Image segmentation using dense and sparse hierarchies of superpixels

Superpixel segmentation, a preprocessing component, is widely used in computer vision tasks. Superpixel algorithm is supposed to generate superpixels with required boundary adherence, compactness as well as less computational complexity. However, most of the existing superpixel algorithms do not perform satisfactorily when it comes to compactness and boundary adherence, as they are a paradox in nature. In this paper, we propose a new superpixel segmentation method based on density peak (DP) clustering and modification of the original DP algorithm. The experimental results have been compared with state-of-the-art methods, both quantitatively and qualitatively, revealing the efficient outcomes that adhere to the object boundaries better than others.

Deep superpixel algorithms have made remarkable strides by substituting hand-crafted features with learnable ones. Nevertheless, we observe that existing deep superpixel methods, serving as mid-level representation operations, remain sensitive to the statistical properties (e.g., color distribution, high-level semantics) embedded within the training dataset. Consequently, learnable features exhibit constrained discriminative capability, resulting in unsatisfactory pixel grouping performance, particularly in untrainable application scenarios. To address this issue, we propose the Content Disentangle Superpixel (CDS) algorithm to selectively separate the invariant inter-pixel correlations and statistical properties, i.e., style noise. Specifically, We first construct auxiliary modalities that are homologous to the original RGB image but have substantial stylistic variations. Then, driven by mutual information, we propose the local-grid correlation alignment across modalities to reduce the distribution discrepancy of adaptively selected features and learn invariant inter-pixel correlations. Afterwards, we perform global-style mutual information minimization to enforce the separation of invariant content and train data styles. The experimental results on four benchmark datasets demonstrate the superiority of our approach to existing state-of-the-art methods, regarding boundary adherence, generalization, and efficiency. Code and pre-trained model are available at https://github.com/rookiie/CDSpixel.

In recent studies, superpixel segmentation has been integrated into hyperspectral (HS) image classification methods. However, the existing superpixel-based classification methods usually suffer from two serious problems. First, the accuracy and efficiency of current superpixel segmentation approaches cannot meet the demands of practical applications for HS images; second, conventional superpixel-based classification methods generally consider each generated superpixel as a unit for the image classification, which may help to reduce the computing time but result in a significant decrease of the classification accuracy. To solve the problems, we propose a fast region growing based superpixel segmentation (FRGSS) algorithm and a novel texture-adaptive superpixel integration strategy (TASIS) for the HS image classification. Experimental results on real Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) HS images demonstrate that the proposed FRGSS outperforms the state-of-the-art superpixel algorithm. In addition, the superiority of the TASIS is verified compared to the pixel-wise and the conventional superpixel-based classification methods.

Novel Method for Prostate Cancer Detection Using Super Pixel and ANN Algorithm

Image prominence is the most important region in an image, which can cause the visual attention and response of human beings. Preferentially allocating the computer resources for the image analysis and synthesis by the significant region is of great significance to improve the image area detecting. As a preprocessing of other disciplines in image processing field, the image prominence has widely applications in image retrieval and image segmentation. Among these applications, the super-pixel segmentation significance detection algorithm based on linear spectral clustering (LSC) has achieved good results. The significance detection algorithm proposed in this paper is better than the regional contrast ratio by replacing the method of regional formation in the latter with the linear spectral clustering image is super-pixel block. After combining with the latest depth learning method, the accuracy of the significant region detecting has a great promotion. At last, the superiority and feasibility of the super-pixel segmentation detection algorithm based on linear spectral clustering are proved by the comparative test.

Superpixel segmentation is a fundamental task in computer vision. Existing works contribute to superpixel segmentation either by improving segmentation accuracy or by reducing execution time. The former modifies existing models or develops new models to improve accuracy. The latter accelerates existing implementations or reduces algorithm complexity to improve execution rate. This work falls into the second category. Recently, a superpixel algorithm using Gaussian mixture model (GMMSP) achieves state-of-the-art performance in accuracy. After exploring this algorithm, we reached new conclusions on GMMSP that unlock potential concerning fine-grain parallelism implementation. We implement GMMSP with CUDA and make it run on GPUs. Experiments are conducted to validate the consistency between CPU and GPU implementations and to evaluate the performance of our implementation with respect to a serial and an OpenMP implementation. When we consider a full implementation with a postprocessing step executed on CPU to guarantee connectivity constraint, the proposed implementation achieves a speedup of 21× compared to the OpenMP implementation for images of size 240 × 320, using NVIDIA GTX 1080. It is also mentionable that we achieve a performance of over 1000 FPS on GTX 1080 (speedup of 77× compared to the OpenMP implementation) if the connectivity constraint is not included.

Superpixel segmentation has been commonly used in various image processing tasks such as object detection and image classification. In this paper, we propose a novel superpixel segmentation method based on a new distance function and superpixel seed updating strategy for polarimetric synthetic aperture radar (PolSAR) images. We initialize superpixel seeds with an expected number of superpixels. Then, we iteratively cluster the pixels based on the distance function and update the superpixel seeds based on the updating strategy. When the termination condition is reaches, we stop the iteration and obtain the superpixels. The experimental results based on RADARSAT-2 data demonstrate that our method is effective and achieves a better tradeoff between boundary adherence and compactness.

Superpixel segmentation: A benchmark

A large number of improved variants of the Fuzzy c-means were used to segment the gray scale and color image. Nevertheless, some of them take time to yield the best and optimal results and for two reasons cannot produce adequate segmentation results for color images. This work proposes a simple FCM clustering algorithm based on the Super pixel Algorithm (SFFCM), which is considerably faster and more robust for image segmentation applications which are based purely on the color parameter. In this research work, to attain an accurate contour super pixel image for improved local spatial neighborhoods, an efficient algorithm referred as multi-scale morphological gradient reconstruction (MMGR) operation is originally described. The significance of the proposed method lies in the relationships between the pixels and how they are utilized in the flow of the application. Compared to the conventional adjacent fixed-size and shape frame, the super pixel image provides improved adaptive and exact amount of irregular local spatial communities which help to enhance color image segmentation. Coming to the next step, the original color image is essentially based on the obtained super pixel picture, and the number of pixels in each super pixel region easily decides its histogram. Ultimately, FCM is implemented to obtain final segmentation results that increase the histogram parameter on the super pixel picture. The performance of the proposed method is computed using Matlab computing language and also a statistical measure is carried out based on different parameters and their respective graphical representations.

Super-pixel algorithm and group sparsity regularization method for compressed sensing MR image reconstruction

Over-segmentation has often been employed to simplify representation of images and speed the process of image analysis, where each over-segment is also called a superpixel. However, the superpixels generated by the existing algorithms rely heavily on some preset parameters, for example, number of superpixels. In this paper, we present a novel superpixel algorithm under the framework of nonparametric Bayesian image clustering, which is called Nonparametric Bayesian Iterative Clustering (NBIC). Unlike traditional approaches for image clustering, Bayesian nonparametric models provide a principled way to infer the number of clusters from observed data. Therefore, unlike traditional approach to image over-segmentation, the NBIC is free of preset number of superpixels. The NBIC to superpixel segmentation is based on histogram clustering, and local histograms are extracted as observation. For each observation, compute the probability of each class and sample a class label accordingly. The cluster probabilities depend on the number of classes in the pixel neighborhood and the distance of cluster center. This method groups pixels into meaningful regions without setting any parameters related to superpixels in the nonparametric Bayesian theory. The adaptive amount of superpixels can eventually be converged, and the size of superpixels can automatically be controlled by iterative calculation

There exist almost as many superpixel segmentation algorithms as applications they can be used for. So far, the choice of the right superpixel algorithm for the task at hand is based on their ability to resemble human-made ground truth segmentations (besides runtime and availability). We investigate the equally important question of how stable the segmentations are under image changes as they appear in video data. Further we propose a new quality measure that evaluates how well the segmentation algorithms cover relevant image boundaries. Instead of relying on human-made annotations, that may be biased by semantic knowledge, we present a completely data-driven measure that inherently emphasizes the importance of image boundaries. Our evaluation is based on two recently published datasets coming with ground truth optical flow fields. We discuss how these ground optical truth fields can be used to evaluate segmentation algorithms and compare several existing superpixel algorithms.

Superpixels have gradually become popular in computer vision and image processing applications. However, no comprehensive study has been performed to evaluate the robustness of superpixel algorithms in regard to common forms of noise in natural images. We evaluated the robustness of 11 recently proposed algorithms to different types of noise. The images were corrupted with various degrees of Gaussian blur, additive white Gaussian noise, and impulse noise that either made the object boundaries weak or added extra information to it. We performed a robustness analysis of simple linear iterative clustering (SLIC), Voronoi Cells (VCells), flooding-based superpixel generation (FCCS), bilateral geodesic distance (Bilateral-G), superpixel via geodesic distance (SSS-G), manifold SLIC (M-SLIC), Turbopixels, superpixels extracted via energy-driven sampling (SEEDS), lazy random walk (LRW), real-time superpixel segmentation by DBSCAN clustering, and video supervoxels using partially absorbing random walks (PARW) algorithms. The evaluation process was carried out both qualitatively and quantitatively. For quantitative performance comparison, we used achievable segmentation accuracy (ASA), compactness, under-segmentation error (USE), and boundary recall (BR) on the Berkeley image database. The results demonstrated that all algorithms suffered performance degradation due to noise. For Gaussian blur, Bilateral-G exhibited optimal results for ASA and USE measures, SLIC yielded optimal compactness, whereas FCCS and DBSCAN remained optimal for BR. For the case of additive Gaussian and impulse noises, FCCS exhibited optimal results for ASA, USE, and BR, whereas Bilateral-G remained a close competitor in ASA and USE for Gaussian noise only. Additionally, Turbopixel demonstrated optimal performance for compactness for both types of noise. Thus, no single algorithm was able to yield optimal results for all three types of noise across all performance measures. Conclusively, to solve real-world problems effectively, more robust superpixel algorithms must be developed.

The concept of superpixel firstly appeared in the research of image segmentation, Superpixel algorithms are designed to segment an image into a series of blocks, all these blocks are comprised of a number of pixels. By composing a superpixel network instead of making a pixel network, we can deal with every superpixel as a separate entity. By this means, we reduce the time complexity of the original algorithms which deal with pixels one by one. And always we could get better results via improved algorithms aimed at superpixels. The essence of superpixel segmentation is an abstraction of basic information in an image. One of the best superxiel segmentation algorithm is SLIC algorithm, we will introduce it and implement it by C programming language.

An artificial intelligence method for vessel detection in images of cardiac catheterization