Error Threshold Method Research Articles

A Method of Chest Film Segmentation Based on Minimum Error Threshold Method

In recent years, due to irregular life schedule and environmental pollution, the incidence rate and mortality of lung cancer have greatly increased. However, early detection and treatment can significantly reduce mortality. In the diagnosis of lung cancer, X-ray plays a key role. With the wide application of artificial intelligence, intelligent analysis of medical images has also ushered in a new breakthrough. In the intelligent analysis of medical images, image segmentation is an extremely critical link. This paper mainly introduces an image segmentation method about minimum error threshold segmentation, which provides an efficient and convenient method for medical image segmentation. This method can effectively extract the target lung region, avoid obvious over-segmentation and interference of stomach air region, and eliminate cavities and noise points, to obtain more accurate lung segmentation effect. Various reasons have led to the rapid rise of the incidence rate and mortality of lung cancer. Lung cancer will become one of the most threatening diseases to mankind in the 21st century. People should pay more attention to lung cancer related issues, realizing the advantages of intelligent analysis of medical images, and pay more attention to this field.

A Novel Image Thresholding Method Combining Entropy With Parzen Window Estimation

Abstract Image thresholding is an important and efficient image segmentation technique, which is crucial and essential for image analysis and computer vision. In this paper, we proposed a new image thresholding method based on entropy and parzen window (PW) estimation. First, the probability of each gray-level distribution is approximate by using the PW estimation. Second, by combining the obtained probability information with entropic information of the foreground and background, a new objective function is created. At last, the ideal threshold value is obtained by optimizing the objective function. By comparing with some classical thresholding methods, such as inter class variance method (OTSU), minimum error thresholding method (MET), Kapur’s entropy based method (KAPUR) and the recent methods that take spatial information into consideration (2D-D histogram method, GLLV histogram method and Gabor histogram method), the proposed method, experiment on 10 images (one synthetic image, four nondestructive testing images and five real-world images), presents a better performance on the accuracy, robustness and visual effect of segmentation.

An analytical proof on suitability of Cauchy-Schwarz Divergence as the aggregation criterion in Region Growing Algorithm

Region Growing Algorithm (RGA) is a popular, fast and strongly formed object segmentation method. In RGA, the region is grown from the seed points to adjacent points depending on an aggregation criterion. Despite the huge literature on RGA, none of the proposed aggregation criteria have been analytically proved to be suitable for an ideal segmentation. In this paper, Cauchy-Schwarz Divergence (CSD) is proved to be suitable as an aggregation criterion in RGA for object segmentation. First, RGA is formulated in this context. The Cauchy-Schwarz-based criterion is proposed here in the continuous case for a bimodal image that contains one object in the background while both regions are normally distributed with different parameters (while the assumption of normal distribution of object and background has been used by many researchers in minimum error thresholding method). Then, a proof is given that in the mentioned formulated case, the proposed RGA will lead to an ideal segmentation. The case is also investigated while object and background have heavy-tail distributions like generalized Gaussian function when β < 2. While all formulations and proofs are given in the continuous case, the segmentation results in the discrete case are shown to be good. Comparison of these results with the outcomes of RGA with traditional aggregation criteria, shows how analytical justifications can suggest a better criterion.

Research on Image Segmentation Algorithm Based on Component Tree

The key part of sea target recognition is to search for the possible ship targets in the image. For the problem that the standard segmentation of threshold algorithm is not effective in the complex sea condition, in this paper, a component tree image segmentation method based on minimum error threshold and ship area is proposed for ship target recognition. Firstly, area criterion is used to filter the image, then minimum error threshold method is used to construct the component tree and determine the filtering mechanism, finally, gray level criterion is used to filter the component tree. The simulation results show that proposed method is effective.

Sistem Monitoring Kolesterol Melalui Iris Mata dengan Metode Pengolahan Citra

Early detection to determine the presence or absence of cholesterol in the body is a necessity for everyone who wants to live healthy. Many diseases can be caused by the presence of cholesterol such as heart disease, stroke, nerve disorders, kidney problems, hypertension, and etc. Therefore, cholesterol detection must be done regularly. This study discusses about the cholesterol detection system through the iris eyes using image processing and monitoring progress in continously. Detection of cholesterol can be observed with Arcus Senilis or a gray ring in the iris eyes. Tests carried using 15 samples which cholesterol identifed. The process of image processing consists of image acquisition, sharpening, segmentation, convert grayscale and binary images. Cholesterol can be identify with difference between pixel values 0 (black) and pixel values 1 (white) in binary images. Research data will be stored in an Excel format database with adding some user data. From the test, results analysis carried the try and error threshold method using values of 80, 100, 150, and getting an accuracy of 87%, 73%, and 33%. Besides, monitoring cholesterol can be carried using a system interface and database with adding the required data and can display it on excel.

A Survey on Global Thresholding Methods for Mapping Open Water Body Using Sentinel-2 Satellite Imagery and Normalized Difference Water Index

The aim of this study is to investigate the performance of fifteen automatic thresholding methods, namely Huang and Wang’s fuzzy thresholding method, inter-mode thresholding method, isodata thresholding method, Li and Tam’s thresholding method, maximum entropy thresholding method, mean thresholding method, minimum error thresholding method, minimum thresholding method, moment-preserving thresholding method, Otsu’s thresholding method, percentile (p-tile) thresholding method, Renyi’s entropy thresholding method, Shanbhag’s thresholding method, triangle thresholding method and Yen’s thresholding method, for mapping open water body using Sentinel-2 data based on Normalized Difference Water Index (NDWI). Sentinel-2 data was acquired on 22 September 2018 and Lake Salda from Turkey was selected as a test site. Due to the lack of digital reference data of the test site, Support Vector Machine (SVM) classification was implemented to Sentinel-2 data and the classified image was utilized as reference data since previous studies proved that SVM classification provided better results than the thresholding methods. SVM classification results were evaluated using 1000 random points and the Overall Accuracy (OA) and Kappa coefficient were obtained 96.2% and 0.90, respectively. The thresholding methods were assessed using the statistical measures, namely OA, Kappa and Misclassification Error (ME). Considering the remote sensing perspective, all thresholding methods presented satisfying results having at least 92% OA for open water body extraction. The obtained accuracy results showed that minimum thresholding method was the best method among these fifteen algorithms with 0.000264 ME, 99.9355% OA and 0.9987 Kappa. On the other hand, p-tile and Shanbhag’s thresholding method provided the worst accuracy results for open water body delineation.

Potential of global thresholding methods for the identification of surface water resources using Sentinel-2 satellite imagery and normalized difference water index

The aim of this study is to investigate the performance of 15 automatic thresholding methods, namely Huang and Wang’s fuzzy thresholding method, intermode thresholding method, isodata thresholding method, Li and Tam’s thresholding method, maximum entropy thresholding method, mean thresholding method, minimum error thresholding method, minimum thresholding method, moment-preserving thresholding method, Otsu’s thresholding method, percentile (p-tile) thresholding method, Renyi’s entropy thresholding method, Shanbhag’s thresholding method, triangle thresholding method, and Yen’s thresholding method, for mapping water body using Sentinel-2 data based on normalized difference water index. Three different types of surface water bodies, such as a natural lake (Lake Burdur), a dam reservoir (Aslantaş Dam Reservoir), and a part of a river (Aras River), are chosen to reveal the potential of 15 thresholding methods. The reference water body maps of each test site were generated by manual digitization of high-resolution Google Earth images. The thresholding methods were assessed using the statistical measures, namely overall accuracy (OA), Kappa coefficient, producer’s accuracy, user’s accuracy, and misclassification error (ME). The accuracy analyses of 15 thresholding methods were carried out separately for each test site, and then the overall accuracies were calculated to determine the best method. The obtained OA results showed that minimum thresholding method was the best method among these 15 algorithms with 0.0008 ME, 99.92% OA, and 0.9758 Kappa coefficient. On the other hand, Shanbhag’s method provided the lowest overall accuracies as 0.3133 ME, 68.67% OA, and 0.3190 Kappa coefficient.

The Agriculture Vision Image Segmentation Algorithm Based on Improved Quantum-Behaved Particle Swarm Optimization

Image segmentation and feature extraction are the premise for machine vision system to analyze and identify the image. Threshold image segmentation algorithm according to the method of two dimension threshold has a lot of calculation in calculating the threshold, and the minimum error threshold method can not use the spatial information of image. This paper presents an improved quantum-behaved particle swarm optimization based on the night segmentation and feature extraction technology. This paper introduces the QPSO algorithm based on multi group and multi stage improvement. The QPSO optimizing algorithm gradually approaches the global optimum threshold value to achieve better convergence and stability. An algorithm of vision image segmentation and feature extraction based on improved quantum-behaved particle swarm optimization is designed. Experimental results show that the optimization process of this algorithm has less control parameters and faster convergence speed.

Paper Currency CIS Image Fuzzy Enhancement and Boundary Detection

According to the features of paper currency CIS image, the fuzzy set theory is initial used to improve the contrast of banknote target and background, paper money’s edge pixels are obtained by scanning, and then the sub-pixel edges are fitted by least square method; in the fitting process, the error threshold method is applied for eliminating noisy edge points, then slope correction of paper money is carried out according to the angle of sub-pixel edge line and the note area is extracted, finally, fuzzy enhancement is used for the extracted image again. Experiments show that, this method has good versatility, high accuracy and strong anti-interference ability, it can even extract the paper currency area effectively in the edge deterioration and unfilled corner condition, and the enhanced image is in favor of subsequent paper currency recognition.

Collaborative image compression with error bounds in wireless sensor networks for crop monitoring

Using the correlation characteristic between the reference image may reduce transmission energy in wireless sensor networks. However, as crop images are usually captured periodically and the images are easily influenced by the peripheral environment during capture, transmitting the subtraction information of crop images may consume large amounts of energy. Moreover, sensor nodes should provide sufficiently accurate images for evaluating crop status according to the crop conditions. A compression scheme should be designed to compress the subtraction information and to ensure reconstruction image quality. In this paper, based on the properties of non-standard Haar transformation, we apply non-standard Haar transformation to decompose the subtraction crop images, and we use the error threshold method to compress crop images and to ensure image quality. Experimental results show that our scheme has a higher compression ratio and higher computing efficiency than the Haar wavelets method and the JPEG method.

Adaptive Minimum Error Thresholding Algorithm

A robust minimum error thresholding method is proposed to combine the three-dimensional (3D) minimum error thresholding scheme based on 2D method with the principle of rebuilding and dimension reduction of the 3D histogram. Considering the global behavior of this approach and its ability to process even illumination images only, a water flow model is used to estimate the background of uneven illumination images for improving adaptability of the proposed method. Then, the difference image between the original image and background can be readily obtained to reduce the interference of uneven illumination during the binarization process. To improve execution performance of the segmentation procedure, gamma correction is employed to enhance image in addition to a global segmentation using robust minimum error thresholding algorithm. Subsequently, image segmentation tests are carried out with even and uneven illumination, and then comparison on misclassification error and time expenditure are performed between the proposed method and other approaches, i.e., 1D/2D minimum error thresholding, Otsu thresholding algorithm based on 3D histogram rebuilding and dimensionality reduction, adaptive gray wave transformation thresholding scheme, as well as a modified FCM method. The results show that the proposed approach yields better thresholding performance than those methods.

ABNORMALITY DETECTION IN BRAIN MR IMAGES USING MINIMUM ERROR THRESHOLDING METHOD

Medical image segmentation plays an instrumental role in clinical diagnosis. An ideal medical image segmentation scheme should possess some preferred properties such as minimum user interaction, fast computation, and accurate and robust segmentation results. In this paper, an automated algorithm is proposed to enable the doctors to detect the presence of abnormal tissues in brain magnetic resonance images (MRIs). The merged image of different weighted images of each slice is obtained by averaging the intensities of pixels and is enhanced based on their local information by variance mapping. The abnormal regions are segmented by using minimum error thresholding method by formulating a criterion function. The segmentation is performed on the real data of MRI images for different abnormalities and the results are compared with radiologist labeled ground truth. Quantitative analysis between ground truth and segmented abnormal region is presented in terms of Percent Match and Correspondence Ratio. A maximum average percent match of 98.56% and correspondence ratio of 0.8892 of an MRI data is obtained.

On Threshold Selection Using Fuzzy Risk Criterion

A parametric and unsupervised method of automatic threshold selection for image segmentation is presented. An optimal threshold is selected by the fuzzy risk criterion, namely, so as to separate a given picture into meaningful gray level classes under the assumption of object and pixel gray level values being normally distributed. The effectiveness of the proposed approach is illustrated using some experimental images with 256 gray-levels, and the results are compared with minimum error thresholding method using the criterion functions such as uniformity, shape, and edge measures.

Improvement of kittler and illingworth's minimum error thresholding

A simple modification to Kittler and Illingworth's minimum error thresholding method was made and the performance of the modified version was compared with that of the original version empirically. By correcting the biased estimates of variances of model distributions, a significant improvement in performance was found. The improvement was most outstanding among not-well-separated, but still bimodal histograms. In fact, the modification provides a more robust method. The new version is nearly computationally equivalent in complexity to the original version.