Marker-controlled Watershed Transformation Research Articles

Comparing Deep Learning and MCWST Approaches for Individual Tree Crown Segmentation

Abstract. Accurate segmentation of individual tree crowns (ITC) segmentation is essential for investigating tree-level based growth trends and assessing tree vitality. ITC segmentation using remote sensing data faces challenges due to crown heterogeneity, overlapping crowns and data quality. Currently, both classical and deep learning methods have been employed for crown detection and segmentation. However, the effectiveness of deep learning based approaches is limited by the need for high-quality annotated datasets. Benefiting from the BaKIM project, a high-quality annotated dataset can be provided and tested with a Mask Region-based Convolutional Neural Network (Mask R-CNN). In addition, we have used the deep learning based approach to detect the tree locations thus refining the previous Marker controlled Watershed Transformation (MCWST) segmentation approach. The experimental results show that the Mask R-CNN model exhibits better model performance and less time cost compared to the MCWST algorithm for ITC segmentation. In summary, the proposed framework can achieve robust and fast ITC segmentation, which has the potential to support various forest applications such as tree vitality estimation.

A Novel Segmentation Recognition Algorithm of Agaricus bisporus Based on Morphology and Iterative Marker-Controlled Watershed Transform

Accurate recognition of Agaricus bisporus is a prerequisite for precise automatic harvesting in a factory environment. Aimed at segmenting mushrooms adhering together from the complex background, this paper proposes a watershed-based segmentation recognition algorithm for A. bisporus. First, the foreground of A. bisporus is extracted via Otsu threshold segmentation and morphological operations. Then, a preliminary segmentation algorithm and a novel iterative marker generation method are proposed to prepare watershed markers. On this basis, a marker-controlled watershed algorithm is adopted to segment and recognize A. bisporus individuals. All the algorithms are implemented based on OpenCV (Open Source Computer Vision) libraries. Tests on images of A. bisporus collected at the cultivation bed show that the average correct recognition rate of the proposed algorithm is 95.7%, the average diameter measurement error is 1.15%, and the average coordinate deviation rate is 1.43%. The average processing time is 705.7 ms per single image, satisfying the real-time constraints based on 1 image/s. The proposed algorithm performed better than the current Circle Hough Transform (OpenCV’s implementation). It is convenient and easy to operate, providing a sound basis for subsequent research on mechanized harvesting equipment for A. bisporus.

Using Marker-Controlled Watershed Transform to Detect Baker's Cyst in Magnetic Resonance Imaging Images: A Pilot Study.

Nowadays, magnetic resonance imaging (MRI) has a high ability to distinguish between soft tissues because of high spatial resolution. Image processing is extensively used to extract clinical data from imaging modalities. In the medical image processing field, the knee's cyst (especially Baker) segmentation is one of the novel research areas. There are different methods for image segmentation. In this paper, the mathematical operation of the watershed algorithm is utilized by MATLAB software based on marker-controlled watershed segmentation for the detection of Baker's cyst in the knee's joint MRI sagittal and axial T2-weighted images. The performance of this algorithm was investigated, and the results showed that in a short time Baker's cyst can be clearly extracted from original images in axial and sagittal planes. The marker-controlled watershed segmentation was able to detect Baker's cyst reliable and can save time and current cost, especially in the absence of specialists it can help us for the easier diagnosis of MRI pathologies.

Identification of Breast Malignancy by Marker-Controlled Watershed Transformation and Hybrid Feature Set for Healthcare

Breast cancer is a highly prevalent disease in females that may lead to mortality in severe cases. The mortality can be subsided if breast cancer is diagnosed at an early stage. The focus of this study is to detect breast malignancy through computer-aided diagnosis (CADx). In the first phase of this work, Hilbert transform is employed to reconstruct B-mode images from the raw data followed by the marker-controlled watershed transformation to segment the lesion. The methods based only on texture analysis are quite sensitive to speckle noise and other artifacts. Therefore, a hybrid feature set is developed after the extraction of shape-based and texture features from the breast lesion. Decision tree, k-nearest neighbor (KNN), and ensemble decision tree model via random under-sampling with Boost (RUSBoost) are utilized to segregate the cancerous lesions from the benign ones. The proposed technique is tested on OASBUD (Open Access Series of Breast Ultrasonic Data) and breast ultrasound (BUS) images collected at Baheya Hospital Egypt (BHE). The OASBUD dataset contains raw ultrasound data obtained from 100 patients containing 52 malignant and 48 benign lesions. The dataset collected at BHE contains 210 malignant and 437 benign images. The proposed system achieved promising accuracy of 97% with confidence interval (CI) of 91.48% to 99.38% for OASBUD and 96.6% accuracy with CI of 94.90% to 97.86% for the BHE dataset using ensemble method.

Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN

Accurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. However, it is difficult to automatically segment individual tooth in cone beam computed tomography (CBCT) images due to the blurring boundaries of neighboring teeth and the similar intensities between teeth and mandible bone. In this work, we propose the use of a multi-task 3D fully convolutional network (FCN) and marker-controlled watershed transform (MWT) to segment individual tooth. The multi-task FCN learns to simultaneously predict the probability of tooth region and the probability of tooth surface. Through the combination of the tooth probability gradient map and the surface probability map as the input image, MWT is used to automatically separate and segment individual tooth. Twenty-five dental CBCT scans are used in the study. The average Dice similarity coefficient, Jaccard index, and relative volume difference are 0.936 (±0.012), 0.881 (±0.019), and 0.072 (±0.027), respectively, and the average symmetric surface distance is 0.363 (±0.145) mm for our method. The experimental results demonstrate that the multi-task 3D FCN combined with MWT can segment individual tooth of various types in dental CBCT images.

Glaucoma Detection in Retinal Images using Automatic Thresholding and Marker - Controlled Watershed Transformation

The eye is an organ in human, responsible for the vision. However, it gets affected by the diseases. Glaucoma is a one such eye disease. It develops in the eye due to the increase in intra-ocular pressure. If glaucoma is not treated in its initial stage, leads for permanent vision loss. This work is aimed to develop a computer aided diagnosis system for glaucoma detection in fundus retinal images. In this paper, we presented a method to automatically outline the optic disc in a retinal image by automatic thresholding technique. The optic cup is segmented based on marker-controlled automatic watershed transformation. The optic cup to disc ratio (OCDR) is calculated, to show the presence of glaucoma. The proposed work is assessed with 15 normal retinal images and 15 retinal images with glaucoma, retrospectively collected from the Annai Eye Clinic, Chennai. To validate the system performance, obtained results were compared with the ophthalmologist results (taken as the gold standard). The experimental results show that, the proposed work is potential for the glaucoma detection.

Automated integrated system for stained neuron detection: An end-to-end framework with a high negative predictive rate

Background and objectiveMapping the architecture of the brain is essential for identifying the neural computations that affect behavior. Traditionally in histology, stained objects in tissue slices are hand-marked under a microscope in a manually intensive, time-consuming process. An integrated hardware and software system is needed to automate image acquisition, image processing, and object detection. Such a system would enable high throughput tissue analysis to rapidly map an entire brain. MethodsWe demonstrate an automated system to detect neurons using a monkey brain slice immunohistochemically stained for retrogradely labeled neurons. The proposed system obtains a reconstructed image of the sample, and stained neurons are detected in three steps. First, the reconstructed image is pre-processed using adaptive histogram equalization. Second, candidates for stained neurons are segmented from each region via marker-controlled watershed transformation (MCWT) using maximally stable extremal regions (MSERs). Third, the candidates are categorized as neurons or non-neurons using deep transfer learning via pre-trained convolutional neural networks (CNN). ResultsThe proposed MCWT algorithm was compared qualitatively against MorphLibJ and an IHC analysis tool, while our unified classification algorithm was evaluated quantitatively using ROC analyses. The proposed classification system was first compared with five previously developed layers (AlexNet, VGG-16, VGG-19, GoogleNet, and ResNet). A comparison with conventional multi-stage frameworks followed using six off-the-shelf classifiers [Bayesian network (BN), support vector machines (SVM), decision tree (DT), bagging (BAG), AdaBoost (ADA), and logistic regression (LR)] and two descriptors (LBP and HOG). The system achieved a 0.918 F1-score with an 86.6% negative prediction value. Remarkably, other metrics such as precision, recall, and F-scores surpassed the 90% threshold compared to traditional methods. ConclusionsWe demonstrate a fully automated, integrated hardware and software system for rapidly acquiring focused images and identifying neurons from a stained brain slice. This system could be adapted for the identification of stained features of any biological tissue.

Automated Segmentation of Optic Disc and Cup in Color Fundus Images

An automatic Optic disc and Optic cup detection technique which is an important step in developing systems for computer-aided eye disease diagnosis is presented in this paper. This paper presents an algorithm for localization and segmentation of optic disc from digital retinal images. OD localization is achieved by circular Hough transform using morphological preprocessing and segmentation is achieved by watershed transformation. Optic cup segmentation is achieved by marker controlled watershed transformation. The optic disc to cup ratio (CDR) is calculated which is an important parameter for glaucoma diagnosis. The presented algorithm is evaluated against publically available DRIVE dataset. The presented methodology achieved 88% average sensitivity and 80% average overlap. The average CDR detected is 0.1983.

Analyzing the Optimal Performance of Pest Image Segmentation using Non Linear Objective Assessments

<p>In modern agricultural field, pest detection is a major role in plant cultivation. In order to increase the Production rate of agricultural field, the presence of whitefly pests which cause leaf discoloration is the major problem. This emphasizes the necessity of image segmentation, which divides an image into parts that have strong correlations with objects to reflect the actual information collected from the real world. Image processing is affected by illumination conditions, random noise and environmental disturbances due to atmospheric pressure or temperature fluctuation. The quality of pest images is directly affected by atmosphere medium, pressure and temperature. The fuzzy c means (FCM) have been proposed to identify accurate location of whitefly pests. The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However, when applied to pest image analysis, it has important drawbacks (over segmentation, sensitivity to noise). In this paper, pest image segmentation using marker controlled watershed segmentation is presented. Objective of this paper is segmenting the pest image and comparing the results of fuzzy c means algorithm and marker controlled watershed transformation. The performance of an image segmentation algorithms are compared using nonlinear objective assessment or the quantitative measures like structural content, peak signal to noise ratio, normalized correlation coefficient, average difference and normalized absolute error. Out of the above methods the experimental results show that fuzzy c means algorithm performs better than watershed transformation algorithm in processing pest images.</p>

Automatic color correction: region-based approach and performance evaluation using full reference metrics

We propose a solution for automatic color correction between two images/videos based on region correspondences. It starts with image segmentation by marker-controlled watershed transformation, which is faster and produces more uniform regions with better adherence to object boundaries than the segmentation in previous color correction approaches. Then regions between two images are matched using point feature correspondences, which are invariant to geometric transformation and illumination change. Finally, the color-distorted image is corrected using the color statistics of corresponding regions and the color transfer functions weighted by influence masks. We demonstrate the experimental results using several data sets and evaluate the color correction by different measures of image similarity.

Waterpixels.

Many approaches for image segmentation rely on a first low-level segmentation step, where an image is partitioned into homogeneous regions with enforced regularity and adherence to object boundaries. Methods to generate these superpixels have gained substantial interest in the last few years, but only a few have made it into applications in practice, in particular because the requirements on the processing time are essential but are not met by most of them. Here, we propose waterpixels as a general strategy for generating superpixels which relies on the marker controlled watershed transformation. We introduce a spatially regularized gradient to achieve a tunable tradeoff between the superpixel regularity and the adherence to object boundaries. The complexity of the resulting methods is linear with respect to the number of image pixels. We quantitatively evaluate our approach on the Berkeley segmentation database and compare it against the state-of-the-art.

Extraction of Brain Tumour in MRI Images using Marker Controlled Watershed Transform Technique in MATLAB

In recent years, substantial research has been carried out in the field of image processing to evaluate different structures and information from images. Image processing techniques have played a pivotal role in a wide range of medical image applications. They have been widely used to design different computational algorithms for extracting clinical information from medical images in different modalities including MRI, CT and Ultrasound. This paper aims to propose the use of image processing techniques in the medical field. The objective of this paper is to develop a MATLAB based algorithm that can be used to extract a brain tumor from a MRI Image. In this research, we have performed some noise removal functions, segmentation techniques and morphological operations for detection and extraction which are the basic concepts of image processing. We have developed a Watershed Transform technique based on internal and external markers. The detection and extraction of tumor from MRI image of the brain is done by using MATLAB software.

Machine learning approach for automated screening of malaria parasite using light microscopic images

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification.

Structural and textural classification of erythrocytes in anaemic cases: A scanning electron microscopic study

The objective of this study is to address quantitative microscopic approach for automated screening of erythrocytes in anaemic cases using scanning electron microscopic (SEM) images of unstained blood cells. Erythrocytes were separated from blood samples and processed for SEM imaging. Thereafter, erythrocytes were segmented using marker controlled watershed transformation technique. Total 47 structural and textural features of erythrocytes were extracted using various mathematical measures for six types of anaemic cases as compared to the control group. These features were statistically evaluated at 1% level of significance and subsequently ranked using Fisher's F-statistic describing the group discriminating potentiality. Amongst all extracted features, twenty nine features were found to be statistically significant (p<0.001). Finally, Bayesian classifier was applied to classify six types of anaemia based on top seventeen ranked features those of which are of course statistically significant. The present study yielded a predictive accuracy of 88.99%.

Automatic vehicle extraction from airborne LiDAR data of urban areas aided by geodesic morphology

In this study, we address one of the key issues in traffic monitoring of urban areas using airborne laser scanning (ALS) data – vehicle extraction. Our aim is to automatically segment point sets of single vehicles solely relying on the geometric components of ALS data. To tackle the complexity of vehicle appearance in ALS data, a context-guided approach based on geometric model of vehicle is proposed to accomplish the task. Ground level separation is firstly used to exclude the irrelevant objects and provide the “Region of Interest”. The marker-controlled watershed transformation assisted by morphological reconstruction is then performed on the filled height raster of ground level to isolate vehicles. The results from different ALS datasets are evaluated with respect to the semantic and geometric accuracy, respectively. They clearly show the high potential of airborne LiDAR in outlining single vehicles in urban areas, which allows accurate 3D point retrieval of single vehicles. Based on moving object model, the examination of vehicle movement is becoming feasible when the extracted vehicle points undergo the shape parametrization.

Feature based characterization of worn surfaces for a sliding test

In this paper a novel 3D surface characterization technique—feature based characterization—is applied to analyse worn surfaces from a ball on disc sliding test. This technique concentrates on analysis of surface features that are related to tribological behaviour. The worn surfaces of discs are segmented according to their surface texture primitives in order to analyse the shapes of the asperities. In order to remove shapes and unnecessary features of the ball surfaces, a filtering technique through wavelet analysis is applied. Then the significant features are extracted by means of a marker controlled watershed transformation. As a result, the relationship between the feature based parameters and the tribological behaviour is presented.

Computerized lesion segmentation of breast ultrasound based on marker‐controlled watershed transformation

This paper presents a computerized segmentation method for breast lesions on ultrasound (US) images. It consists of first applying a contrast-enhanced approach, i.e., a contrast-limited adaptive histogram equalization. Then, aiming at removing speckle and enhancing the lesion boundary, an anisotropic diffusion filter, guided by texture descriptors derived from a set of Gabor filters, is applied. To eliminate the distant pixels that do not belong to the tumor, the resulting filtered image is multiplied by a constraint Gaussian function. By doing so, both the segmentation and the marker functions are generated and could be used in the marker-controlled watershed transformation algorithm to create potential lesion boundaries. Finally, to determine the lesion contour, the average radial derivative function is evaluated. The proposed method was tested with 50 breast US images and 60 simulated "ultrasound-like" images. Accuracy and precision of the segmentation method were then assessed. For the accuracy, three parameters were used: Overlap ratio (OR), normalized residual value (nrv), and proportional distance (PD) between contours. The average results for US images were OR = 0.86 +/- 0.05, nrv = 0.16 +/- 0.06, and PD = 6.58 +/- 2.52%. For simulated ultrasound-like images, a better performance (OR = 0.92 +/- 0.01, nrv = 0.08 +/- 0.01, and PD = 3.20 +/- 0.53%) was achieved. The segmentation method proposed was capable of delineating the lesion contours with high accuracy in comparison to both the radiologists' delineations and the true delineations of simulated images. Moreover, this method was also found to be robust to human-dependent parameters variations.

Detecting dominant landscape objects through multiple scales: An integration of object-specific methods and watershed segmentation

Complex systems, such as landscapes, are composed of different critical levels of organization where interactions are stronger within levels than among levels, and where each level operates at relatively distinct time and spatial scales. To detect significant features occurring at specific levels of organization in a landscape, two steps are required. First, a multiscale dataset must be generated from which these features can emerge. Second, a procedure must be developed to delineate individual image-objects and identify them as they change through scale. In this paper, we introduce a framework for the automatic definition of multiscale landscape features using object-specific techniques and marker-controlled watershed segmentation. By applying this framework to a high-resolution satellite scene, image-objects of varying size and shape can be delineated and studied individually at their characteristic scale of expression. This framework involves three main steps: 1) multiscale dataset generation using an object-specific analysis and upscaling technique, 2) marker-controlled watershed transformation to automatically delineate individual image-objects as they evolve through scale, and 3) landscape feature identification to assess the significance of these image-objects in terms of meaningful landscape features. This study was conducted on an agro-forested region in southwest Quebec, Canada, using IKONOS satellite data. Results show that image-objects tend to persist within one or two scale domains, and then suddenly disappear at the next, while new image-objects emerge at coarser scale domains. We suggest that these patterns are associated to sudden shifts in the entire image structure at certain scale domains, which may correspond to critical landscape thresholds.