Simple Linear Iterative Clustering Superpixel Research Articles

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G.

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter(SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.

Super pixels transmission map-based object detection using deep neural network in UAV video

ABSTRACT Object detection has become a very prominent subject for research in recent times. This study's main goal is to suggest a technique for video saliency object detection. It seems to sense that using the depth information in photos to detect salient things. Since depth offers abundant information about scene structure, object forms, and other 3D cues. This information is very compatible to distinguish between objects in the foreground and background. As a result of the high object density, small object size, and cluttered background, aerial photos and movies provide results with low precision. In this paper, the proposed SPTM (Super Pixel Transmission Map)-YOLO model, the input RGB image has applied Dark Channel Prior (DCP) method for estimating the transmission map. From the transmission map only, the background probability is estimated with the help of SLIC (simple linear iterative clustering algorithm) superpixel segmentation. That foreground extracted image is further learned with YOLO architecture to detect the objects effectively. For object detection in aerial images, this proposed SPTM-YOLO approach outperforms classic YOLO by up to 6% accuracy. Accurate detection of things that are small in size, partially occluded, and out of view is possible.

Zero watermarking scheme for privacy protection in e-Health care

E-health care is an emerging field where health services and information are delivered and offered over the Internet. So the health information of the patients communicated over the Internet has to protect the privacy of the patients. The patient information is embedded into the health record and communicated online which also induces degradation to the original information. So, in this article, a zero watermarking scheme for privacy protection is proposed which protects the privacy and also eliminates the degradation done during embedding of patient information into the health record. This method is based on simple linear iterative clustering (SLIC) superpixels and partial pivoting lower triangular upper triangular (PPLU) factorization. The novelty of this article is that the use of SLIC superpixels and PPLU decomposition for the privacy protection of medical images (MI). The original image is subjected to SLIC segmentation and non-overlapping high entropy blocks are selected. On the selected blocks discrete wavelet transform (DWT) is applied and those blocks undergo PPLU factorization to get three matrices, L, U and P, which are lower triangular, upper triangular and permutation matrix respectively. The product matrix is used to construct a zero-watermark. The technique has been experimented on the UCID, BOWS and SIPI databases. The test results demonstrate that this work shows high robustness which is measured using normalized correlation (NC) and bit error rate (BER) against the listed attacks.

UAV-based weed detection in Chinese cabbage using deep learning

Weeds are unwanted plants on agricultural soil. They always competing for sunlight, nutrient, space and water with economic crops. Uncontrolled weed growth can cause both significant economic and ecological loss. Hence, weeds should be efficiently differentiated from the crops for the smart spraying solution. In this study, the Convolutional Neural Network (CNN) was used to perform weed detection amongst the commercial crop of Chinese cabbage, using the acquired images by Unmanned Aerial Vehicles. The acquired images were pre-processed and subsequently segmented into the crop, soil, and weed classes using the Simple Linear Iterative Clustering Superpixel algorithm. The segmented images were then used to construct the CNN-based classifier. The Random Forest (RF) was applied to compare with the performance of CNN. The results showed that the CNN achieved a higher overall accuracy of 92.41% than the 86.18% attained by RF.

A Sample Enhancement Method Based on Simple Linear Iterative Clustering Superpixel Segmentation Applied to Multibeam Seabed Classification

Full-coverage and high-efficiency seabed sediment detection and identification are critical elements of digital marine construction that support the three-dimensional and thematic development of maritime spatial geographic information systems. With the development of multibeam echo sounder (MBES), the use of MBES backscatter intensity and bathymetry data to extract backscatter angular response (AR) features has increased. Using backscatter intensity features and seabed terrain features for classification is an effective way to achieve large-scale seabed sediment classification. However, it was still limited by small sample size problems and the poor stability of the classification model due to the complexity of performing seabed sediment sampling. In response to the above issues, this paper proposes a sample enhancement method based on simple linear iterative clustering (SLIC) superpixel segmentation to address the problems. First, a superpixel-based sample homogeneity expansion method is combined with multibeam backscatter intensity images to achieve adaptive sample range selection. Then, a Random Forest (RF)-based model is constructed using MBES backscatter intensity and seabed terrain features. To assess the model’s validity, the experiment uses data from an extensive MBES survey and field sampling information from the Celtic Sea, UK. It achieves accurate predictions for the area’s eight sediment types. The experimental results show that the proposed method expands 60 groups of original sample points to 9293 groups of valid sample points, and achieves an overall classification accuracy and kappa coefficient of 84.05% and 0.81 for the seabed sediment, respectively. In addition, the classification accuracy is significantly better compared to the traditional methods.

A Novel Multi-Scale Feature Fusion-Based 3SCNet for Building Crack Detection

Crack detection at an early stage is necessary to save people’s lives and to prevent the collapse of building/bridge structures. Manual crack detection is time-consuming, especially when a building structure is too high. Image processing, machine learning, and deep learning-based methods can be used in such scenarios to build an automatic crack detection system. This study uses a novel deep convolutional neural network, 3SCNet (3ScaleNetwork), for crack detection. The SLIC (Simple Linear Iterative Clustering) segmentation method forms the cluster of similar pixels and the LBP (Local Binary Pattern) finds the texture pattern in the crack image. The SLIC, LBP, and grey images are fed to 3SCNet to form pool of feature vector. This multi-scale feature fusion (3SCNet+LBP+SLIC) method achieved the highest sensitivity, specificity, an accuracy of 99.47%, 99.75%, and 99.69%, respectively, on a public historical building crack dataset. It shows that using SLIC super pixel segmentation and LBP can improve the performance of the CNN (Convolution Neural Network). The achieved performance of the model can be used to develop a real-time crack detection system.

Extended SLIC superpixels algorithm for applications to non-imagery geospatial rasters

Converting an image to a set of superpixels is a useful preprocessing step in many computer vision applications; it reduces the dimensionality of the data and removes noise. The most popular superpixels algorithm is the Simple Linear Iterative Clustering (SLIC). To use original SLIC with non-imagery data (for example, rasters of discrete probability distributions, time-series, or matrices describing local texture or pattern), the data needs to be converted to the false-color RGB image constructed from the first three principal components. Here we propose to extend the SLIC algorithm so it can work with non-imagery data structures without data reduction and conversion to the false-color image. The modification allows for using a data distance measure most appropriate to a particular data structure and for using a custom function for averaging values of clusters centers. Comparisons between the extended and original SLIC algorithms in three different mapping tasks are presented and discussed. The results show that the extended SLIC improves the accuracy of the final products in reverse proportion to the percentage of variability explained by the three-dimensional (RGB) approximation to multidimensional non-imagery data. Thus, the largest advantage of using the modified SLIC can be expected in applications to data that cannot be compressed to three dimensions without a significant departure from its original variability. • Superpixels algorithm SLIC is extended to work with non-imagery geospatial data. • Case studies show that the extended SLIC outperforms the original on such data. • The improvement is inversely proportional to the compressibility of the data. • Extended SLIC expedites automated regionalization of large geospatial data.

Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images

With the development of unmanned aerial vehicle (UAV), obtaining high-resolution aerial images has become easier. Identifying and locating specific crops from aerial images is a valuable task. The location and quantity of crops are important for agricultural insurance businesses. In this paper, the problem of locating chili seedling crops in large-field UAV images is processed. Two problems are encountered in the location process: a small number of samples and objects in UAV images are similar on a small scale, which increases the location difficulty. A detection framework based on a prototypical network to detect crops in UAV aerial images is proposed. In particular, a method of subcategory slicing is applied to solve the problem, in which objects in aerial images have similarities at a smaller scale. The detection framework is divided into two parts: training and detection. In the training process, crop images are sliced into subcategories, and then these subcategory patch images and background category images are used to train the prototype network. In the detection process, a simple linear iterative clustering superpixel segmentation method is used to generate candidate regions in the UAV image. The location method uses a prototypical network to recognize nine patch images extracted simultaneously. To train and evaluate the proposed method, we construct an evaluation dataset by collecting the images of chilies in a seedling stage by an UAV. We achieve a location accuracy of 96.46%. This study proposes a seedling crop detection framework based on few-shot learning that does not require the use of labeled boxes. It reduces the workload of manual annotation and meets the location needs of seedling crops.

An Improved SLIC Algorithm for Segmentation of Microscopic Cell Images

Accurate nuclear and cell segmentations plays an important role in improving the accuracy of target recognition in microscopic cell images. As the traditional SLIC (Simple Linear Iterative Clustering) algorithm cannot segment microscopic cell images well, an improved SLIC superpixel segmentation algorithm based on gray scale enhancement and regional equalization is proposed. According to the characteristics of microscopic cell images, selecting different transformation parameters with the conditional iterative algorithm, the best classification multi-threshold method based on maximum entropy criterion is used to nonlinearly enhance the gray scale of the original images, while enhancing the contrast of the image, it also greatly improves the balance of each classification region. Then the gray distance and spatial distance are calculated respectively in the circle neighborhood of the cluster center to realize the superpixel segmentation of the image. Finally, the improved SLIC algorithm and the comparison algorithm are tested and evaluated. The experimental results show that our improved SLIC algorithm model has higher segmentation accuracy and is more suitable for cell segmentation in microscopic cell images than original SLIC algorithm.

Region extraction method for skin grafts via image analysis

ABSTRACT Dermal grafts are used for patients with severe burn injuries whose natural healing abilities are limited or exhausted. This paper proposes a method to segment burnt and grafted areas from images with meshed grafts. First, RGB colour input images are converted to images in the L*a*b* colour space. The transformed images are then segmented with the simple linear iterative clustering superpixel algorithm. Subsequently, the burnt and grafted areas are classified with a support vector machine, and the output area size is modified for all burnt areas. The segmentation results are compared with the areas identified by two dermatologists based on the concordance rate (CR), positive predictive value (PPV), sensitivity, and F-measure values. The proposed segmentation method yielded CRs equal to 84.3 % and 85.9 %, PPVs equal to 87.2 % and 87.9 %, sensitivities equal to 84.7 % and 86.4 %, and F-measure values equal to 85.8 % and 87.0 %. This study developed a segmentation method for classifying burnt and grafted areas from images with meshed grafts. The segmented areas obtained were significantly consistent with those identified by the two dermatologists.

Automatic ladybird beetle detection using deep-learning models.

Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from the iNaturalist project. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.

Swarm Intelligence-Based Methodology for Scanning Electron Microscope Image Segmentation of Solid Oxide Fuel Cell Anode

Segmentation of images from scanning electron microscope, especially multiphase, poses a drawback in their microstructure quantification process. The labeling process must be automatized due to the time consumption and irreproducibility of the manual labeling procedure. Here we show a swarm intelligence-driven filtration methodology performed on raw solid oxide fuel cell anode’s material images to improve the segmentation methods’ performance. The methodology focused on two significant parts of the segmentation process, which are filtering and labeling. During the first one, the images underwent filtering by applying a series of filters, whose operation parameters were determined using Particle Swarm Optimization upon a dedicated cost function. Next, Seeded Region Growing, k-Means Clustering, Multithresholding, and Simple Linear Iterative Clustering Superpixel algorithms were utilized to label the filtered images’ regions into consecutive phases in the microstructure. The improvement was presented for three different metrics: the Misclassification Ratio, Structural Similarity Index Measure, and Mean Squared Error. The obtained distribution of metrics’ performances was based on 200 images, with and without filtering. Results indicate an improvement up to 29%, depending on the metric and method used. The presented work contributes to the ongoing efforts to automatize segmentation processes fully for an increasing number of tomographic measurements, particularly in solid oxide fuel cell research.

Adaptive tuning of SLIC parameter K

The well-known simple linear iterative clustering (SLIC) is the most effective among the existing algorithms for superpixel segmentation, which requires manual tuning of the number of superpixels K. The optimal value of the parameter K of the SLIC algorithm for a given image is yet an open issue. In this work, we present granulometry and quality metrics based methods for adaptive tuning of the parameter K. The proposed granulometric method exploits the weighted average of the image pattern spectrum for the adaptive tuning of the parameter K. In the quality metrics method, we use majority voting scheme based on information, texture and ground truth independent quality metrics. The experimental results demonstrate that the K SLIC superpixels from the proposed methods achieved good boundary adherence of the ground truth for the images with high value of the compactness.

A Method for Human Burn Diagnosis Using Machine Learning and SLIC Superpixels Based Segmentation

The burn is a global health issue. The treatment of burn is performed by a burn surgeon. Burn region color is used to categorize burn types by a burn surgeon. Due to the lack of resources in many places burn patient dies. In such a situation a computer-based diagnosis system is very helpful. The severity of the burn is based on the depth and size of the burn region. The burn severity analysis can be accurately done by using the CIELab image as it contains all spectrums of colors. In the proposed work, the CIELab image is segmented using SLIC (Simple Linear Iterative Clustering) superpixel segmentation algorithm to form the same color pixels clusters. These clusters are used to diagnosis the severity of a burn, The severity of a burn is measured by the value of kurtosis. A high kurtosis value implies a larger depth and a small value implies a smaller depth. Based on the depth of burn, grafting or non-grafting is suggested by a burn surgeon. We observed depth of the burn is high in full-thickness burn compared to the deep dermal and the superficial dermal burn. The proposed method can correctly identify full-thickness burn and most of the deep dermal burn image. The open-access standard data set BURNS BIP-US DATABASE is used for training and testing of the proposed model on SVM (Support Vector Machine). The proposed model can classify with an accuracy of 89.16% and F1- score 90%. The achieved accuracy of the model is better than 79% of multidimensional scaling (MDS) in previous work.

Automatic segmentation and RECIST score evaluation in osteosarcoma using diffusion MRI: A computer aided system process

PurposeAccuracy and consistency in RECIST (Response evaluation criteria in solid tumors) measurements are crucial for treatment planning. Manual RECIST measurement is tedious, prone-to-error and operator-subjective. Objective was to develop a fully automated system for tumor segmentation and RECIST score estimation with reasonable accuracy, consistency and speed. MethodsDiffusion weight images (DWI) of forty patients (N = 40; Male:Female = 30:10; Age = 17.7 ± 5.9years) with Osteosarcoma was acquired using 1.5 T MRI scanner before (baseline) and after neoadjuvant chemotherapy (follow-up). 3D tumor volume was segmented applying Simple-linear-iterative-clustering Superpixels (SLIC-S) and Fuzzy-c-means-clustering (FCM) separately. Connected-component-analysis was performed to identify image-slice with maximum tumor-burden (Max-burden-sliceno) and measure tumor-sizes (Tumor-diameter(cm) & Tumor-volume(cc)). Relative-percentage-changes in tumor-sizes across time-points were scored using RECIST1.1 and Volumetric-response criterion. Segmentation accuracy was estimated by Dice-coefficient (DC), Jaccard-Index (JI), Precision (P) and Recall (R). Evaluated Apparent-diffusion-coefficient (ADC), Tumor-diameter, Max-burden-sliceno and Tumor-volume in segmented tumor-mask and ground-truth tumor-mask were compared using paired-t-test (p < 0.05), Pearson-correlation-coefficient(PCC) and Bland-Altman plots. Misclassification-error-rate (MER) was evaluated for automated RECIST1.1 and Volumetric-response scoring methods. ResultsAutomated SLIC-S and FCM produced satisfactory tumor segmentation (DC:∼70−83%;JI:∼55−72%;P:∼64−85%;R:∼73−83%) and showed excellent correlation with ground-truth measurements in estimating ADC (p > 0.05; PCC=0.84−0.89), Tumor-diameters (p > 0.05; PCC=0.90−0.95; bias=0.3−2.41), Max-burden-sliceno (p > 0.05; PCC=0.87-0.96) and Tumor-volumes (p > 0.05; PCC=0.89−0.94; bias=15.19–131.81) at baseline and follow-up. MER for SLIC-S and FCM were comparable for RECIST1.1 (15–18 %) and Volumetric-response (18–20 %) scores and assessment times were 2−3s and 4−6s per patient respectively. ConclusionsProposed method produced promising segmentation and RECIST score measurements in current bone tumor dataset and might be useful as decision-support-tool for response evaluation in other tumors.

Oil Spill Detection in Quad-Polarimetric SAR Images Using an Advanced Convolutional Neural Network Based on SuperPixel Model

Oil spill detection plays an important role in marine environment protection. Quad-polarimetric Synthetic Aperture Radar (SAR) has been proved to have great potential for this task, and different SAR polarimetric features have the advantages to recognize oil spill areas from other look-alikes. In this paper we proposed an oil spill detection method based on convolutional neural network (CNN) and Simple Linear Iterative Clustering (SLIC) superpixel. Experiments were conducted on three Single Look Complex (SLC) quad-polarimetric SAR images obtained by Radarsat-2 and Spaceborne Imaging Radar-C/X-Band Synthetic Aperture Radar (SIR-C/X-SAR). Several groups of polarized parameters, including H/A/Alpha decomposition, Single-Bounce Eigenvalue Relative Difference (SERD), correlation coefficients, conformity coefficients, Freeman 3-component decomposition, Yamaguchi 4-component decomposition were extracted as feature sets. Among all considered polarimetric features, Yamaguchi parameters achieved the highest performance with total Mean Intersection over Union (MIoU) of 90.5%. It is proved that the SLIC superpixel method significantly improved the oil spill classification accuracy on all the polarimetric feature sets. The classification accuracy of all kinds of targets types were improved, and the largest increase on mean MIoU of all features sets was on emulsions by 21.9%.

Image Segmentation of Brain MRI Based on LTriDP and Superpixels of Improved SLIC.

Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI). To this end, we propose a novel superpixel segmentation algorithm by integrating texture features and improved simple linear iterative clustering (SLIC). First, a 3D histogram reconstruction model is used to reconstruct the input image, which is further enhanced by gamma transformation. Next, the local tri-directional pattern descriptor is used to extract texture features of the image; this is followed by an improved SLIC superpixel segmentation. Finally, a novel clustering-center updating rule is proposed, using pixels with gray difference with original clustering centers smaller than a predefined threshold. The experiments on the Whole Brain Atlas (WBA) image database showed that, compared to existing state-of-the-art methods, our superpixel segmentation algorithm generated significantly more uniform superpixels, and demonstrated the performance accuracy of the superpixel segmentation in both fuzzy boundaries and fuzzy regions.

Image classification using SLIC superpixel and FAAGKFCM image segmentation

Image classification is one of the popular fields for researchers in computer vision. This study highlights the use of simple linear iterative clustering (SLIC) superpixel in combination with fast and automatically adjustable Gaussian radial basis function kernel-based fuzzy C-means (FAAGKFCM) for image segmentation along with the deep learning techniques. Bag-of-feature with speeded up robust feature along with deep features are used for classification of 101 classes of the image and 256 classes of the image from Caltech 101, Caltech 256 and MIT 67 image datasets. The combination of SLIC superpixel with FAAGKFCM image segmentation acts as the pre-processing step for image classification, which in turn provides a better result in the classification of images. This method has achieved an accuracy of 94% in Caltech 101 dataset, 85% in Caltech 256 dataset and 84% in MIT 67 dataset.

Segmentation of osteosarcoma tumor using diffusion weighted MRI: a comparative study using nine segmentation algorithms

Osteosarcoma is a primary malignant bone tumor in children and adolescents with significant morbidity and poor prognosis. Diffusion weighted imaging (DWI) plays a crucial role in diagnosis and prognosis of this malignant disease by capturing cellular changes in tumor tissue early in the course of treatment without any contrast injection. Segmentation of tumor in DWI is challenging due to low signal-to-noise ratio, partial-volume effects, intensity inhomogeneities and irregular shape of osteosarcoma. The purpose of this study was to segment osteosarcoma solely utilizing DWI and identify effective and robust technique(s) for tumor segmentation. DWI dataset of fifty-five (N = 55; male:female = 41:14; Age = 17.8 ± 7.4 years) patients with osteosarcoma was acquired before treatment. Total nine automated and semi-automated segmentation algorithms based on (1) Otsu thresholding (OT), (2) Otsu threshold-based region growing (OT-RG), (3) Active contour (AC), (4) Simple linear iterative clustering Superpixels (SLIC-S), (5) Fuzzy c-means clustering (FCM), (6) Graph cut (GC), (7) Logistic regression (LR) (8) Linear support vector machines (L-SVM) and (9) Deep feed-forward neural network (DNN) were implemented. Segmentation accuracy was estimated by Dice coefficient (DC), Jaccard Index (JI), precision (P) and recall (R) using manually demarcated ground-truth tumor mask by a radiologist. Evaluated apparent diffusion coefficient (ADC) in segmented tumor mask and ground-truth tumor mask was compared using paired t test for statistical significance (p < 0.05) and Pearson correlation coefficient (PCC). Automated SLIC-S and FCM showed quantitatively and qualitatively superior segmentation with DC: ~ 79–82%; JI: ~ 67–71%; P: ~ 81–83%; R: ~ 80–86% and PCC = 0.89, 0.88 among all methods. Among semi-automated methods, AC was quantitatively more accurate (DC: ~ 77%; JI: ~ 65%; P: ~ 72%; R: ~ 88%; PCC = 0.85) than OT-RG and GC (DC: ~ 74–75%; JI: ~ 60–61%; P: ~ 67–72%; R: ~ 84–89%; PCC = 0.78, 0.73). Among machine learning algorithms, DNN showed the highest accuracy (DC: ~ 73%; JI: ~ 62%; P: ~ 77%; R: ~ 86%; PCC = 0.79) than LR and L-SVM (DC: ~ 70–71%; JI: ~ 58–63%; P: ~ 73%; R: ~ 74–85%; PCC = 0.69, 0.71). Execution times were instantaneous for SLIC-S, FCM and machine learning methods, while OT-RG, AC and GC took comparable ~ 1–6 s/slice image. Automated SLIC-S, FCM and semi-automated AC methods produced promising tumor segmentation results using DWI of the osteosarcoma dataset.

Purifying SLIC Superpixels to Optimize Superpixel-Based Classification of High Spatial Resolution Remote Sensing Image

Fast and accurate classification of high spatial resolution remote sensing image is important for many applications. The usage of superpixels in classification has been proposed to accelerate the speed of classification. However, although most superpixels only contain pixels from single class, there are still some mixed superpixels, which mostly locate near the edge of different classes, and contain pixels from more than one class. Such mixed superpixels will cause misclassification regardless of classification methods used. In this paper, a superpixels purification algorithm based on color quantization is proposed to purify mixed Simple Linear Iterative Clustering (SLIC) superpixels. After purifying, the mixed SLIC superpixel will be separated into smaller superpixels. These smaller superpixels are pure superpixels which only contain a single kind of ground object. The experiments on images from the dataset BSDS500 show that the purified SLIC superpixels outperform the original SLIC superpixels on three segmentation evaluation metrics. With the purified SLIC superpixels, a classification scheme in which only edge superpixels are selected to be purified is proposed. The strategy of purifying edge superpixels not only improves the efficiency of the algorithm, but also improves the accuracy of the classification. The experiments on a remote sensing image from WorldView-2 satellite demonstrate that purified SLIC superpixels at all scales can generate classification result with higher accuracy than original SLIC superpixels, especially at the scale of 20 × 20 , for which the accuracy increase is higher than 4%.