Image Thresholding Research Papers - Academia.edu (original) (raw)

2025, Yosar Leman

Pengenalan golongan darah penting dalam medis, terutama untuk transfusi. Metode konvensional berbasis aglutinasi memiliki keterbatasan. Penelitian ini merancang sistem otomatis menggunakan Hidden Markov Model (HMM) untuk mengklasifikasikan golongan darah ABO. Tahapannya meliputi pengumpulan citra darah, pra-pemrosesan, ekstraksi fitur (GLCM dan histogram), serta pemodelan HMM. Evaluasi menggunakan akurasi, presisi, recall, F1-score, dan kecepatan. Tujuannya adalah menciptakan sistem cepat, akurat, dan andal untuk identifikasi golongan darah.

2025, IEEE

In this paper, we present an effective multilevel threshold selection method of color image segmentation based on minimum class variance thresholding (MCVT) and OTSU method. The input RGB color image is segmented into regions and proceeds to the region merge using JND (Just Noticeable Difference) of human visual property. The result shows that with simple yet very effective JND merge criteria, the proposed algorithm is capable of generating region representations. After analyzing these two results, Otsu method is better than MCVT method.

2025, Engineering and Technology Journal

Image preprocessing has assumed an essential part of handwriting recognition system. The main primary stage of the image preprocessing is thresholding. An effective thresholding method is based on Fuzzy C-Means clustering (FCM) for Arabic Handwriting Recognition system (AHR) has been proposed in this paper. Since thresholding stage in AHR is imperative to reduce the dimensionality of image to remove the undesirable information (noise) then increase the processing speed of the AHR system. The algorithm is performing by feeding the intensity of the pixel value of the image pixels into the FCM clustering algorithm. Exploratory results with artificial and real life images show that the proposed method gives better accuracy and good efficiency than the current methods.

2025, Indonesian Journal of Electrical Engineering and Computer Science

Thresholding is a type of image segmentation, where the pixels change to make the image easier to analyze. In bi-level thresholding, the image in grayscale format is transformed into a binary format. The traditional methods for image thresholding may be inefficient in finding the best threshold and take longer computation time. Recently, metaheuristic swarm-based algorithms were applied for optimization in different applications to find optimal solutions with minimum computational time. The proposed work aims to optimize the fitness function obtained by the Otsu algorithm using a metaheuristic swarm-based algorithm called the bat algorithm. As a result, the optimal threshold value for bi-level images in cloud detection was obtained. Also, one of the trajectory-based algorithms called hill climbing was applied to optimize the fitness function taken from the Otsu algorithm. The HYTA dataset was used to evaluate the work, which was later confirmed through testing. The findings of exper...

2025

The standard examination blood type was performed using a reagent that actually less economical. This research in order to determine whether serum blood type can be used as a reagent blood type. It has been already conducted research antibodies in the serum of blood type A, B, and AB. Each serum would reacted with antigent in the blood, indicated by the agglutination. The research method was experimental by performing blood type with drops of serum in the blood type A, B and AB then saw the grade agglutination. The data obtained were processed statistically using Kruskal Wallis. The result showed serum A, B, and O can be used as a substitute reagents alternative anti -A, anti -B, and anti -AB in determining blood type. Based on analysis, quality clotting produced by serum aglutination is not same with the reagent anti -A, anti -B, and anti -AB in determining blood type.

2024, The Proceedings of the 4th International Conference on Industrial Application Engineering 2016

Fingerprint segmentation is a preprocessing stage in the fingerprint recognition system. It is used to prevent the extraction of false features in the background or the low quality parts in the foreground (fingerprint area). Besides, it reduces the execution time of the recognition by considering only the region of interest. It is often preferred using simplified segmentation techniques to build the recognition systems. The most popular one is the variance based thresholding. This method has been developed in this paper through making it more robust while maintain the simplicity of design. It is proven to act more reliable in case of bad images.

2024, Iranian Journal of Fuzzy Systems

In this research paper, we use a normalized graph cut measure as a thresholding principle to separate an object from the background based on the standard S membership function. The implementation of the proposed algorithm known as fuzzy normalized graph cut method. This proposed algorithm compared with the fuzzy entropy method [25], Kittler [11], Rosin [21], Sauvola [23] and Wolf [33] method. Moreover, we examine that in most cases, our algorithm gives the lowest absolute error that improves the segmentation process of gray images. Finally, we change different parameter values in fuzzy normalized graph cut and the effect of the substitutes is studied. Also, we analyze the computational complexity of fuzzy weight matrix (fuzzification) results with a weight matrix (classical) results.

2024, Journal of Electronic Imaging

Abstract. The study of image segmentation is a crucial impression in image processing and computer vision appliances, which segments an input image into distinct non-overlapping homogenous divisions and helps to depict the image more conveniently. To improve the performance of the segmentation of gray-level images by introducing a normalized graph cut
measure as a thresholding principle to separate an object from the
background based on the neutrosophic membership function. We proposed an innovative neutrosophic approach combining a set of features of some efficient algorithms. The implementation of the proposed algorithm is known as the neutrosophic normalized graph cut (NNGC) method. In the gray image segmentation, the problem of wrongly segmentation and segmentation with low accuracy can identify
by using this approach. This proposed algorithm is compared with the fuzzy entropy method, neutrosophic graph cut (NGC), classical graphcut, Otsu, and Kittler method. Moreover, we examine that in most cases, our algorithm gives the lowest absolute error, misclassification error,
and higher values of signal to noise ratio values that improve the segmentation process of gray images. Finally, we analyze the change of different parameter values in the NNGC and the effect of the substitutes. Also, we discuss the computational complexity of neutrosophic weight matrix results with a weight matrix (classical) results.

2024, Iranian Journal of Fuzzy Systems

In this research paper, we use a normalized graph cut measure as a thresholding principle to separate an object from the background based on the standard S membership function. The implementation of the proposed algorithm known as fuzzy normalized graph cut method. This proposed algorithm compared with the fuzzy entropy method [25], Kittler
[11], Rosin [21], Sauvola [23] and Wolf [33] method. Moreover, we examine that in most cases, our algorithm gives the lowest absolute error that improves the segmentation process of gray images. Finally, we change different parameter values in fuzzy normalized graph cut and the effect of the substitutes is studied. Also, we analyze the computational
complexity of fuzzy weight matrix (fuzzification) results with a weight matrix (classical) results.

2024, Indonesian Journal of Electrical Engineering and Computer Science

2024, 4th IIAE International Conference on Industrial Application Engineering 2016

2024, International Journal of Electrical and Computer Engineering (IJECE)

Lung cancer is the leading cause of cancer death among people worldwide. The primary aim of this research is to establish an image processing method for lung cancer detection. This paper focuses on lung region segmentation from computed tomography (CT) scan images. In this work, a new procedure for lung region segmentation is proposed. First, the lung CT scan images will undergo an image thresholding stage before going through two morphological reconstruction and masking stages. In between morphological and masking stages, object extraction, border change, and object elimination will occur. Finally, the lung field will be annotated. The outcomes of the proposed procedure and previous lung segmentation methods i.e., the modified watershed segmentation method is compared with the ground truth images for performance evaluation that will be carried out both in qualitative and quantitative manners. Based on the analyses, the new proposed procedure for lung segmentation, denotes better pe...

2024, International Journal of Electrical and Computer Engineering (IJECE)

The classification of student performance involves categorizing students' performance using input data such as demographic information and examination results. However, our study introduces a novel approach by emphasizing students' online learning activities as a rich data source. To avoid misinterpretation during the classification, we therefore presented a study comparing several feature selection (FS) methods combined with artificial neural network (ANN), for classifying students' performance based on their online learning activities. At first, we focused on tackling the issue of missing values by implementing data cleaning using variance threshold. feature selection techniques were implemented which encompass both filterbased (information gain, chi-square, Pearson correlation) and wrapper-based, sequential selection (forward and backward) techniques. In the classification stage, multi-layer perceptron (MLP) was used with the default hyperparameters and 5-fold cross-validation along with synthetic minority oversampling technique (SMOTE) were also applied to each method. We evaluated each feature selection method's performance using key metrics: accuracy, precision, recall, and F1-score. The outcomes highlighted information gain and sequential selection (forward and backward) as the topperforming methods, all achieving 100% accuracy. This research underscores the potential of leveraging online learning activities for robust student performance classification within the specified constraints.

2024, International Journal of Electrical and Computer Engineering (IJECE)

The widespread of coronavirus disease 2019 (COVID-19) pandemic led to a discovery that open distance learning (ODL) has turned out to be the only choice for teaching and learning by most institution (s) of higher learning (IHLs). In Malaysia, ODL is considered a new approach as physical laboratory practice has always been conducted for laboratory courses. This is a quantitative study which explores the perceptions of e-Lab among the students of bachelor’s in electrical and electronic engineering (EE) by focusing on the effectiveness and readiness in conducting the e-Lab. Simulation-based model is proposed for conducting the e-Lab using an interactive media and validated with the final score performance. With the future goals of improving the e-Lab in terms of delivering methods and engaging mediums between students and laboratory instructor, this study also discovered the levels of response from students’ perception to substitute the conventional laboratory by providing an equivalen...

2024, Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics Service

2024, Brazilian Symposium of Computer Graphic and Image Processing

The digital image segmentation challenge has demanded the development of a plethora of methods and approaches. A quite simple approach, the thresholding, has still been intensively applied mainly for real-time vision applications. However, the threshold criteria often depend on entropic or statistical image features. This work searches a relationship between these features and subjective human threshold decisions. Then, an image thresholding model based on these subjective decisions and global statistical features was developed by training a Radial Basis Functions Network (RBFN). This work also compares the automatic thresholding methods to the human responses. Furthermore, the RBFN-modeled answers were compared to the automatic thresholding. The results show that entropic-based method was closer to RBFNmodeled thresholding than variance-based method. It was also found that another automatic method which combines global and local criteria presented higher correlation with human responses.

2024

Image thresholding is one of the most widely used segmentation techniques in image processing. The objective of image thresholding is to segment a given image so that the object is more distinguishable from its background. This has been an active area of research in image processing and several methods have been proposed. Some of them are based on entropy of the image and its histogram. In this paper we provide a brief survey of entropy based thresholding techniques which include method based on entropy of histogram, thresholding using Renyi entropy and thresholding using Tsallis entropy.

2024, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi

Cizelgeleme, belirli zaman araliklarinda kaynak kisitlari dikkate alinarak kabul edilir bir sekilde atama yapma islemidir. Egitim kurumlari icin ders programi hazirlama islemi cizelgeleme cesitlerinden biridir. Amac, belirlenen kisitlar cercevesinde donem derslerinin zaman cizelgesine yerlestirilmesidir. Egitim kurumlarinda ders programi genellikle idareciler tarafindan elle hazirlanmaktadir. Bu calismasinda, elle hazirlamayi gerektirmeyen, ders programini otomatik olarak hazirlayan bir program gelistirilmistir. Programda Suleyman Demirel Universitesi Gelendost Meslek Yuksekokulu donem dersleri ve ders gorevlendirmeleri kullanilmistir. Daha onceki calismalar incelenerek ve Gelendost Meslek Yuksekokulu'nun ihtiyaclari dikkate alinarak problemin kisitlari belirlenmistir. Problemin cozumune yonelik C# programlama dilinde, Yapay Ari Kolonisi algoritmasi kullanilarak, kullanici etkilesimli arayuze sahip bir program gelistirilmistir. Calismalar sonucunda kullanilan algoritma ile uygun...

2024, Civil Engineering and Architecture

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.

2024, DergiPark (Istanbul University)

Özet-Bu çalışmada renkli görüntülerin üç boyutlu histogram yardımıyla otomatik olarak sınıflandırılması için geliştirilen yeni bir algoritma sunulmuştur. Önerilen yöntemde, öncelikle sayısal görüntünün üç boyutlu histogramı elde edilmiştir. Akabinde istenilen küme sayısı kadar histogramın tepe noktası tespit edilerek küme merkezleri olarak atanmıştır. Renk uzayında herhangi bir konuma karşılık gelen piksellerin, küme merkezlerine olan uzaklıkları ve benzerlikleri hesaplanmıştır. Her hangi bir pikselin hangi küme ya da sınıfa ait olduğu benzerlik değerlerinin eşiklenmesi ile kararlaştırılmıştır. Yöntemin performansı yapılan deneylerle test edilmiş ve elde edilen sonuçlar verilmiştir. Anahtar Kelimeler-Görüntü ayrıştırma, üç boyutlu histogram, piksel benzerliği.

2024

Sentiment analysis or opinion mining is one of the major tasks of NLP (Natural Language Processing). It captures the user’s opinion, feelings, and belief regarding the respective product especially to determine whether the user’s attitude is positive, negative, or neutral. This analysis greatly helps the companies to make necessary changes in their product which in return can overcome the flaws that the product is facing and targets better customer satisfaction. Existing techniques for the sentiment analysis of online product reviews obtained low accuracy and also took more time for training. To overcome such issues in this paper, a DLMNN is proposed for sentiment analysis of online product review and IANFIS is proposed for future prediction of online product. Here, the sentiment analysis and future predictions are done on the products taken from the food review dataset. First, from the dataset, the data values are partitioned into GB, CB, and CLB scenarios and then the review analy...

2024

The paper presents real time speckle de-noising based on activity computation algorithm and wavelet transform. Speckles arise in an image when laser light is reflected from an illuminated surface. The process involves detection of speckles in an image by obtaining a number of frames of the same object under different illumination or angle and comparing the frames for the granular computation and de-noising the same on presence of greater activity index. The project can be implemented in FPGA (Field Programmable Gate Array) technology. The results can be shown that the used activity computation algorithm and wavelet transform has better accuracy in the process of speckle detection and de-noising.

2023, International Symposium Innovative Technologies Engineering and Science

Bu çalışma da, en iyi ajan operatörlü yerçekimi arama algoritmasını kullanarak (EİAYAA) gri görüntülerde çoklu eşik yöntemi ile bölütleme gerçekleştirilmiştir. EİAYAA hassas arama kabiliyetini artırmak için en iyi ajan operatörü kullanılmıştır. Bölütleme görüntü işleme alanında en temel işlemlerden biri olup, görüntü piksel yoğunluklarının önceden belirlenmiş sınıflara ayrılmasıdır. Bölütleme metotlarından en kolay uygulanabilir olanlarından biri olan eşikleme, gri tonlu görüntü piksellerinin yoğunluk seviyelerine bağlı olarak kümelere veya sınıflara bölünme sürecidir. Bu sınıflandırmanın yapılabilmesi için th eşik değerinin seçilmesi gerekir. En uygun eşik değer seçimi için amaç fonksiyonu olarak Kapur'un metodu kullanılmıştır. Optimizasyon safhasından sonra, en iyi eşik değerler çoklu eşik bölütleme metoduna uygulanarak sınıflara ayrılmış görüntü elde edilmiştir. Elde edilen deneysel sonuçlar, bilinen yöntemler ile karşılaştırılmış ve sonuçlar önerilen algoritmanın sayısal görüntü bölütleme de güçlü olduğunu göstermiştir.

2023

Bu çalışmada, komşu pikseller arasındaki benzeşim özelliği kullanılarak, bölgelere ayrıştırma işlemi gerçekleştirilmiştir. Bölgelere ayırma işlemi gerçek görüntü üzerinde değil de, elde edilen benzeşim görüntüsü üzerinde bölge büyüme algoritması kullanılarak yapılmıştır. Benzeşim görüntüsünde fark alma, benzeşim bulma fonksiyonları ve bağıntı matrisi kavramları açıklanmış, benzeşim bulma fonksiyonlarının etkisi nedir ve normalleştirilmiş katsayı ve eşik değerler ayrıştırmayı nasıl etkiliyor gibi sorular yanıtlanmaya çalışılmıştır.

2023, Indonesian Journal of Electrical Engineering and Computer Science

This study presents characterization of cracking in pavement distress using image processing techniques and k-nearest neighbour (kNN) classifier. The proposed semi-automated detection system for characterization on pavement distress anticipated to minimize the human supervision from traditional surveys and reduces cost of maintenance of pavement distress. The system consists of 4 stages which are image acquisition, image processing, feature extraction and classification. Firstly, a tool for image acquisition, consisting of digital camera, camera holder and tripod, is developed to capture images of pavement distress. Secondly, image processing techniques such as image thresholding, median filter, image erosion and image filling are applied. Thirdly, two features that represent the length of pavement cracking in x and y coordinate system namely delta_x and delta_y are computed. Finally, the computed features is fed to a kNN classifier to build its committee and further used to classif...

2023, Pattern Recognition

In this paper, we propose a multi-level thresholding model based on graylevel & local-average histogram (GLLA) and Tsallis-Havrda-Charvát entropy for RGB color image. We validate the multi-level thresholding formulation by using the mathematical induction method. We apply particle swarm optimization (PSO) algorithm to obtain the optimal threshold values for each component of a RGB image. By assigning the mean values from each thresholded class, we obtain three segmented component images independently. We conduct the experiments extensively on The Berkeley Segmentation Dataset and Benchmark (BSDS300) and calculate the average four performance indices (BDE, P RI, GCE and V OI) to show the effectiveness and reasonability of the proposed method.

2023, International journal of artificial intelligence

A human face detection method for color images is presented in this paper, which is pose, size and position independent, and has the priority of classifying detected faces in three groups: frontal, near frontal and profile, according to their pose. This system is a fuzzy rule base one, optimized by genetic algorithm. In the first stage, skin color regions are selected in the input image. Within each skin area, lip pixels and ear texture are searched, and applied as features to identify face candidates in the skin regions. Summarizing all obtained information along by skin region shape and lip area position relative to skin area, four inputs are computed for fuzzy inference system, and face areas as well as their poses would be introduced. The proposed method is tried on various databases, including HHI, Champion, Caltech, Bao and IMM databases. Achieved results show a remarkable detection rates compared to other methods, for various face poses. 96.8%, 95.3% and 87.8% correct detecti...

2023, Deu Muhendislik Fakultesi Fen ve Muhendislik

Özet: Görüntü işleme teknikleri klinik karar destek sistemlerinde (KKDS) sıklıkla kullanılmaktadır. Bu çalışmada çağın önemli bir hastalığı olan beyin tümörlerinin görüntü işleme teknikleri ile tespit edilebilmesi amaçlanmıştır. Manyetik Rezonans görüntülerinden (MRI) yararlanarak beyin tümörünün görüntü segmentasyonu ile tespit edilmesine yönelik bir çalışma gerçekleştirilmiştir. Devlet hastanelerinden MR görüntüleri resmi izinlerle alınmış ve çalışmada kullanılmıştır. Markov Random Field (MRF), Kapur, Kittler ve Otsu algoritmaları ile MR görüntülerindeki tümörlü bölgeler tespit edilmeye çalışılmıştır. Algoritmalar, MR görüntülerinin daha önceden belirlenmiş bölgelerine (ROI-Region of Interest) ayrı ayrı uygulanmıştır. Yapılan deneysel uygulamada Markov Random Field (MRF) algoritmasının beyin tümörü tespitinde diğer algoritmalara oranla daha başarılı sonuçlar verdiği gözlemlenmiştir.

2023, TEKNIMEDIA: Teknologi Informasi dan Multimedia

Based on police data quoted from one of the online news portal pages, there are 43,842 thousand criminal acts in the The Capital City of Jakarta. Of all these criminal cases burglary empty houses included in the top three acts of crime. Houses that are abandoned by their owners are often targeted by crime operations due to lack of close supervision and security support technology. The purpose of this study is to detect human motion which can later be used to prevent crime in the form of theft. Another purpose of this research is to find out how the method used works in identifying changes in the image of several consecutive frames. This research develops a motion detection system in humans on video using a Closed Circuit Television (CCTV) camera which is simulated using sample video. The motion detection process uses the Accumulative Differences Image (ADI) method and the human detection process uses the classification of Opencv, the Haar Cascade Classification. Which with this meth...

2023

1M.E. Student, Electronics & Communication Department, Dr. S. & S. S. Ghandhy Government Engineering College, Surat, Gujarat, India. 2,3,4Assistant Professor, Electronics & Communication Department, Sarvajanik College of Engineering & Technology, Surat, Gujarat, India. ---------------------------------------------------------------------***---------------------------------------------------------------------Abstract Image segmentation is to find the desired object presented in the image. Gray Level Local Variance (GLLV), Gray Level Local Entropy (GLLE), Gray Level Spatial Correlation (GLSC) are different 2D histogram methods used to do the segmentation using Tsallis Entropy. In this paper, visible images of Plasma of TOKAMAK are used to extract the desired bright spots from images using different 2D histogram Segmentation Methods, which can further be used to find the position of the plasma. Due to unavailability of ground truth image, unsupervised parameter Uniformity Value is used...

2023, EDUSAINTEK: Jurnal Pendidikan, Sains dan Teknologi

In this study a device was designed to detect human blood group using the ABO method which is integrated with a blood oxygen saturation meter. This tool can detect agglutination or non-agglutination reactions in blood samples that have been treated with antisera and will then be read by three TCRT5000 sensors which are reflective sensors used as detectors of A, B and Rhesus antigens when agglutination and non-agglutination reactions occur on paper. blood sample test. In addition, the MAX30100 sensor is also used to measure blood oxygen saturation in the human body. Data that has been read by the sensor will be directly processed by Arduino Uno and the results from reading by the sensor will be displayed on the 16x2 LCD. In testing the human blood group detector designed where the results of all tests on the respondent's blood samples totaling 8 blood samples obtained a success value of 100%. In addition, the results of testing the Oxygen Saturation Measuring Instrument using the...

2023, International Journal of Hybrid Information Technology

Multilevel thresholding is one of the most important techniques for image processing and pattern recognition. The maximum entropy thresholding (MET) has been widely applied in multilevel thresholding. In this paper, a novel multilevel MET algorithm based on the hybrid of particle swarm optimization (PSO) and Genetic algorithm is presented. In standard PSO the non-oscillatory route can quickly cause a particle to stagnate and also it may prematurely converge on suboptimal solutions that are not even guaranteed local optimal solution. To overcome this problem, we used Genetic algorithm. To obtain an optimal solution in Genetic algorithm, operation such as selection, reproduction, and mutation procedures are used to generate next generations. The capability of this hybrid PSO that called HPGT is enhanced by cloning of fitter particles instead of worst particles that is determined based on their fitness values. The performance of HPGT algorithm and PSO algorithm compared. The results show the convergence of the HPGT is very good.

2023, Jurnal Teknologi Informasi dan Ilmu Komputer

Dokumen Jawi kuno merupakan warisan budaya yang berisi informasi penting tentang peradaban masa lalu yang dapat dijadikan pedoman untuk masa sekarang ini. Dokumen Jawi kuno telah mengalami penurunan kualitas yang disebabkan oleh beberapa faktor seperti kualitas kertas atau karena proses penyimpanan. Penurunan kualitas ini menyebabkan informasi yang terdapat pada dokumen tersebut menghilang dan sulit untuk diakses. Artikel ini mengusulkan metode binerisasi untuk membangkitkan kembali informasi yang terdapat pada dokumen Jawi kuno. Metode usulan merupakan kombinasi antara metode binerisasi berbasis nilai ambang lokal dan global. Metode usulan diuji terhadap dokumen Jawi kuno dan dokumen uji standar yang dikenal dengan nama Handwritten Document Image Binarization Contest (HDIBCO) 2016. Citra hasil binerisasi dievaluasi menggunakan metode: F-measure, pseudo F-measure, peak signal-to-noise ratio, distance reciprocal distortion, dan misclasification penalty metric. Secara rata-rata, nilai...

2023

This paper proposes a new segmentation approach which aims to segment only the foreground of an image after background elimination. Background elimination is treated as an optimization problem and is solved by using principle of PSO. The proposed algorithm is a thresholding method used to eliminate background from an image assuming that the image to be threshold contains two classes of pixels or bi-modal histogram(foreground and background). This gives a low level binary representation to the image eliminating the background and highlighting the foreground part. Based on the distance and similarity among the connected components in the binary image, it is segmented and a different similar color is assigned to each of the segment to preserve the color information contained in the real color image.

2023, 2015 International Conference on Communications and Signal Processing (ICCSP)

This article presents an optimal edge detection scheme based on the concepts of fuzzy Smallest Univalue Assimilating Nucleus (SUSAN) and the Gravitational Search Algorithm (GSA). Initially, the Univalue Assimilating Nucleus (USAN) area is calculated from the gray levels of every neighborhood pixel of a pixel of interest in the test image. In accordance with the SUSAN principle, the neighborhood is chosen as a circular mask and applied separately on the individual RGB components of the image in case the image is a color image. The USAN area edge map of each component is fuzzified using a Gaussian membership function (used for detecting strong edges) and a bell-shaped function (used for detecting weak edges). Then the entropy and edge sharpness factors are calculated from these fuzzy measures and optimized using GSA by evolving the fuzzifier and the parameters controlling the shape and range of the bell-shaped curve. Adaptive thresholding converts the fuzzy domain edge map to a spatial domain edge map. Finally, the individual RGB edge maps are concatenated to obtain the final image edge map. Qualitative and quantitative comparisons have been rendered with respect to a few promising edge detectors (both traditional as well as state-of-the-art) and also optimal fuzzy edge detectors based on metaheuristic algorithms like Differential Evolution (DE) and Particle Swarm Optimizer (PSO). Extensive comparisons based on several quantitative measures strongly reflect merits of the proposed method.

2023, Indonesian Journal of Electrical Engineering and Computer Science

2023, Image and Vision Computing

In this paper, we present a novel multi-modal histogram thresholding method in which no a priori knowledge about the number of clusters to be extracted is needed. The proposed method combines regularization and statistical approaches. By converting the approaching histogram thresholding problem to the mixture Gaussian density modeling problem, threshold values can be estimated precisely according to the parameters belonging to each contiguous cluster. Computational complexity has been greatly reduced since our method does not employ conventional iterative parameter re®nement. Instead, an optimal parameter estimation interval was de®ned before the estimation procedure. This prede®ned optimal estimation interval reduces time consumption while other histogram decomposition based methods search all feature space to locate an estimation interval for each candidate cluster. Experimental results with both simulated data and real images demonstrate the robustness of our method.

2023, American Journal of Applied Sciences

Problem statement: Skin detection is a common primitive for many human-related image processing applications, such as video surveillance, naked image filters and face detection. Skin color is considered as a useful and discriminating spatial feature for many applications, but it is not robust enough to deal with complex image environments. Skin tones range from dark (some Africans) to light white (Caucasians and some Europeans). In addition, both the light-changing conditions and the existence of objects with skin-like colors could cause some major difficulties faced pixel-based skin detector depending only on a color feature. Approach: This study proposed a novel Fuzzy Inference System (FIS) for skin detection, which combines both color and texture features. To increase the reliability of the skin detection process, neighborhood pixel information is incorporated into the proposed method. The color feature is represented using RGB color model, while the texture feature is estimated using three statistical measures: standard deviation, entropy and range. The subtractive clustering-based fuzzy system method and the Sugeno type reasoning mechanism are used for modeling FIS-based skin detection. The proposed approach builds a fuzzy model of skin detection from existing images within skin and non-skin regions (output data) and from both color and texture features of the skin regions (input data). Results: The proposed skin detection method achieved a true positive rate of approximately 90% and a false positive rate of approximately 0.22%. Furthermore, this study analyzes and compares the obtained results from the proposed skin detection with thresholdbased skin detector to show the level of robustness, using both color and texture features in the proposed skin detector. Conclusion: It was found that a skin detector based on both color and texture features can lead to an efficient and more reliable skin detection method compared with other state-ofthe-art threshold-based skin detectors. The proposed detector reduces the FP rate to 0.22% compared with a skin detector based on predefined color rules.

2023, Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

Çok seviyeli eşikleme, en çok kullanılan görüntü bölütleme yöntemlerinden birisidir. Görüntü bölütleme de kullanılan pek çok metot hesaplama karmaşıklığından dolayı çok fazla zaman tüketmektedir. Ayrıca eşik seviye sayısı arttıkça uygulama daha karmaşık ve zaman alıcı hale gelmektedir. Bu çalışmada, hesaplama zamanını azaltmak ve çok seviyeli eşikleme performansını geliştirmek için PSO yönteminin hızlı yakınsama oranı dikkate alınarak 2 boyutlu yerel olmayan histograma dayalı çok seviyeli bir eşikleme yöntemi (2DYOH-PSO) önerilmiştir. Önerilen 2DYOH-PSO yöntemi iki boyutlu Renyi’nin entropisine dayalı eşikleme yöntemi kullanılarak gerçekleştirilmiştir. Deneysel çalışmalar, Berkeley-Benchmark veri setindeki 300 görüntü için farklı seviyeli eşik değerleri dikkate alınarak yapılmıştır. Var olan 5 farklı eşik belirleme yöntemi (Diferansiyel Gelişim, Yapay Arı Algoritması, Yer Çekimi Arma Algoritması, Kbest Yer Çekimi Arma Algoritması, Kaotik Kbest Yer Çekimi Arma Algoritması) ile karşıl...

2023, International Journal of Electrical and Computer Engineering (IJECE)

2023, Multimedia Tools and Applications

In this paper, five successful nature inspired algorithms; the artificial tree algorithm (AT), the particle swarm optimization (PSO), the genetic algorithm (GA), the cultural algorithm (CA), and the cuckoo search algorithm (CS) have been compared on multilevel image thresholding. The segmentation process is based on the Levine and Nazif intra class uniformity criterion which is seen as an optimization problem. The comparison performances are in terms of the value of the objectif function, the peak signal to noise ratio (PSNR) and the computation time. Empirical results over different benchmark images for different threshold numbers reveal the robustness, the reliability and the rapidity of the cultural algorithm (CA).

2023, Pattern Recognition Letters

In a typical shoeprint classification and retrieval system, the first step is to segment meaningful basic shapes and patterns in a noisy shoeprint image. This step has significant influence on shape descriptors and shoeprint indexing in the later stages. In this paper, we extend a recently developed denoising technique proposed by Buades, called non-local mean filtering, to give a more general model. In this model, the expected result of an operation on a pixel can be estimated by performing the same operation on all of its reference pixels in the same image. A working pixel's reference pixels are those pixels whose neighbourhoods are similar to the working pixel's neighbourhood. Similarity is based on the correlation between the local neighbourhoods of the working pixel and the reference pixel. We incorporate a special instance of this general case into thresholding a very noisy shoeprint image. Visual and quantitative comparisons with two benchmarking techniques, by Otsu and Kittler, are conducted in the last section, giving evidence of the effectiveness of our method for thresholding noisy shoeprint images.

2023, International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering 2009

Image thresholding is a critical process in digital image processing application. However, there are some disturbing factors like image vagueness and bad illumination resulting in not satisfied image thresholding output. Several fuzzy thresholding techniques are developed to remove graylevel ambiguity during threshold selection. One of the techniques is thresholding method using type II fuzzy sets. In this paper, we propose relaxation of the ultrafuzziness measurement by considering ultrafuzziness for background and object fuzzy sets separately. The proposed method optimizing ultrafuzziness to decrease uncertainty in fuzzy system used type II fuzzy sets. Experimental results on several images show the effectiveness of the proposed method.

2023, 1996 8th European Signal Processing Conference (EUSIPCO 1996)

The Hue, Chroma, Intensity (HCI) space is well suited to colour images segmentation processing. In this paper, we used fuzzy logic for integrating specific knowledge of the Hue component. Based upon several linguistic rules which built a symbolic cooperation between Hue and Intensity according to Chroma, a region growing segmentation with fuzzy aggregation is proposed. This fuzzy segmentation is compared with a technique using a Fuzzy C-Means algorithm in different colour spaces.

2023

Bu calismada renkli goruntuleri otomatik olarak ayristirmak icin gelistirilen yeni bir algoritma sunulmustur. Birinci asamada, gri olcekli goruntuleri ikili kumelemek icin kullanilan Otsu, Kapur ve ortalama esasli esik secim yontemleri her bir kanal icin ayri ayri uygulamis, sonraki adimda ise belirlenen esik degerleri ile uc boyutlu renk uzayi toplamda sekiz adet kucuk kupler veya prizmalar seklinde yeniden yapilandirilmistir. Renk uzayinda olusturulan her bir renk kupu veya prizmasi bir alt kume olarak tasnif edilmistir. Yapilan benzetim ve uygulamalarla onerilen yontemin performansi test edilmis ve elde edilen sonuclarin insan algisina paralel oldugu gozlenmistir.

2023, International Journal of Advanced Computer Science and Applications

There are various mathematical optimization problems that can be effectively solved by meta-heuristic algorithms. The improvement of these algorithms is that they carry out iterative search processes which resourcefully act upon exploration and exploitation in spatial domain containing global and local optima. An innovative robust Cuckoo Optimization Algorithm (COA) with adaptive thresholding is proposed to solve the problem of detection and estimation of surface defects on metal coating surfaces. The proposed method is developed through implementing changes to COA and improved the performance. For improving capability of local search as well to keep the global search effect, the enhanced methods such as level set is associated with the proposed method. Also, the method adapts dynamic step size, adaptively changing with the search process for improving the rate of convergence and the ability of local search. The algorithm performance is scrutinized from the experimental analysis and results. Also, the segmentation effectiveness is further enhanced by adapting suitable methods for preprocessing and post processing. The comparison and analysis of the results accomplished with the proposed method and results of earlier methods shows superior performance of the proposed method.

2023

Segmentation is an essential step of image processing that directly affects its success. Among the methods used for image segmentation, histogram-based thresholding is prevalent. Two well-known approaches to histogram-based thresholding are Otsu’s and Kapur’s methods in grey images that maximize the between-class variance and the entropy measure, respectively. Both techniques were introduced for bi-level thresholding. However, these techniques can be expanded to multilevel image thresholding. For this to occur, a large number of iterations are required to account for exact threshold values. To this end, various optimization techniques have been used to overcome this drawback. Recently, a new optimization algorithm called Battle Royal Optimizer (BRO) has been published, which is shown to solve various optimization tasks effectively. In this study, BRO has been applied to yield optimum threshold values in multilevel image thresholding. Here is also demonstrated the effectiveness of BR...

2023, Signal, Image and Video Processing

In this paper, a new method for improving unsupervised LBG clustering algorithm has been proposed. This algorithm belongs to the hard and K-means vector quantization groups and drive directly from a simpler LBG. The defect of the LBG algorithm is to partition cluster in different iterations blindly. The basic idea of this paper is to use of principal component analysis and eigenvalue for handling this issue. Utilizing the eigenvalue in each step of LBG algorithm, it can either prevent from blindly splitting of vector or aggregation of data points in each cluster undoubtedly. The proficiency of eigenvalue-based LBG (E-LBG) algorithm is tested against other clustering algorithm such as Fuzzy c-Means and Gustafson-Kessel. On standard database (Iris database) and acceptable results are obtained. Comparing the obtained result of simple LBG with E-LBG in term of time and accuracy has shown that the better performance of E-LBG method in segmentation of images.

2023, Intelligent Industrial Systems

Bearings vibration in gas turbines is considered as an injurious event, which results in incidents such as emergency shutdown or damages in turbine blades and imposes expensive costs to the system. Thus, measuring and analyzing of vibration rate in gas turbines is very important and knowing about its operational conditions and prediction of this phenomenon can help a lot in reducing vibration, avoiding damage to the blades and eventually financial savings. In this paper, we are modelling the vibration rate of a real double shaft 25 MW gas turbine, located in Iran, by making use of a hybrid intelligent model based on multi-layer perceptron neural network and cuckoo optimization algorithm; so, the model in this paper is abbreviated as MLP-COA. It should be noted that this work is an absolutely novel work and the idea is implemented in a real turbine for first time. We have used a real dataset with 161 samples which are collected during a year from a gas turbine in a gas pressure booster station. Furthermore, to obtain the effect of each input parameter on the vibration rate, we have applied sensitivity analysis using the