Watershed Algorithm Research Articles

基于标记分水岭分割算法在矿石异物检测应用研究

提出一种改进的分水岭分割算法和目标几何特征提取相结合的目标检测方法，应用于传送带矿石中的异物检测。矿石图像噪声及边缘连接严重，分水岭算法产生过分割及欠分割问题。本文通过优化矿石种子区域，改善分割缺陷，并提取分割目标的几何特征，通过特征统计分析，实施矿石异物检测。实验结果表明，该算法可准确获得矿石边界，并能有效的对图像中异物进行标记。 This article describes an improved target detection method which combines the watershed seg-mentation algorithm and targeting geometric feature extraction. It is used in the area of detecting impurities, ore image noise and edge connections in conveyor belts. The watershed algorithm causes over-segmentation and under-segmentation in the detection work as the noise area gravely connected to the edge of ore objects. This article concentrates on optimizing the ore seed area, improving segmentation defects to extract the geometric characteristics of the segmentation target and implementation of the ore impurities detection by feature statistical analysis. As shown in the experimental results, such algorithm can obtain the ore boundary accurately, as well as mark the impurities from images effectively.

A Support Vector Machine with Gabor Features for Animal Intrusion Detection in Agriculture Fields

Animal intrusion in agricultural fields has been a pestering problem for farmers, especially during monsoon when they try to maximize their yield. This paper puts forth an image processing and machine learning based approach to classify the animal as threat and hence alert the farmer. The image is segmented into parts using Watershed algorithm. The features are extracted from the training set by using 2D Gabor filter bank. Classification is done using Support Vector Machines algorithm. Percentage accuracy for each test image is analyzed. Training set has been increased in a step wise manner in order to find the minimum possible combination of test images and filter bank and hence increase the efficiency of the model compared to the existing models.

Algebraic Multi-Grid Based Multi-Focus Image Fusion Using Watershed Algorithm

This paper proposes a new multi-focus image fusion method named AMGW, and it is based on algebraic multi-grid (AMG) algorithm and watershed segmentation method. In the implementation, the coarse grids of the source images are first extracted with the affinity matrix, and with a spatial interpolation function the approximation of the source image can be reconstructed from the coarse grids. A considerable amount of edge and textural information is still preserved in such approximation. The two source images are compared with their corresponding approximation block by block respectively by employing the mean square error (MSE) as a sharpness criterion. The MSE values are then used to identify the blocks of higher fidelity from the source images. The watershed segmentation is applied to those uncertain blocks in one source image. The two source images are compared again with the MSEs of the segmented regions. The fused image is obtained by reserving the blocks and regions with higher MSEs and applying a post-processing operation. Experimental results demonstrate that the AMG-based method outperforms the state-of-the-art fusion approaches in terms of selected objective image quality assessments. The details of the source images are well preserved in the fused image.

Mature Tomato Fruit Detection Algorithm Based on improved HSV and Watershed Algorithm

Tomato is well known fruit since it has many essential and beneficial nutrients like antioxidant, vitamin C and A for human daily diet. Tomato picking by hand is both labor and time consuming. Therefore, to overcome these issues, tomato needs to be picked up automatically with the help of harvesting robot. Recently automation of fruit harvesting gains great popularity. To guide the harvesting robot to pick up the fruit correctly, it is important to correctly detect and find the location of the red mature fruit. In this study, a new mature tomato detection algorithm based on the improved HSV (Hue, Saturation, Value) color space and the improved watershed segmentation was proposed, by using a cheap and easily accessible RGB camera for guiding a robot to pick up red tomatoes automatically. For that purpose, the color images of tomato plants were captured under natural light. At the first stage, improved HSV transform was used to remove background and to detect only red tomatoes. Then the morphological operations were applied to modify the detected fruit. The second step was the separation of connected fruits, so that the harvesting robot can pick up fruit correctly. To achieve this task, the improved watershed algorithm was applied. As a result, the detection of separated red mature tomato was done by using the improved HSV and watershed, with uneven illumination and complex background. The overall red fruit detection accuracy was up to 81.6%, and it shows good potential to be used on harvesting robot.

Tumor Spheres Quantification with Smoothed Euclidean Distance Transform.

Tumor sphere quantification plays an important role in cancer research and drugs screening. Even though the number and size of tumor spheres can be found manually, this process is time-consuming, prone to making errors, and may not be viable when the number of images is very large. This manuscript presents a method for automated quantification of spheres with a novel segmentation technique. The segmentation method relies on initial watershed algorithm which detects the minima of the distance transform and finds a tumor sphere for each minimum. Due to the irregular edges of tumor spheres, the distance transform matrix has often more number of minima than the true number of spheres. This leads to the over segmentation problem. The proposed approach uses the smoothed form of the distance transform to effectively eliminate superfluous minima and then seeds the watershed algorithm with the remaining minima. The proposed method was validated over pancreatic tumor spheres images achieving high efficiency for tumor spheres quantification.

Analysis of moisture and total sugar content of Huizao based on surface images

Moisture and total sugar content are two important internal qualities of Huizao. In order to explore their correlation with external qualities, a novel method of moisture and total sugar content analysis was proposed based on surface images. Firstly, five geometric features and seven texture features of Huizao were obtained to be the external quality indexes by digital image processing technology. Secondly, the wrinkle degree as an important index was extracted by marked watershed segmentation algorithm. According to the external quality the Huizao samples were grouped, and the moisture and total sugar content were determined through physical and chemical methods. Lastly, the moisture and total sugar content and twelve external indexes were all processed by step discriminatory analysis. Meanwhile, the regression models of moisture content with short diameter, contrast, and wrinkle degree and total sugar with wrinkle degree were established. The coefficients of the model were 0.9992 and 0.9978 respectively, and all the significance was less than 0.01, which show that the regression equation and regression coefficient effect are highly significant. The results indicate that the moisture and total sugar content of Huizao are greatly correlated with the wrinkle degree. The moisture and total sugar content are the highest when the wrinkle degree is at 2 to 3 grade, and they decrease gradually with the wrinkle degree increasing. Moisture content shows positive correlation with the size of Huizao. The results of model analysis agree well with the experimental results, which can provide valuable reference for improving Huizao grade diversity. Keywords: Huizao, step discriminatory analysis, moisture content, total sugar DOI: 10.25165/j.ijabe.20181104.3386 Citation: Zhang J X, Ma Q Q, He F, Qu F, Li W. Analysis of moisture and total sugar content of Huizao based on surface images. Int J Agric & Biol Eng, 2018; 11(4): 238-243.

Regularized Surface and Point Landmarks Based Efficient Non-Rigid Medical Image Registration

Medical image registration is one of the fundamental tasks in medical image processing. It has various applications in field of image guided surgery (IGS) and computer assisted diagnosis (CAD). A set of non-linear methods have been already developed for inter-subject and intra-subject 3D medical image registration. However, efficient registration in terms of accuracy and speed is one of the most demanded of today surgical navigation (SN) systems. This paper is a result of a series of experiments which utilizes Fast Radial Basis Function (RBF) technique to register one or more medical images non-rigidly. Initially, a set of curves are extracted using a combined watershed and active contours algorithm and then tiled and converted to a regular surface using a global parameterization algorithm. It is shown that the registration accuracy improves when higher number of salient features (i.e. anatomical point landmarks and surfaces) are used and it also has no impact on the speed of the algorithm. The results show that the target registration error is less than 2 mm and has sub-second performance on intra-subject registration of MR image real datasets. It is observed that the Fast RBF algorithm is relatively insensitive to the increasing number of point landmarks used as compared with the competing feature based algorithms.

基于迭代H-minima改进分水岭算法的高分辨率遥感影像单木树冠提取

基于迭代H-minima改进分水岭算法的高分辨率遥感影像单木树冠提取

A Minimum Barrier Distance based Saliency Box for Object Proposals Generation

Object proposals generation plays an important role in computer vision. A good object proposals generation model should assign obviously high and low objectness score to the window that contains complete objects and incomplete objects, respectively. However, some existing methods such as local contrast based models usually fail to satisfy this requirement. In this letter, we propose MBDSal Box, a minimum barrier distance (MBD) based saliency box for locating object proposals. MBDSal Box consists of three components: item: First, a window saliency computation module that calculates the MBD saliency of each sliding window; second, a window refinement module that provides more accurate bounding boxes by a marker based watershed algorithm; third, a window scoring module which combines multiple features to compute the final objectness score. The experimental results carried on PASCAL VOC 2007 and Microsoft COCO 2014 datasets show that our model achieves better performance than the state-of-the-art models with competitive speed.

Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures

A plethora of information contained in full-waveform (FW) Light Detection and Ranging (LiDAR) data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM) using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW) algorithms. Subsequently, the Random forests (RF) and Conditional inference forests (CF) models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak) and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR) using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF) and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR) and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due to the similar characteristics of blue oak and interior live oak. Uncertainty estimates from the BMLR method compensate for this downside by providing classification results in a probabilistic sense and rendering users with more confidence in interpreting and applying classification results to real-world tasks such as forest inventory. Overall, this study recommends the CF method for feature selection and suggests that BMLR could be a superior alternative to classical machining learning methods.

The recognition of apple fruits in plastic bags based on block classification

The recognition of apple fruits in plastic bags is easy to be affected by reflected and refracted light. In order to weaken the influence of light, a method based on block classification is proposed. The method adopts watershed algorithm to segment original images into irregular blocks based on edge detection results of R–G grayscale images firstly. Compared with the watershed algorithm based on gradient images, the segmentation method can preserve fruits edge and reduce the number of blocks by 20.31%, because graying image method, R–G, filters most of leaves and edge detection operator insures that the edge of fruits are detected accurately. Next, these blocks are classified into fruit blocks and non-fruit blocks by support vector machine on the basis of the color and texture features extracted from blocks. Compared with the image recognition method based on pixel classification, the proposed method can restrain the interference of light caused by plastic bags effectively. The false negative rate (FNR) and false positive rate (FPR) of the method based on pixel classification are 21.71 and 14.53% respectively. The FNR and FPR of the proposed method are 4.65 and 3.50% respectively.

Boundary Detection of Dispersal Impact Craters Based on Morphological Characteristics Using Lunar Digital Elevation Model

Lunar impact craters are the most typical geomorphic unit found on the moon and are of great significance for the study of terrain features. Currently, most mainstream detection algorithms for lunar impact craters represent craters as circles, but these methods counter difficulty in expressing the real shapes in an accurate manner. It is difficult to conduct an advanced analysis, such as characteristic and spatial heterogeneity analyses of the lunar surface. The lunar terrain characteristics were analyzed using dispersal impact craters as the object, and a dispersal crater detection algorithm (CDA) based on a digital elevation model (DEM-based CDA) was proposed. By analyzing the surface catchment, the impact crater can be treated as a closed basin structure. The raw impact crater region is detected using watershed algorithm. This algorithm can detect the real boundaries of an impact crater based on the actual terrain. Several morphological factors, such as posture ratio and rectangle factor, are used to filter the raw impact crater regions. A suborbicular raw impact crater region is treated as the desired result after the elimination of false impact craters. For the remaining raw impact crater regions, terrain profile analysis is applied to accurately identify the boundaries of impact craters. The DEM data produced from the Chang'E-2 imagery and LRO laser altimeter data (20 and 60 m) are used in verification. The results show that the impact crater boundaries with real terrain characteristics can be effectively expressed and used in further exploration.

AN EXTENDED SPECTRAL–SPATIAL CLASSIFICATION APPROACH FOR HYPERSPECTRAL DATA

Abstract. In this paper an extended classification approach for hyperspectral imagery based on both spectral and spatial information is proposed. The spatial information is obtained by an enhanced marker-based minimum spanning forest (MSF) algorithm. Three different methods of dimension reduction are first used to obtain the subspace of hyperspectral data: (1) unsupervised feature extraction methods including principal component analysis (PCA), independent component analysis (ICA), and minimum noise fraction (MNF); (2) supervised feature extraction including decision boundary feature extraction (DBFE), discriminate analysis feature extraction (DAFE), and nonparametric weighted feature extraction (NWFE); (3) genetic algorithm (GA). The spectral features obtained are then fed into the enhanced marker-based MSF classification algorithm. In the enhanced MSF algorithm, the markers are extracted from the classification maps obtained by both SVM and watershed segmentation algorithm. To evaluate the proposed approach, the Pavia University hyperspectral data is tested. Experimental results show that the proposed approach using GA achieves an approximately 8 % overall accuracy higher than the original MSF-based algorithm.

Brain Tumor Segmentation using Watershed Technique and Self Organizing Maps

Objectives: To segment tumor with higher accuracy. Methods/Statistical Analysis: Noise removal is done with the help of Gabor filter as a preprocessing step. Skull stripping is done to remove non cerebral regions using thresholding and morphological operations. Segmentation using watershed algorithm is done, as it achieves exact location of outline. Unsupervised type of neural network i.e. self organizing maps is used for classification. Finding: It has been analyzed that by combining watershed and neural networks segmentation accuracy has been improved to 95.93%. The motive of the research is to segment the tumor with precision using computerized segmentation algorithm that can help physicians to analyze brain diseases and treatment can be started as soon as possible. Applications: The proposed technique can be used in image processing of brain tumor detection. Keywords: Brain Tumor Segmentation, Image Segmentation, Magnetic Resonance Imaging (MRI), Self Organizing Maps (SOM), Stationary Wavelet Transform (SWT)

Cervical cancer histology image identification method based on texture and lesion area features

The issue of an automated approach for detecting cervical cancer is proposed to improve the accuracy of recognition. Firstly, the cervical cancer histology source images are needed to use image preprocessing for reducing the impact brought by noise of images as well as the impact on subsequent precise feature extraction brought by irrelevant background. Secondly, the images are grouped into ten vertical images and the information of texture feature is extracted by Grey Level Co-occurrence Matrix (GLCM). GLCM is an effective tool to analyze the features of texture. The textures of different diseases in the source image of Cervical Cancer Histology (such as contrast, correlation, entropy, uniformity and energy, etc.) can all be obtained in this way. Thirdly, the image is segmented by using K-means clustering and Marker-controlled watershed Algorithm. And each vertical image is divided into three layers to calculate the areas of different layers. Based on GLCM and lesion area features, the tissues are investigated with segmentation by using Support Vector Machine (SVM) method. Finally, the results show that it is effective and feasible to recognize cervical cancer by automated approach and verified by experiment.

Detection of early bruises on peaches (Amygdalus persica L.) using hyperspectral imaging coupled with improved watershed segmentation algorithm

Bruise is the most common type of damage to peaches in a major cause of quality loss. However, fast and nondestructive detection of early bruises on peaches is a challenging task. In this study, short-wave near infrared (SW-NIR) and long-wave near infrared (LW-NIR) hyperspectral imaging technologies were observed and compared the ability to discriminate bruised from sound regions. Principal components analysis (PCA) was utilized to select the effective wavelengths for each type of imaging mode. SW-NIR imaging mode was more suitable for detection of early bruises on peaches. A novel improved watershed segmentation algorithm based on morphological gradient reconstruction and marker extraction was developed and applied to the multispectral PC images. The detection results indicated that for all test peaches used in this experiment, 96.5% of the bruised and 97.5% of sound peaches were accurately identified, respectively. A proposed algorithm was superior to the common segmentation methods including Ostu and the global threshold value method. This study demonstrated that SW-NIR hyperspectral imaging coupled with the proposed improved watershed segmentation algorithm could be a potential approach for detection of early bruises on peaches.

エッジ特徴を用いたWatershedアルゴリズムの改善とその髪型抽出への応用(映像メディアおよび一般 : インターネット, デジタル放送, マルチメディア, 三次元画像, 視覚と画質評価, ITS等)

エッジ特徴を用いたWatershedアルゴリズムの改善とその髪型抽出への応用(映像メディアおよび一般 : インターネット, デジタル放送, マルチメディア, 三次元画像, 視覚と画質評価, ITS等)

Automated red blood cells extraction from holographic images using fully convolutional neural networks.

In this paper, we present two models for automatically extracting red blood cells (RBCs) from RBCs holographic images based on a deep learning fully convolutional neural network (FCN) algorithm. The first model, called FCN-1, only uses the FCN algorithm to carry out RBCs prediction, whereas the second model, called FCN-2, combines the FCN approach with the marker-controlled watershed transform segmentation scheme to achieve RBCs extraction. Both models achieve good segmentation accuracy. In addition, the second model has much better performance in terms of cell separation than traditional segmentation methods. In the proposed methods, the RBCs phase images are first numerically reconstructed from RBCs holograms recorded with off-axis digital holographic microscopy. Then, some RBCs phase images are manually segmented and used as training data to fine-tune the FCN. Finally, each pixel in new input RBCs phase images is predicted into either foreground or background using the trained FCN models. The RBCs prediction result from the first model is the final segmentation result, whereas the result from the second model is used as the internal markers of the marker-controlled transform algorithm for further segmentation. Experimental results show that the given schemes can automatically extract RBCs from RBCs phase images and much better RBCs separation results are obtained when the FCN technique is combined with the marker-controlled watershed segmentation algorithm.

Concurrent computation of topological watershed on shared memory parallel machines

Abstract The watershed transform is considered as the most appropriate method for image segmentation in the field of mathematical morphology. In the following paper, we present an adapted topological watershed algorithm suited for a rapid and effective implementation on Shared Memory Parallel Machine (SMPM). The introduced algorithm allows a parallel watershed computing while preserving the given topology. No prior minima extraction is needed, nor the use of any sorting step or hierarchical queue. The strategy that guides the parallel watershed computing, labeled SDM-Strategy (equivalent to Split-Distributes and Merge), is also presented. Experimental analyses such as execution time, performance enhancement, cache consumption, efficiency and scalability are also presented and discussed.

VMP1-related autophagy induced by fructose rich diet in ß-cells: Its prevention by incretins

The watershed transform is considered as the most appropriate method for image segmentation in the field of mathematical morphology. In the following paper, we present an adapted topological watershed algorithm suited for a rapid and effective implementation on Shared Memory Parallel Machine (SMPM). The introduced algorithm allows a parallel watershed computing while preserving the given topology. No prior minima extraction is needed, nor the use of any sorting step or hierarchical queue. The strategy that guides the parallel watershed computing, labeled SDM-Strategy (equivalent to Split-Distributes and Merge), is also presented. Experimental analyses such as execution time, performance enhancement, cache consumption, efficiency and scalability are also presented and discussed.