Superpixel Classification Research Articles

Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network

Background and Objective:Tendon segmentation is crucial for studying tendon-related pathologies like tendinopathy, tendinosis, etc. This step further enables detailed analysis of specific tendon regions using automated or semi-automated methods. This study specifically aims at the segmentation of Achilles tendon, the largest tendon in the human body. Methods:This study proposes a comprehensive end-to-end tendon segmentation module composed of a preliminary superpixel-based coarse segmentation preceding the final segmentation task. The final segmentation results are obtained through two distinct approaches. In the first approach, the coarsely generated superpixels are subjected to classification using Random Forest (RF) and Support Vector Machine (SVM) classifiers to classify whether each superpixel belongs to a tendon class or not (resulting in tendon segmentation). In the second approach, the arrangements of superpixels are converted to graphs instead of being treated as conventional image grids. This classification process uses a graph-based convolutional network (GCN) to determine whether each superpixel corresponds to a tendon class or not. Results:All experiments are conducted on a custom-made ankle MRI dataset. The dataset comprises 76 subjects and is divided into two sets: one for training (Dataset 1, trained and evaluated using leave-one-group-out cross-validation) and the other as unseen test data (Dataset 2). Using our first approach, the final test AUC (Area Under the ROC Curve) scores using RF and SVM classifiers on the test data (Dataset 2) are 0.992 and 0.987, respectively, with sensitivities of 0.904 and 0.966. On the other hand, using our second approach (GCN-based node classification), the AUC score for the test set is 0.933 with a sensitivity of 0.899. Conclusions:Our proposed pipeline demonstrates the efficacy of employing superpixel generation as a coarse segmentation technique for the final tendon segmentation. Whether utilizing RF, SVM-based superpixel classification, or GCN-based classification for tendon segmentation, our system consistently achieves commendable AUC scores, especially the non-graph-based approach. Given the limited dataset, our graph-based method did not perform as well as non-graph-based superpixel classifications; however, the results obtained provide valuable insights into how well the models can distinguish between tendons and non-tendons. This opens up opportunities for further exploration and improvement.

Semi-supervised video object segmentation via an edge attention gated graph convolutional network

Video object segmentation (VOS) exhibits heavy occlusions, large deformation, and severe motion blur. While many remarkable convolutional neural networks are devoted to the VOS task, they often mis-identify background noise as the target or output coarse object boundaries, due to the failure of mining detail information and high-order correlations of pixels within the whole video. In this work, we propose an edge attention gated graph convolutional network (GCN) for VOS. The seed point initialization and graph construction stages construct a spatio-temporal graph of the video by exploring the spatial intra-frame correlation and the temporal inter-frame correlation of superpixels. The node classification stage identifies foreground superpixels by using an edge attention gated GCN which mines higher-order correlations between superpixels and propagates features among different nodes. The segmentation optimization stage optimizes the classification of foreground superpixels and reduces segmentation errors by using a global appearance model which captures the long-term stable feature of objects. In summary, the key contribution of our framework is twofold: (a) the spatio-temporal graph representation can propagate the seed points of the first frame to subsequent frames and facilitate our framework for the semi-supervised VOS task; (b) the edge attention gated GCN can learn the importance of each node with respect to both the neighboring nodes and the whole task with small number of layers. Experiments on Davis 2016 and Davis 2017 datasets show that our framework achieves the excellent performance with only small training samples (45 video sequences).

SSWT-UUNet++ Submarine Oil Pipeline Spill Detection Approach

The existing leak detection methods of submarine oil pipelines mainly rely on compositing synthetic aperture radar (SAR) satellite images to detect oil spills on the sea surface or installing underwater cameras to monitor the joints of submarine pipelines manually. The former is poor in timeliness and high in cost, while the latter is inflexible. Aiming at this, this paper studies the underwater image processing method of intelligent oil spill recognition using an underwater camera. Nevertheless, this method is currently faced with challenges such as poor quality of datasets, unclear goals, and scarce quantity. The U-Net++ algorithm can theoretically reduce the dependence on the number of datasets. However, the pixel feature extraction method used by U-Net++ is difficult to achieve the segmentation effect of oil spill images, so a new network architecture SSWT (Suitable Superpixel With Texture)-UNet++ based on texture superpixel is proposed. In SSWT-UNet++, the input is the oil spill image with texture superpixel division, and the output was changed to the middle layer. In addition, the resolution of each layer and the ratio of up/down sampling were adjusted. This algorithm completes the classification of oil spill texture superpixels and finally realizes oil spill detection according to the minimum bounding rectangle of the classification result of the oil spill region. Experimental verification shows that the final detection effect of the proposed algorithm is higher than that of other algorithms, with an average precision of 0.985.

Fuzzy Color Aura Matrices for Texture Image Segmentation.

Fuzzy gray-level aura matrices have been developed from fuzzy set theory and the aura concept to characterize texture images. They have proven to be powerful descriptors for color texture classification. However, using them for color texture segmentation is difficult because of their high memory and computation requirements. To overcome this problem, we propose to extend fuzzy gray-level aura matrices to fuzzy color aura matrices, which would allow us to apply them to color texture image segmentation. Unlike the marginal approach that requires one fuzzy gray-level aura matrix for each color channel, a single fuzzy color aura matrix is required to locally characterize the interactions between colors of neighboring pixels. Furthermore, all works about fuzzy gray-level aura matrices consider the same neighborhood function for each site. Another contribution of this paper is to define an adaptive neighborhood function based on information about neighboring sites provided by a pre-segmentation method. For this purpose, we propose a modified simple linear iterative clustering algorithm that incorporates a regional feature in order to partition the image into superpixels. All in all, the proposed color texture image segmentation boils down to a superpixel classification using a simple supervised classifier, each superpixel being characterized by a fuzzy color aura matrix. Experimental results on the Prague texture segmentation benchmark show that our method outperforms the classical state-of-the-art supervised segmentation methods and is similar to recent methods based on deep learning.

A Hybrid Model Based on Superpixel Entropy Discrimination for PolSAR Image Classification

Superpixel segmentation is widely used in polarimetric synthetic aperture radar (PolSAR) image classification. However, the classification method using simple majority voting cannot easily handle evidence conflicts in a single superpixel. At present, there is no method to evaluate the quality of superpixel classification. To solve the above problems, this paper proposes a hybrid classification model based on superpixel entropy discrimination (SED), and constructs a two-level cascade classifier. Firstly, a light gradient boosting machine (LGBM) was used to process large-dimensional input features, and simple linear iterative clustering (SLIC) was integrated to obtain the primary classification results based on superpixels. Secondly, information entropy was introduced to evaluate the quality of superpixel classification, and a complex-valued convolutional neural network (CV-CNN) was used to reclassify the high-entropy superpixels to obtain the secondary classification results. Experiments with two measured PolSAR datasets show that the overall accuracy of both classification methods exceeded 97%. This method suppressed the evidence conflict in a single superpixel and the inaccuracy of superpixel segmentation. The test time of our proposed method was shorter than that of CV-CNN, and using only 55% of CV-CNN test data could achieve the same accuracy as using CV-CNN for the whole image.

AUTOMATIC FLOOD DETECTION USING SENTINEL-1 IMAGES IN GOOGLE EARTH ENGINE

The paper presents a method to detect flooded areas based on the classification of superpixels from Sentinel-1 satellite image data. The automatic thresholding method based on the Simple Non-Iterative Clustering and the OTSU algorithm extracts flooded areas from Sentinel-1 images on the Google Earth Engine platform. Experimental results in Quang Binh province in October 2016 show the efficiency of the proposed method (Simple Non-Iterative Clustering algorithm combined with the OTSU algorithm). The proposed method accuracy is 91% higher than the OTSU algorithm, with about 86% in classifying flooded areas in SAR images. The results obtained in the study area can provide timely information about the flooded area, contributing to effective response and reduction of damage caused by floods. The study also shows the power of the Google Earth Engine platform. Google Earth Engine has supported rapid data analysis and processing thanks to rich data sources, multi-time, diverse data, and various algorithms.

Computer vision system for superpixel classification and segmentation of sheep

This paper presents an experiment with four different convolutional neural networks architectures that aim to classify segments of a sheep using a dataset of superpixels. The proposal used an image dataset with 512 images of 32 sheep. In this dataset of images, we applied the Simple Linear Iterative Clustering technique with a K number parameter of 600 to generate the dataset of superpixels that was later processed in the deep neural networks. We selected four architectures for training the models: VGG16, ResNet152V2, InceptionV3, and DenseNet201. The experiment was conducted using cross-validation with five-folds separating the dataset into training (60%), validation (20%), and testing (20%). The best result presented was from the approach with the DenseNet201 technique with an F-score of 0.928. When applying ANOVA, the P-value was 0.0000000000329 (3.29e-11***) between the tested architectures, which shows that the results are statistically significant. Therefore, DenseNet201 presented itself as a relevant architecture for this problem that aims to classify the superpixels referring to a sheep and the image's background, and the average IoU with post-processing for image segmentation with DenseNet201 obtained 0.8332. Thus, we can highlight the contributions of this research as a methodology to segment images of mixed-breed sheep of the Texel and Santa Inês breeds using convolutional neural networks and provide a non-invasive method that can support other implementations such as animal tracking and weight prediction.

Wheat Ear Segmentation Based on a Multisensor System and Superpixel Classification.

The automatic segmentation of ears in wheat canopy images is an important step to measure ear density or extract relevant plant traits separately for the different organs. Recent deep learning algorithms appear as promising tools to accurately detect ears in a wide diversity of conditions. However, they remain complicated to implement and necessitate a huge training database. This paper is aimed at proposing an easy and quick to train and robust alternative to segment wheat ears from heading to maturity growth stage. The tested method was based on superpixel classification exploiting features from RGB and multispectral cameras. Three classifiers were trained with wheat images acquired from heading to maturity on two cultivars at different levels of fertilizer. The best classifier, the support vector machine (SVM), yielded satisfactory segmentation and reached 94% accuracy. However, the segmentation at the pixel level could not be assessed only by the superpixel classification accuracy. For this reason, a second assessment method was proposed to consider the entire process. A simple graphical tool was developed to annotate pixels. The strategy was to annotate a few pixels per image to be able to quickly annotate the entire image set, and thus account for very diverse conditions. Results showed a lesser segmentation score (F1-score) for the heading and flowering stages and for the zero nitrogen input object. The methodology appeared appropriate for further work on the growth dynamics of the different wheat organs and in the frame of other segmentation challenges.

Super pixel segmentation and classification of SAR images for brightness enhancement

By and large, distant detecting photos are taken in dim conditions like mist, snow, slim cloudiness, mud, etc, bringing about picture contrast misfortune. The Dark Channel Prior (DCP) was utilized to eliminate the dimness impact on far off detecting pictures in this examination. DE inception is conceivable in this model for both characteristic and distant detecting pictures. The initial phase in improving satellite picture properties is to decide if the picture is a characteristic picture or a far off detecting picture, and afterward recuperate it to take out dimness. Emphasis proceeds with the utilization of airlight values, trailed by the utilization of DCP to limit dust, lastly the fog is eliminated utilizing the Iterative dehazing measure for distant detecting picture (IDERS) model. The aftereffect of the Low light picture upgrade (LIME) measure is a fog free picture with expanded lucidity.

SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images.

High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers.

Bottom-up image detection of water channel slope damages based on superpixel segmentation and support vector machine

The operation of water supply channels is threatened by the occasionally occurred slope damages. Timely detection of their occurrence is critical for the rapid enforcement of mitigation measures. However, current practices based on routine inspection and structural heath monitoring are inefficient, laborious and tend to be biased. As an attempt to address the limitations, this paper proposes a bottom-up image detection approach for slope damages, which includes four steps, i.e. superpixel segmentation, feature handcrafting, superpixel classification based on support vector machine (SVM), and slope damage recognition. The approach employs a bottom-up strategy to infer the upper-level slope condition from the classification results of individual superpixels in the bottom level. Experiments were conducted to demonstrate the effectiveness of the approach. The handcrafted feature “LBP + HSV” was demonstrated to be effective in characterizing the image features of slope damages. An SVM model with “LBP + HSV” as input can reliably identify the slope condition in superpixels. Based on the SVM model, the bottom-up strategy achieved high recognition performance, of which the overall accuracy can be up to 91.7%. The proposed approach has potential to facilitate the early and comprehensive awareness of slope damages along the entire route of water channel by the integration with unmanned aerial vehicles.

Automatic measurement of pressure ulcers using Support Vector Machines and GrabCut

Background and Objective: Pressure ulcers are regions of trauma caused by a continuous pressure applied to soft tissues between a bony prominence and a hard surface. The manual monitoring of their healing evolution can be achieved by area assessment techniques that include the use of rulers and adhesive labels in direct contact with the injury, being highly inaccurate and subjective. In this paper we present a Support Vector Machine classifier in combination with a modified version of the GrabCut method for the automatic measurement of the area affected by pressure ulcers in digital images. Methods: Three methods of region segmentation using the superpixel strategy were evaluated from which color and texture descriptors were extracted. After the superpixel classification, the GrabCut segmentation method was applied in order to delineate the region affected by the ulcer from the rest of the image. Results: Experiments on a set of 105 pressure ulcer images from a public data set resulted in an average accuracy of 96%, sensitivity of 94%, specificity of 97% and precision of 94%. Conclusions: The association of support vector machines with superpixel segmentation outperformed current methods based on deep learning and may be extended to tissue classification.

Discriminant sub-dictionary learning with adaptive multiscale superpixel representation for hyperspectral image classification

Sparse representation and dictionary learning have been successfully applied in hyperspectral image classification. Generally, it is more effective to learn the sub-dictionary for each class and utilize multiple scale strategy. However, the sub-dictionary may only consider the within-class information and ignore the discriminative information. For multiscale sparse representation, the shape of the regions would not adaptively change according to context structure. This paper proposes a discriminative sub-dictionary learning algorithm and an adaptive multiscale superpixel classification strategy under sparse representation framework for hyperspectral image classification. In dictionary learning stage, the global constraint term can ensure the learnt sub-dictionaries contain more discriminative information. In sparse representation stage, the adaptive multiscale superpixel strategy can exploit the spatial context according to the structural information. The combination of the two strategies can further explore the spatial and spectral information in hyperspectral image. Experiments on four hyperspectral image datasets prove that the proposed method has a significant improvement in both quantitative and qualitative analysis comparing with state-of-the-art algorithms. Moreover, the proposed algorithm can produce satisfactory results for the imbalanced data problem involved in hyperspectral image.

Joint energy active contour CT image segmentation method based on super-pixel

In this paper, an active contour segmentation method for organs CT images based on super-pixel and convolutional neural network is proposed to solve the sensitive problem of the initial contour of the segmentation method of the CT image. The method firstly super-pixels the CT image based on super-pixel segmentation and determines the edge super-pixels by the super-pixel classification through a convolutional neural network. Afterwards, the seed points of the edge super-pixels are extracted to form the initial contour. Finally, based on the extracted initial contour, the human organ segmentation is realized by solving the minimum value of the integrated energy function proposed in this paper. The results in this paper show that the average Dice coefficient is improved by 5% compared with the advanced U-Net method, providing a theoretical basis and a new solution for the diagnosis of clinical CT image lesions.

Segmentation of breast ultrasound image with semantic classification of superpixels.

Breast cancer is a great threat to females. Ultrasound imaging has been applied extensively in diagnosis of breast cancer. Due to the poor image quality, segmentation of breast ultrasound (BUS) image remains a very challenging task. Besides, BUS image segmentation is a crucial step for further analysis. In this paper, we proposed a novel method to segment the breast tumor via semantic classification and merging patches. The proposed method firstly selects two diagonal points to crop a region of interest (ROI) on the original image. Then, histogram equalization, bilateral filter and pyramid mean shift filter are adopted to enhance the image. The cropped image is divided into many superpixels using simple linear iterative clustering (SLIC). Furthermore, some features are extracted from the superpixels and a bag-of-words model can be created. The initial classification can be obtained by a back propagation neural network (BPNN). To refine preliminary result, k-nearest neighbor (KNN) is used for reclassification and the final result is achieved. To verify the proposed method, we collected a BUS dataset containing 320 cases. The segmentation results of our method have been compared with the corresponding results obtained by five existing approaches. The experimental results show that our method achieved competitive results compared to conventional methods in terms of TP and FP, and produced good approximations to the hand-labelled tumor contours with comprehensive consideration of all metrics (the F1-score=89.87%±4.05%, and the average radial error=9.95%±4.42%).

Supervised Fine-Grained Cloud Detection and Recognition in Whole-Sky Images

The whole-sky imager has been increasingly used for ground-based cloud automatic observation. Many approaches based on image processing have been applied to detect or classify clouds in whole-sky images (WSIs). However, most of the studies only focus on image segmentation for cloud detection or image classification for cloud recognition separately. The cloud detection only does the binary segmentation (sky and cloud) without cloud types, while the cloud recognition only gives the single image-level label without cloud coverage. In this paper, a fine-grained cloud detection and recognition task with a solution is proposed to fill the gap, which can simultaneously detect and classify clouds in a WSI. It can be regarded as a pixel-level fine-grained dense prediction for images. First, a new data set is built with pixel-level annotation of nine different types. Then, a solution based on supervised learning is proposed, in which the pixel-level prediction problem is converted to a superpixel classification problem. Multiview features are extracted, including color, inside texture, neighbor texture, and global relation, to represent the superpixels. Moreover, a class-specific feature space transformation method based on metric learning and subspace alignment is proposed to overcome the challenge brought by the high similarity among cloud types and the feature shifting. Finally, several experiments have verified that our approach is effective to the challenging new task and also outperforms some other methods in the normal tasks of cloud detection and cloud classification, respectively.

SUPERPIXEL CLASSIFICATION OF HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGE BASED ON MULTI-SCALE CNN AND SCALE PARAMETER ESTIMATION

Abstract. In recent years, considerable attention has been paid to integrate convolutional neural network (CNN) with land cover classification of high spatial resolution remote sensing image. Per-pixel classification method based on CNN (Per-pixel CNN) achieved higher accuracy with the help of high-level features, however, this method still has limitations. Even though per-superpixel classification method based on CNN (Per-superpixel CNN) overcome the limitations of per-pixel CNN, classification accuracy of complex urban is easily influenced by scale effect. To solve this issue, superpixel classification method combining multi-scale CNN (Per-superpixel MCNN) method is proposed. Besides, this paper proposes a novel spatial statistics based method to estimate applicable scale parameter of per-superpixel CNN. Experiments using proposed method were performed on Digital Orthophoto Quarer Quad (DOQQ) images in urban and suburban area. Classification results show that per-superpixel MCNN can effectively avoid misclassification in complex urban area compared with per-superpixel classification method combining single-scale CNN (Per-superpixel SCNN). Series of classification results also show that using the pre-estimated scale parameter can guarantee high classification accuracy, thus arbitrary nature of scale estimation can be avoided to some extent.

An automated glaucoma screening system using cup-to-disc ratio via Simple Linear Iterative Clustering superpixel approach

Glaucoma is an ocular disease caused by damaged optic nerve head (ONH) due to high intraocular pressure (IOP) within the eyeball. Usually, glaucoma patients will not realize the presence of this disease due to lack of visible early symptoms such as pain and redness mark. The disease can cause permanent blindness if it is not treated immediately. Hence, glaucoma screening is very crucial in detecting the disease during the early stages. There are various types of glaucoma screening tests such as tonometry test which is based on IOP measurement, ophthalmology test which is based on shape and color of the eyes, and pachymetry test which is based on complete field vision measurement. All these three screening tests involve manual assessment which is time-consuming and costly. Therefore, an efficient glaucoma screening system that can automatically analyze the severity level of the disease is very much needed. Thus, the main objective of this paper is to develop an automatic glaucoma screening system based on superpixel classification by providing a high-quality input image. Firstly, input images are undergone preprocessing methods to cater for noise removal and illumination correction. This is emphasized in the implementation of the anisotropic diffusion filter and illumination correction method. The pixels of the input images are then aggregate into superpixels using Simple Linear Iterative Clustering (SLIC) approach. Then, image features based on histogram data and textural information are extracted on each superpixel using statistical pixel-level (SPL) method. The prominent features are then fed into Support Vector Machine (SVM) classifier to classify each superpixel into optic disc, optic cup, blood vessel, and background regions. The classifier is also used to determine the boundaries of both optic disc and optic cup. Lastly, the segmented optic disc and optic cup are used to determine the presence of glaucoma using cup-to-disc ratio (CDR) measurement. The proposed method has been tested on RIM-One database. The experimental results have successfully distinguished optic disc and optic cup from the background with an average accuracy and sensitivity of 98.6% and 92.3%, respectively tested on linear kernel.

Mapping of Coastal Cities Using Optimized Spectral–Spatial Features Based Multi-Scale Superpixel Classification

The high interior heterogeneity of land surface covers in high-resolution image of coastal cities makes classification challenging. To meet this challenge, a Multi-Scale Superpixels-based Classification method using Optimized Spectral–Spatial features, denoted as OSS-MSSC, is proposed in this paper. In the proposed method, the multi-scale superpixels are firstly generated to capture the local spatial structures of the ground objects with various sizes. Then, the normalized difference vegetation index and extend multi-attribute profiles are introduced to extract the spectral–spatial features from the multi-spectral bands of the image. To reduce the redundancy of the spectral–spatial features, the crossover-based search algorithm is utilized for feature optimization. The pre-classification results at each single scale are, therefore, obtained based on the optimized spectral–spatial features and random forest classifier. Finally, the ultimate classification is generated via the majority voting of those pre-classification results in each scale. Experimental results on the Gaofen-2 image of Qingdao and WorldView-2 image of Hong Kong, China confirmed the effectiveness of the proposed method. The experiments verify that the OSS-MSSC method not only works effectively on the homogeneous regions, but also is able to preserve the small local spatial structures in the high-resolution remote sensing images of coastal cities.

Influence of normalization and color features on super-pixel classification: application to cytological image segmentation

Super-pixel feature extraction is a key problem to get an acceptable performance in color super-pixel classification. Given a color feature extraction problem, it is necessary to know which is the best approach to solve this problem. In the current work, we're interested in the challenge of nucleus and cytoplasm automatic recognition in the cytological image. We propose an automatic process for white blood cells (WBC) segmentation using super-pixel classification. The process is divided into five steps. In first step, the color normalization is calculated. The super-pixels generation by Simple Linear Iterative Clustering algorithm is performed in the second step. In third step, the color property is used to achieve illumination invariance. In fourth step, color features are calculated on each super-pixel. Finally, supervised learning is realized to classify each super-pixel into nucleus and cytoplasm region. The present work rallied an exhaustive statistical evaluation of a very wide variety of the color super-pixel classification, with height normalization methods, four-color spaces and four feature extraction techniques. Normalization and color spaces slightly increase the average accuracy of super-pixel classification. Our experiments based to statistical comparison allow to conclude that comprehensive gray world normalized normalization is better than without normalization for super-pixel classification achieving the first positions in the Friedman ranking. RGB space is the best color spaces to be used in super-pixel feature extraction for nucleus and cytoplasm segmentation. For feature extraction, the learning methods work better on the first order statistics features for the automatic WBC segmentation.