Salient Object Segmentation Based on Superpixel and Background Connectivity Prior

This paper investigates the application of the Simple Linear Iterative Clustering (SLIC) algorithm for complex object image segmentation, on the example of images of human body injuries. The study solves the problem of the lack of quantitative evidence regarding SLIC's algorithm performance in high-precision area and boundary assessment of the lesion on a digital image of a human body with a wound injury on it. A comprehensive methodology is developed to evaluate SLIC's algorithm efficacy across various complex images and image resolutions. The research utilizes a combined dataset of 3696 wound images from the Foot Ulcer Segmentation Challenge (FUSeg) and WoundSeg datasets. Bayesian optimization is utilized to fine-tune SLIC algorithm hyperparameters, focusing on the number of segments and compactness. Results indicate that SLIC algorithm demonstrates consistent performance across different implementations, achieving Dice scores around 0.84 and Soft Boundary F1 scores around 0.55. The study reveals that the optimal number of segments for SLIC algorithm can be defined relative to the spatial dimensions of the input image, with maximal image dimension *2 being the most effective value. A thorough analysis of various segmentation metrics is conducted, including IoU, Dice Score, and Boundary F1 Score. The research introduces and employs the Soft Boundary F1 Score – modification of Boundary F1 Score, a novel metric designed to provide a more nuanced evaluation of boundary detection accuracy while offering a smoother optimization landscape. This metric proves particularly valuable in assessing the performance of SLIC algorithm in image with complex objects on them segmentation tasks. Importantly, this research presents an idealized SLIC-based segmentation approach, where superpixels are optimally combined using ground-truth masks to establish an upper bound of performance. This idealized SLIC algorithm segmentation is compared with a pre-trained on the FUSeg dataset UNet model, showcasing superior generalization capability across diverse wound types. On the WoundSeg dataset, the idealized SLIC algorithm approach achieved a Dice score of 0.84, significantly outperforming the UNet model (0.12 Dice score). As a result, this study provides valuable insights for improving complex objects segmentation methods and highlights the need for further research on developing effective methods for superpixel classification in real-world scenarios. The findings also highlight the potential of SLIC-based approaches in addressing the challenges of diverse data types and limited training data.

Simple Linear Iterative Clustering (SLIC) algorithm is increasingly applied to different kinds of image processing because of its excellent perceptually meaningful characteristics. In order to better meet the needs of medical image processing and provide technical reference for SLIC on the application of medical image segmentation, two indicators of boundary accuracy and superpixel uniformity are introduced with other indicators to systematically analyze the performance of SLIC algorithm, compared with Normalized cuts and Turbopixels algorithm. The extensive experimental results show that SLIC is faster and less sensitive to the image type and the setting superpixel number than other similar algorithms such as Turbopixels and Normalized cuts algorithms. And it also has a great benefit to the boundary recall, the robustness of fuzzy boundary, the setting superpixel size and the segmentation performance on medical image segmentation.

To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for pre-segmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.

We present a novel, robust estimation method to distinguish salient objects from complicated, dynamic backgrounds in videos. In this method, we propose a novel approach to model motion energy based on motion magnitude, motion orientation, gradient flow field, and spatial gradient of the video frame. Furthermore, an effective spatiotemporal objectness map is also proposed to estimate a compact object-like region in the current video frame leveraging both the objectness proposals and the saliency map of the previous frame. Then the current video frame is oversegmented into the granularity of superpixels using the simple linear iterative clustering algorithm. Each superpixel is designated as a node of a graph. The similarity between adjacent superpixels will be assigned as the weight of an edge that connects these two nodes. The feature values of motion energy and spatiotemporal objectness within each superpixel will be averaged respectively, and used to graphically cluster similar superpixels to form the detected salient object. Extensive experiments comparing this proposed new method against twelve existing salient object detection (SOD) methods have been performed using the benchmark datasets unconstrained video saliency detection and densely annotated video segmentation. Superior performance of this proposed SOD method has been observed through three well-known performance metrics: precision-recall curves, F-measure curves, and the mean absolute error.

This paper presents a new virtual view synthesis method with depth map preprocessing and superpixel segmentation based hole filling. First, in order to reduce the ghosting artifacts caused by the misalignment between depth and texture, the depth image is preprocessed through expanding the regions of foreground objects. Virtual view images are then generated using the depth-image-based rendering algorithm. Second, the original reference color image is segmented into superpixels using simple linear iterative clustering algorithm. Finally, an oriented hole filling method is utilized to fill the disoccluded regions. For each hole pixel, instead of using exemplar patches, a set of candidate superpixels is selected from SLIC segmentations to form the sample space, and the best matching superpixel with the minimum cost is chosen to fill the hole. Experimental results demonstrate that comparing with the state-of-the-art methods, the subjective and objective quality of the synthesized virtual view images are substantially improved with the proposed method.

The Wide Field of View (WFV) imaging system equipped on the GaoFen-6 (GF-6) optical remote sensing satellite can acquire an image with a swath width 800 km and a resolution of 16 m, which is the largest Earth observation swath width among similar satellites in the world. With the advantages of the high spatial resolution and the wide field of view, GF-6 WFV images are widely used in agricultural resources monitoring, forestry resources investigation, and disaster relief. However, the existence of clouds is inevitable problem in GF-6 WFV images, which influences their availability. To quickly and accurately detect cloud areas in GF-6 WFV images, a cloud detection method for GF-6 WFV images based on the spectrum and variance of superpixels is proposed in the paper. First, the GF-6 WFV image is down-sampled. The simple linear iterative clustering algorithm is used to segment down-sampled images to obtain superpixels. The initial cloud detection result is obtained based on the spectrum of superpixels. Second, the initial cloud detection result is refined based on the variance of superpixels to eliminate the influence of cloud-like ground objects. Finally, the refined cloud detection result is post-processed using the region growing algorithm and expansion algorithm. The post-processed cloud detection result is up-sampled to obtain cloud detection result of the GF-6 WFV image. The experimental results show that the recall and precision of the proposed method are 84.61% and 88.46%, respectively, providing good cloud detection results for GF-6 WFV images.

Cropland classification can be used to monitor cropland distribution and its change over time. In this letter, a new superpixel-based cropland classification method is proposed for synthetic aperture radar (SAR) imagery through the integration of statistical texture, polarization, and spatial information. First, the method combines random forest algorithm and superpixels, which are generated using simple linear iterative clustering algorithm with polarization features of Pauli decomposition and spatial information. Superpixel-based spatial context information is used to reduce the influence of coherent speckle and misclassification in cropland blocks. Second, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$G^{0}$ </tex-math></inline-formula> statistical texture feature is used to reduce the interference of background targets such as woodland in cropland classification. Comparison experiments of different methods using C-band airborne SAR (AIRSAR) polarimetric data acquired in early July show that the proposed method has better classification performance, with an overall accuracy of 88.62%. The classification accuracy of corn and soybean is above 95% and 91%, respectively. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$G^{0}$ </tex-math></inline-formula> statistical texture feature is helpful to eliminate woodland that may cause crop misclassification using single-date SAR image.

Recognition of necrotic regions in MRI images of chronic spinal cord injury based on superpixel

In this study, an approach using ground control point-free unmanned aerial vehicle (UAV)-based photogrammetry is proposed to estimate the volume of stockpiles carried on barges in a dynamic environment. Compared with similar studies regarding UAVs, an indirect absolute orientation based on the geometry of the vessel is used to establish a custom-built framework that can provide a unified reference instead of prerequisite ground control points (GCPs). To ensure sufficient overlap and reduce manual intervention, the stereo images are extracted from a UAV video for aerial triangulation. The region of interest is defined to exclude the area of water in all UAV images using a simple linear iterative clustering algorithm, which segments the UAV images into superpixels and helps to improve the accuracy of image matching. Structure-from-motion is used to recover three-dimensional geometry from the overlapping images without assistance of exterior parameters obtained from the airborne global positioning system and inertial measurement unit. Then, the semi-global matching algorithm is used to generate stockpile-covered and stockpile-free surface models. These models are oriented into a custom-built framework established by the known distance, such as the length and width of the vessel, and they do not require GCPs for coordinate transformation. Lastly, the volume of a stockpile is estimated by multiplying the height difference between the stockpile-covered and stockpile-free surface models by the size of the grid that is defined using the resolution of these models. Results show that a relatively small deviation of approximately ±2% between the volume estimated by UAV photogrammetry and the volume calculated by traditional manual measurement was obtained. Therefore, the proposed approach can be considered the better solution for the volume measurement of stockpiles carried on barges in a dynamic environment because UAV-based photogrammetry not only attains superior density and spatial object accuracy but also remarkably reduces data collection time.

This paper proposes an effective salient object segmentation method via the graph-based integration of saliency and objectness. Based on the superpixel segmentation result of the input image, a graph is built to represent superpixels using regular vertex, background seed vertex with the addition of a terminal vertex. The edge weights on the graph are defined by integrating the difference of appearance, saliency, and objectness between superpixels. Then, the object probability of each superpixel is measured by finding the shortest path from the corresponding vertex to the terminal vertex on the graph, and the resultant object probability map can generally better highlight salient objects and suppress background regions compared to both saliency map and objectness map. Finally, the object probability map is used to initialize salient object and background, and effectively incorporated into the framework of graph cut to obtain the final salient object segmentation result. Extensive experimental results on three public benchmark datasets show that the proposed method consistently improves the salient object segmentation performance and outperforms the state-of-the-art salient object segmentation methods. Furthermore, experimental results also demonstrate that the proposed graph-based integration method is more effective than other fusion schemes and robust to saliency maps generated using various saliency models.

For better analyzing and adopting superpixel methods in image segmentation, an improved Simple Linear Iterative Clustering (SLIC) algorithm is put forward, which sustains that homogeneous regions show high consistence during clustering. Firstly, a primary iteration of SLIC approach is employed to generate uniform superpixels. Then an update strategy is introduced to determine whether to recluster the candidate region. In homogeneous regions, a cluster center often shows relatively small deviation of last position in spatial-color feature space when local iteration occurs, which can be regarded as redundant computation and be reduced. Experimental results show that the strategy brings a remarkable increased efficiency for traditional SLIC without significant affection on segmentation results.

This study presents an efficient saliency model mainly aiming at content-based applications such as salient object segmentation. The input colour image is first pre-segmented into a set of regions using the mean shift algorithm. A set of Gaussian models are estimated on the basis of segmented regions, and then for each pixel, a set of normalised colour likelihood measures to different Gaussian models are calculated. The colour saliency measure and spatial saliency measure of each Gaussian model are evaluated based on its colour distinctiveness and the spatial distribution, respectively. Finally, the pixel-wise colour saliency map and spatial saliency map are generated by summing the colour and spatial saliency measures of Gaussian models weighted by the normalised colour likelihood measures, and they are further combined to obtain the final saliency map. Experimental results on a dataset with 1000 images and ground truths demonstrate the better saliency detection performance of our saliency model.

Salient objects’ detection and segmentation are gaining increasing research interest in recent years. A saliency map can be obtained from different models presented in previous studies. Based on this saliency map, the most salient region (MSR) in an image can be extracted. This MSR, generally a rectangle, can be used as the initial parameters for object segmentation algorithms. However, to our knowledge, all of those saliency maps are represented in a unitary resolution although some models have even introduced multiscale principles in the calculation process. Furthermore, some segmentation methods, such as the well-known GrabCut algorithm, need more iteration time or additional interactions to get more precise results without predefined pixel types. A concept of a multiresolution saliency map is introduced. This saliency map is provided in a multiresolution format, which naturally follows the principle of the human visual mechanism. Moreover, the points in this map can be utilized to initialize parameters for GrabCut segmentation by labeling the feature pixels automatically. Both the computing speed and segmentation precision are evaluated. The results imply that this multiresolution saliency map-based object segmentation method is simple and efficient.

Abstract. The Factor analysis and target transformation (FATT) is an effective method to test for the presence of particular mineral on Martian surface. It has been used both in thermal infrared (Thermal Emission Spectrometer, TES) and near-infrared (Compact Reconnaissance Imaging Spectrometer for Mars, CRISM) hyperspectral data. FATT derived a set of orthogonal eigenvectors from a mixed system and typically selected first 10 eigenvectors to least square fit the library mineral spectra. However, minerals present only in a limited pixels will be ignored because its weak spectral features compared with full image signatures. Here, we proposed a superpixel based FATT method to detect the mineral distributions on Mars. The simple linear iterative clustering (SLIC) algorithm was used to partition the CRISM image into multiple connected image regions with spectral homogeneous to enhance the weak signatures by increasing their proportion in a mixed system. A least square fitting was used in target transformation and performed to each region iteratively. Finally, the distribution of the specific minerals in image was obtained, where fitting residual less than a threshold represent presence and otherwise absence. We validate our method by identifying carbonates in a well analysed CRISM image in Nili Fossae on Mars. Our experimental results indicate that the proposed method work well both in simulated and real data sets.

Registration between the baseline and follow-up lung computed tomography (CT) volumes plays an important role in computer-aided diagnosis and following-up care during adaptive radiotherapy. Diffeomorphic log-Demons as state of the art in Demons implementations is restricted to relatively small deformations, low accuracy, and ignoring some prior structural features. In this paper, an automated superpixel-borders-guided deformation image registration (SBG-DIR) algorithm is proposed. The proposed SBG-DIR method uses the simple linear iterative clustering (SLIC) algorithm to automated superpixels generation. Incorporation of superpixel borders into registration algorithm is implemented by a new similarity criterion based on the binary volume representation of superpixel borders. The binary volume representation enables accurate preserving motion boundaries, contributes to a faster convergence of the objective function and eliminates errors caused by manual interaction. In addition, a subtraction volume is produced by the intensity difference between the first time point CT volume and its warped follow-up CT volume. The subtraction volume can be used for detection of tumor tissue growth or shrinkage, which is an essential part of a CT-based diagnosis. Moreover, to ensure the topology preservation of biological objects, our proposed SBG-DIR method is implemented in the space of diffeomorphisms, in which meaningful biological shapes can be found. Compared with the state-of-the-art Demons, the proposed SBG-DIR method doesn’t require any additional optimization, yields a faster convergence and is more accurate and efficient in recovering large deformations. Experimental results indicate that the proposed SBG-DIR method performed better than the state-of-the-art Demons algorithms.