Region-based Image Segmentation Research Articles

A plant disease classification using one-shot learning technique with field images

Early diagnosis of plant diseases is crucial for preventing plagues and mitigating their effects on crops. The most precise automatic methods for identifying plant diseases using images of plant fields are powered by deep learning. Big image datasets should always be gathered and annotated for these methods to work, which is often not technically or financially feasible. This paper offers one-shot learning (OSL) techniques for plant disease classification with limited datasets utilizing Siamese Neural Network (SNN). There are five different crop kinds in the dataset: grape, wheat, cotton, cucumber, and corn. Five sets of images showing both healthy and diseased crops are used to represent each of the new crops. The dataset's includes 25 classes with 875 leaf images. Data augmentation techniques are used to enhance the size and dimension of the plant leaf disease image dataset. To provide effective segmentation, this paper provides a unique method for region-based image segmentation that divides an image into its most prominent regions. It also addresses issues with earlier region-based segmentation methods. SVM-based classifiers have better generalization properties as their efficiency does not depend on the number of features. Such merit is beneficial in primary diagnostics decisions to check if the input image is included in the database or not to reduce the consumed time. OSL was applied and compared to standard fine-tuning transfer learning utilizing Siamese networks and triplet loss. Siamese provides superior classification accuracy and localization accuracy with minimal errors than other approaches. The proposed approach has a total processing time of 5 ms, which makes it appropriate for real-time applications. In terms of specificity, sensitivity, precision, accuracy, MCC, and F-measure, the proposed approach beats all current machine learning algorithms for small training sets.

An enhanced artificial bee colony algorithm using radial bases function neural networks for color image segmentation

The aim of segmentation process is to partition the image into homogeneous regions or objects. The proposed segmentation algorithms using adaptive feature weighting to distinguish the significance of various features. To extract effective feature extraction could be used for establishing regions in region based image segmentation. The main goal of this exploration work is to segment objects that separating the foreground and background of the color images. The segmentation for color images is focused on the Enhanced Artificial Bee Colony segmentation algorithm that utilizes the Radial Basis Function (EABCRBF) neural network algorithm. This work arranges RBF neural networks to predict the end limits of the segmentation, which are formed from the artificial bee colony province made in the image histogram topography. The radial basis function initial parameters, for instance, centers and widths are automatically set upon the histogram peaks and minima. The proposed EABCRBF strategy is compared with two existing techniques of Artificial Bee Colony (ABC) and Fuzzy C-Means (FCM). The EABCRBF method gives great outcomes for color image segmentation as it extracts additional information from color images. The experimentation results are shown through Mat Lab R2013a.

Automatic cardiac evaluations using a deep video object segmentation network

BackgroundAccurate cardiac volume and function assessment have valuable and significant diagnostic implications for patients suffering from ventricular dysfunction and cardiovascular disease. This study has focused on finding a reliable assistant to help physicians have more reliable and accurate cardiac measurements using a deep neural network. EchoRCNN is a semi-automated neural network for echocardiography sequence segmentation using a combination of mask region-based convolutional neural network image segmentation structure with reference-guided mask propagation video object segmentation network.ResultsThe proposed method accurately segments the left and right ventricle regions in four-chamber view echocardiography series with a dice similarity coefficient of 94.03% and 94.97%, respectively. Further post-processing procedures on the segmented left and right ventricle regions resulted in a mean absolute error of 3.13% and 2.03% for ejection fraction and fractional area change parameters, respectively.ConclusionThis study has achieved excellent performance on the left and right ventricle segmentation, leading to more accurate estimations of vital cardiac parameters such as ejection fraction and fractional area change parameters in the left and right ventricle functionalities, respectively. The results represent that our method can predict an assured, accurate, and reliable cardiac function diagnosis in clinical screenings.

A Study on Region-Based Image Segmentation Techniques

This paper addresses the comparison of two popular region-based image segmentation techniques namely the Watershed method and the Mean-shift method. The watershed method is a mathematical morphology based image segmentation approach while Mean-shift method is a data-clustering method that searches for the local maximal density points and then groups all the data to the clusters defined by these maximal density points. Here the efficiency of the both segmentation techniques is presented

Image Segmentation Based on Block Level and Hybrid Directional Local Extrema

In the recent decade, the digitalization of various tasks has added great flexibility to human lifestyle and has changed daily routine activities of communities. Image segmentation is a key step in digitalization. Segmentation plays a key role in almost all areas of image processing, and various approaches have been proposed for image segmentation. In this paper, a novel approach is proposed for image segmentation using a nonuniform adaptive strategy. Region-based image segmentation along with a directional binary pattern generated a better segmented image. An adaptive mask of 8 × 8 was circulated over the pixels whose bit value was 1 in the generated directional binary pattern. Segmentation was performed in three phases: first, an image was divided into sub-images or image chunks; next, the image patches were taken as input, and an adaptive threshold was generated; and finally the image chunks were processed separately by convolving the adaptive mask on the image chunks. Gradient and Laplacian of Gaussian algorithms along with directional extrema patterns provided a double check for boundary pixels. The proposed approach was tested on chunks of varying sizes, and after multiple iterations, it was found that a block size of 8 × 8 performs better than other chunks or block sizes. The accuracy of the segmentation technique was measured in terms of the count of ill regions, which were extracted after the segmentation process.

Risk Assessment of Coastal Flooding under Different Inundation Situations in Southwest of Taiwan (Tainan City)

The Pacific island countries are particularly vulnerable to the effects of global warming including more frequent and intense natural disasters. Seawater inundation, one of the most serious disasters, could damage human property and life. Regional sea level rise, highest astronomic tide, vertical land motions, and extreme sea level could result in episodic, recurrent, or permanent coastal inundation. Therefore, assessing potential flooding areas is a critical task for coastal management plans. In this study, a simulation of the static flooding situation in the southwest coast of Taiwan (Tainan city) at the end of this century was conducted by using a combination of the Taiwan Digital Elevation Model (DEM), regional sea level changes reconstructed by tide gauge and altimetry data, vertical land deformation derived from leveling and GPS data, and ocean tide models. In addition, the extreme sea level situation, which typically results from high water on a spring tide and a storm surge, was also evaluated by the joint probability method using tide gauge records. To analyze the possible static flood risk and avoid overestimation of inundation areas, a region-based image segmentation method was employed in the estimated future topographic data to generate the flood risk map. In addition, an extreme sea level situation, which typically results from high water on a spring tide and a storm surge, was also evaluated by the joint probability method using tide gauge records. Results showed that the range of inundation depth around the Tainan area is 0–8 m with a mean value of 4 m. In addition, most of the inundation areas are agricultural land use (60% of total inundation area of Tainan), and two important international wetlands, 88.5% of Zengwun Estuary Wetlands and 99.5% of Sihcao Wetlands (the important Black-faced Spoonbills Refuge) will disappear under the combined situation. The risk assessment of flooding areas is potentially useful for coastal ocean and land management to develop appropriate adaptation policies for preventing disasters resulting from global climate change.

A fast and fully distributed method for region-based image segmentation

Distributed and parallel computing techniques allow fast image processing, namely when these techniques are applied at the low and the medium level of a vision system. In this paper, a collective and distributed method for image segmentation is introduced and evaluated. The method is modeled as a multi-agent system, where the agents aim to collectively produce a region-based segmentation. Each agent starts searching for an acceptable region seed by randomly jumping within the image. Next, it performs a region growing around its position. Thus, several agents find themselves within the same homogeneous region and are organized in a graph where two agents are connected if they are within the same region. So, a unifying of the labels in a same region is collaboratively performed by the agents themselves. The proposed method was experimented on real range images from the ABW dataset and the Object Segmentation Database (OSD) one, and the obtained results were compared to those of some well-referenced methods from the literature. The evaluation results show that the proposed method provides fast and accurate image segmentation, allowing it to be deployed for real-time vision systems.

Bone Cancer Detection from X-Ray and MRI Images through Image Segmentation Techniques

This paper is based on integration of the biomedical field and computer science. Paper contains the study of bone cancer and features to predict the type of the same. Related work to find cancer in human body using computer vision is discussed in this paper. Image segmentation technique like sobel, prewitt, canny, K-means and Region Growing are described in this paper which can be stimulated for X-Ray and MRI image interpretation. Paper also shows the result of edge based and region based image segmentation techniques applied on X-Ray image to detect osteosarcoma cancer present on bone using MATLAB. Finally, paper concluded by finding best suited segmentation method for grey scaled image with future aspects.

Segmentation of Thermogram Based on Region Based Technique using Split and Merge Method

The main aim of segmentation is to identify the Region of Interest for image analysis. The segregation of an image into meaningful structures is often an important phase in image analysis, object representation, visualization and also in various other image processing tasks. Image segmentation is mostly useful in applications like detection where it is difficult to process whole image at a time. In this paper Region based image segmentation is used to identify the delaminations in Thermographic image of Infrared Non-Destructive Testing. There are two basic techniques in Region based segmentation viz. Region growing method, splitting and merging method. New method based Split and Merge segmentation technique is employed to identify the defective regions in thermogram. Results obtained after segmentation as compared with state of art segmentation methods.

Color-, depth-, and shape-based 3D fruit detection

A novel detection algorithm based on color, depth, and shape information is proposed for detecting spherical or cylindrical fruits on plants in natural environments and thus guiding harvesting robots to pick them automatically. A probabilistic image segmentation method is first presented to segment a red–green–blue image as a binary mask. Multiplied by this mask, a filtered depth image is obtained. Region growing, a region-based image segmentation method, is then applied to group the depth image into multiple clusters. Each cluster represents a fruit, leaf, or branch that is later transformed into a point cloud. Next, a 3D shape detection method based on M-estimator sample consensus, a model parameter estimator, is employed to detect potential fruits from each point cloud. Finally, an angle/color/shape-based global point cloud descriptor (GPCD) is developed to extract a feature vector for an entire point cloud, and a support vector machine classifier trained on the GPCD features is used to exclude false positives. Pepper, eggplant, and guava datasets were captured in the field. For the pepper, eggplant, and guava datasets, the detection precision was 0.864, 0.886, and 0.888, and the recall was 0.889, 0.762, and 0.812, respectively. Experiments revealed that the proposed algorithm was universal and robust and hence applicable to an agricultural harvesting robot.

Review on 2D and 3D MRI Image Segmentation Techniques

Magnetic Resonance Imaging is most widely used for early diagnosis of abnormalities in human organs. Due to the technical advancement in digital image processing, automatic computer aided medical image segmentation has been widely used in medical diagnostics. Image segmentation is an image processing technique which is used for extracting image features, searching and mining the medical image records for better and accurate medical diagnostics. Commonly used segmentation techniques are threshold based image segmentation, clustering based image segmentation, edge based image segmentation, region based image segmentation, atlas based image segmentation, and artificial neural network based image segmentation. This survey aims at providing an insight about different 2-Dimensional and 3- Dimensional MRI image segmentation techniques and to facilitate better understanding to the people who are new in this field. This comparative study summarizes the benefits and limitations of various segmentation techniques.

Median Filter For Transition Region Refinement In Image Segmentation

Transition region based image segmentation is one of the simple and effective image segmentation methods. This method is capable to segment image contains single or multiple objects. However, this method depends on the background. It may produce a bad segmentation result if the gray level variance is high or the background is textured. So a method to repair the transition region is needed. In this study, a new method to repair the transition region with median filter based on the percentage of the adjacent transitional pixels is proposed. Transition region is extracted from the grayscale image. Transition region refinement is conducted based on the percentage of the adjacent transitional pixels. Then, several morphological operations and the edge linking process are conducted to the transition region. Afterward, region filling is used to get the foreground area. Finally, image of segmentation result is obtained by showing the pixels of grayscale image that are located in the foreground area. The value of misclassification error (ME), false negative rate (FNR), and false positive rate (FPR) of the segmentation result are calculated to measure the proposed method performance. Performance of the proposed method is compared with the other method. The experimental results show that the proposed method has average value of ME, FPR, and FNR: 0.0297, 0.0209, and 0.0828 respectively. It defines that the proposed method has better performance than the other methods. Furthermore, the proposed method works well on the image with a variety of background, especially on image with textured background.

Image Segmentation by Using Threshold Techniques

Image segmentation (IS) is a procedure by which provided picture can be subdivided into many segments and to observe every segment included in the image. The desired result could be searched by observing them and that information we get is helpful for high standard machine vision software. The difficulties of IS has large problems for computer vision. Many procedures which came under IS are Edge based IS (EBIS), Region based IS (RBIS), Threshold based IS (TBIS). The result of observing image which is relying upon the reliability of IS, but exact division of a picture is most difficult issue. The technique we are using in this article is thresholding based segmentation (TBS). The studied article of IS by reader is beneficial for analyzing the suitable IS techniques and also for improvement of efficiency, performance and major goal, that helps in building latest algorithms.

Split and Merge: A Region Based Image Segmentation

Image segmentation is a very challenging task in digital image processing field. It is defined as the process of takeout objects from an image by dividing it into different regions where regions that depicts some information are called objects. There are different types of image segmentation algorithms. The segmentation process depends upon the type of description required for an application for which segmentation is to be performed. Hence, there is no universally accepted segmentation algorithm. Region segmentation is divided into three categories region growing, split and merge and watershed. But this study confines only to split and merge techniques. This paper includes split and merge approaches and their extended versions. This study highlights the main limitations and potentials of these approaches.

Region-based Segmentation of Social Images Using Soft KNN Algorithm

Social image data is very useful to solve many real world problems. In this paper, a novel soft classification approach is proposed to deal with the problem of vision segmentation in social networks. Proposed approach is inspired by the k-nearest neighbour and soft classification concepts. K-nearest neighbour is one of the popular and simplest classification algorithms. Soft classification has provision for assigning more than one class label to a single object. Here, soft classification concept is incorporated in k-nearest neighbour algorithm to detect the ambiguous regions of the image. Experimentation is carried out on the images collected from social networks. Three social image datasets i.e. synthetic, standard and real-world are used. Proposed approach performed much better as compared to the traditional k-nearest neighbour approach. It is useful for accomplishing various tasks like fashion analysis, emotion detection, event detection, etc. through object detection and recognition.

Extracting Maya Glyphs from Degraded Ancient Documents via Image Segmentation

We present a system for automatically extracting hieroglyph strokes from images of degraded ancient Maya codices. Our system adopts a region-based image segmentation framework. Multi-resolution super-pixels are first extracted to represent each image. A Support Vector Machine (SVM) classifier is used to label each super-pixel region with a probability to belong to foreground glyph strokes. Pixelwise probability maps from multiple super-pixel resolution scales are then aggregated to cope with various stroke widths and background noise. A fully connected Conditional Random Field model is then applied to improve the labeling consistency. Segmentation results show that our system preserves delicate local details of the historic Maya glyphs with various stroke widths and also reduces background noise. As an application, we conduct retrieval experiments using the extracted binary images. Experimental results show that our automatically extracted glyph strokes achieve comparable retrieval results to those obtained using glyphs manually segmented by epigraphers in our team.

Morphometry of organ cultured corneal endothelium using Voronoi segmentation

The endothelial viability of eye-banked corneas must be assessed before transplantation, yet phase-contrast images of the endothelium of corneas stored in an Organ Culture system have a huge variety of endothelial appearance at different focal planes, due to stromal swelling and an evaluation technique that swells the cells and their intercellular spaces to make them visible. This makes them difficult to assess using common edge-based segmentation methodologies that have mostly been developed in vivo using specular microscopy. Additionally, as the endothelial cell architecture has radically different form at apical and basal poles, segmentation of only the apical view cannot describe the cell as a whole. Using custom software, this study instead defines the cell borders using a calibrated Voronoi diagram, a region-based image segmentation technique that uses a point cloud of cell centroids as the only input required to measure the size (polymegathism) and shape (pleomorphism) of the endothelial cells. Measurements included the range and variation in the cell area and density, the number of cell sides, and several novel shape descriptors. A dataset of endothelial cell measurements was compiled from 2000 images of 678 corneas comprising 354,998 cells, and validated by comparison to previous studies from a variety of tissue sources, imaging modalities, and analysis techniques. While there were some differences in cell size variation and pleomorphic composition than seen in some other studies, much of the data was directly comparable, demonstrating fast and accurate endothelial cell morphometry at a large scale for a wide range of routine organ cultured corneas.

A Review on the Performance of Object Detection Algorithm

This paper represents multiple Object recognitions technology in the field of computer vision for finding and identifying multiple objects in a image or video sequence.It is basically highlight only those objects which are needed. Algorithmic descriptions of recognition task are implemented on machines which is an complex job. Thus multiple object recognition techniques need to be developed which are less intricate and well-organized The multiple object detection is a very important application of image processing. the literature survey has shown that the most of existing methods have ignored the poor quality images like image with noise or poor intensity . Noise means those signals which are not required .Also the most of the existing work for multiple object detection has neglected the use of hybrid technique. The overall goal of this research work is to propose an efficient and simple multiple object detection using the fuzzy and transition region based image segmentation

Image segmentation with dynamic artifacts detection and bias correction

Region-based image segmentation is well-addressed by the Chan-Vese (CV) model. However, this approach fails when images are affected by artifacts (outliers) and illumination bias that outweigh the actual image contrast. Here, we introduce a model for segmenting such images. In a single energy functional, we introduce 1) a dynamic artifact class preventing intensity outliers from skewing the segmentation, and 2), in Retinex-fashion, we decompose the image into a piecewise-constant structural part and a smooth bias part. The CV-segmentation terms then only act on the structure, and only in regions not identified as artifacts. The segmentation is parameterized using a phase-field, and efficiently minimized using threshold dynamics.We demonstrate the proposed model on a series of sample images from diverse modalities exhibiting artifacts and/or bias. Our algorithm typically converges within 10-50 iterations and takes fractions of a second on standard equipment to produce meaningful results. We expect our method to be useful for damaged images, and anticipate use in applications where artifacts and bias are actual features of interest, such as lesion detection and bias field correction in medical imaging, e.g., in magnetic resonance imaging (MRI).

Three-dimensional Image Segmentation using Tissue-like P System

Membrane computing (MC), which abstracts computational models from the structure and functioning of biological cells or population of cells in tissues, has served as a rich framework for handling many problems. Various types of P systems have been proposed in the literature to perform edge-based and region-based segmentation of two-dimensional digital images. However, less attention has been paid to the segmentation of three-dimensional (3D) medical images. Hence, the main contribution of this paper is to propose a tissue-like P system for segmenting 3D medical images. To the best of our knowledge, this is the first work that practically adapts MC for 3D images. Experimental results demonstrate the efficiency of the proposed approach in segmenting 3D images, and it has the potential to be used in real-world applications.