultrasound images. The group of texture parameters are: histogram parameters , coocurrance matrix parameters , first order gradient parameters , grey level run length matrix parameters ,texture feature Descriptors (TFD parameters),acoustical parameters. Mapping this parameters into color coded display improve the visual inspection to the sonographers. After correction an increase of some textural parameters and decrease of others improve the visual inspection from the ultrasonograohers point of view. These results can improve the segmentation quality of the ultrasound images that will facilitate the build of 3D ultrasound images and can have an accurate measurement from the images and from the 3D data.