Global Thresholding Algorithm Research Articles

A Comparison of Thresholding Methods for Forensic Reconstruction Studies Using Fluorescent Powder Proxies for Trace Materials.

Image segmentation is a fundamental precursor to quantitative image analysis. At present, no standardised methodology exists for segmenting images of fluorescent proxies for trace evidence. Experiments evaluated (i) whether manual segmentation is reproducible within and between examiners (with three participants repeatedly tracing three images) (ii) whether manually defining a threshold level offers accurate and reproducible results (with 20 examiners segmenting 10 images), and (iii) whether a global thresholding algorithm might perform with similar accuracy, while offering improved reproducibility and efficiency (16 algorithms tested). Statistically significant differences were seen between examiners’ traced outputs. Manually thresholding produced good accuracy on average (within ±1% of the expected values), but poor reproducibility (with multiple outliers). Three algorithms (Yen, MaxEntropy, and RenyiEntropy) offered similar accuracy, with improved reproducibility and efficiency. Together, these findings suggest that appropriate algorithms could perform thresholding tasks as part of a robust workflow for reconstruction studies employing fluorescent proxies for trace evidence.

An efficient multiple sclerosis segmentation and detection system using neural networks

In this work, an efficient multiple sclerosis (MS) segmentation technique is proposed to simplify pre-processing steps and diminish processing time using heterogeneous single-channel magnetic resonance imaging (MRI). A spatial-filtering image mapping, histogram reference image, and histogram matching techniques are effectively applied to possess a local threshold per image using the global threshold algorithm. Feature extraction is performed using mathematical and morphological operations, and a multilayer feed-forward neural network (MLFFNN) is used identify multiple sclerosis’ tissues. Fluid-attenuated inversion recovery (FLAIR) series are used to integrate a faster system while maintaining reliability and accuracy. A sagittal (SAG) FLAIR-based system is proposed for the first time in MS detection systems, which reduces the number of utilized images, and decreases the processing time by nearly one-third. Our detection system provided a significant recognition rate of up to 98.5%. Moreover, a relatively high dice coefficient (DC) value (0.71 ± 0.18) was observed upon testing new images.

Automatic extraction of sparse trees from high-resolution ortho-images

Obtaining information about tree species distribution in agricultural lands is a topic of interest for various applications, such as tree inventory, forest management, agricultural land management, crop estimation, etc. This information can be derived from images obtained from modern remote sensing technology, which is the most economical way as compare to field surveys covering large geographic areas. Therefore, in this study, a new method is proposed for extraction and counting of sparse and regular distributed individual pistachio trees from agricultural areas on large scale from high-resolution digital ortho-photo maps, which were obtained using an airborne sensor (Ultracam-X). The input images were first smoothed by applying Gaussian filter to reduce the impact of noise. Normalized difference vegetation indices (NDVI) were then derived to obtain vegetation areas followed by Otsu’s global thresholding algorithm to obtain candidate tree areas. Further, connected component (CC) analysis was applied to segregate each object. Morphological processing was performed to fill holes within tree objects and get smooth contours, which were obtained by using the Moore-neighbor tracing method (MNTM) for each CC, while geometrical constraints were applied to undermine possible non-tree elements from output image. To further improve the segmentation results for sparse trees, a new method was applied, called quadratic local analysis (QLA). QLA helped to segment the trees, which were missed by the Otsu method due to low contrast and resulted in improved accuracy (3–6%). The obtained results were compared with well-known support vector machine (SVM) classifier. Proposed method produced slightly better results (1–5%) than SVM for extraction of pistachio trees and obtained accuracy for QLA and SVM were 96 and 91% for region 1, while 91 and 90% for region 2 respectively.

Cross-Entropy Based Image Thresholding

This paper presents a novel global thresholding algorithm for the binarization of documents and gray-scale images using Cross-Entropy Clustering. In the first step, a gray-level histogram is constructed, and the Gaussian densities are fitted. The thresholds are then determined as the cross-points of the Gaussian densities. This approach automatically detects the number of components (the upper limit of Gaussian densities is required).

Threshold Optimization Framework of Global Thresholding Algorithms Using Gaussian Fitting

Threshold Optimization Framework of Global Thresholding Algorithms Using Gaussian Fitting

Visual Saliency Models for Text Detection in Real World.

This paper evaluates the degree of saliency of texts in natural scenes using visual saliency models. A large scale scene image database with pixel level ground truth is created for this purpose. Using this scene image database and five state-of-the-art models, visual saliency maps that represent the degree of saliency of the objects are calculated. The receiver operating characteristic curve is employed in order to evaluate the saliency of scene texts, which is calculated by visual saliency models. A visualization of the distribution of scene texts and non-texts in the space constructed by three kinds of saliency maps, which are calculated using Itti's visual saliency model with intensity, color and orientation features, is given. This visualization of distribution indicates that text characters are more salient than their non-text neighbors, and can be captured from the background. Therefore, scene texts can be extracted from the scene images. With this in mind, a new visual saliency architecture, named hierarchical visual saliency model, is proposed. Hierarchical visual saliency model is based on Itti's model and consists of two stages. In the first stage, Itti's model is used to calculate the saliency map, and Otsu's global thresholding algorithm is applied to extract the salient region that we are interested in. In the second stage, Itti's model is applied to the salient region to calculate the final saliency map. An experimental evaluation demonstrates that the proposed model outperforms Itti's model in terms of captured scene texts.

AN EFFECTIVE AND ROBUST TECHNIQUE FOR THE BINARIZATION OF DEGRADED DOCUMENT IMAGES

Binarization methods play a central role in document image processing. It is usually performed in the preprocessing stage and is important for document image processing tasks such as optical character recognition (OCR). Segmentation of text from badly degraded document images is a challenging task because of the high inter/intra-variation between the document background and foreground text of different document images. So method for segmenting the foreground text from the background is presented here. In this method first of all an image having high contrast has been constructed. For this a rough estimation of background is to be made. Then a hybrid algorithm for thresholding has been used. It consists of both global and local thresholding methods. The Global thresholding step has been modified such that the output will not be a binarized image but an intermediate gray level image. It is helpful as most of the background gets eliminated. Local thresholding will be applied on the result given by global thresholding step. This method is simple, robust and effective. The proposed method works better than most of the existing local and global thresholding algorithms and is able to deal with degradations which occur due to strain, ink bleed through, low contrast, water marks, dust, smear and uneven illumination etc. This method has been tested on three public datasets that are used in recent document image binarization contest (DIBCO) 2009 and 2011and handwritten-DIBCO 2011and achieves the results which are significantly higher than or close to the best performing methods reported in three contests. Also to show the superior performance of the proposed method compared with other techniques, experiments have been performed on more challenging bickley diary dataset.

ECH-A NOVEL MULTILEVEL THRESHOLDING TECHNIQUE FOR MINUTIAE BASED FINGERPRINT RECOGNITION

Thresholding is probably the most frequently used technique in segmenting an image. Several computationally efficient thresholding algorithms have been shown to offer threshold value, however whilst many of the methods will give similar guarantees. In this proposed research work, a novel multilevel global thresholding algorithm ECH (pronounced as eh-chch) is introduced. The algorithm uses HAT transformation to maintain uniform intensity in the gray scale images. The optimum threshold value is decided by entropying of the background and foreground regions, where the gray scale samples are clustered as a mixture of two Gaussians for background and foreground objects, using which the peaks and valleys like minutiae points are analyzed. This paper also explores a range of steps implicated in FP recognition. The performances of the algorithm are compared with NEST DB4, DB2 FVC2002, DB2 FVC2004 databases. The performance indices FAR (False Acceptance Ratio) less than 1.3% and FRR (False Rejection Ratio) almost 0% is reported using MATLAB. The experimental results on MATLAB shows prominent result on gray scale finger print images.

히스토그램 분포 분류를 통한 효율적인 세포 이미지 분할 시스템

Cell segmentation which extracts cell objects from background is one of basic works in bio-imaging which analyze cell images acquired from live cells in cell culture. In the case of clear images, they have a bi-modal histogram distribution and segmentation of them can easily be performed by global threshold algorithm such as Otsu algorithm. But In the case of degraded images, it is difficult to get exact segmentation results. In this paper, we developed a cell segmentation system that it classify input images by the type of their histogram distribution and then apply a proper segmentation algorithm. If it has a bi-modal distribution, a global threshold algorithm is applied for segmentation. Otherwise it has a uni-modal distribution, our algorithm is performed. By experimentation, our system gave exact segmentation results for uni-modal cell images as well as bi-modal cell images.

A Robust Thresholding Algorithm Framework based on Reconstruction and Dimensionality Reduction of the Three Dimensional Histogram

In this work, a robust thresholding algorithm framework based on reconstruction and dimensionality reduction of the three-dimensional (3-D) histogram is proposed with the consideration of the poor anti-noise performance in existing 3-D histogram-based segmentation methods due to the obviously wrong region division. Firstly, our method reconstructs the 3-D histogram based on the distribution of noisy points which reduce its segmentation performance. Secondly, we transfer the region division in 3-D histogram from eight partitions into two parts, thus reducing the searching space of threshold from 3-dimension to 1-dimension, which saves a lot of processing time and memory space. Thirdly, we apply the presented framework to global thresholding algorithms such as Otsu method, minimum error method, and maximum entropy method and so on, and propose corresponding robust global thresholding algorithms. Finally, segmentation result and running time are given at the end of this paper compared with those of 3-D Otsu’s method, Otsu method, minimum error method and maximum entropy method. The experimental results show that the presented method has better anti-noise performance and visual quality compared with the above four approaches, and has lower time complexity than 3-D Otsu’s method.

The Vagueness Measure: A New Interpretation and an Application to Image Thresholding

Here, we introduce a new interpretation of the vagueness measure (which appeared in an earlier work) and an application for this approach. If the vagueness measure is computed for the distribution function of a given population, the value obtained gives a similar characteristic as the standard deviation of the population. Based on this property, a new global thresholding algorithm was developed that generalizes the idea of Otsu's optimality criterion by the means of continuous-valued logic. The performance of this method is compared with other commonly used algorithms to validate the usefulness of the proposed approach. Although the purpose of this algorithm is to threshold a grayscale image (which can be a useful step in the segmentation process of biological and medical images), it can be generalized for other tasks that require the separation of two or more populations, characterized by real values.

Rapid entropy-based detection and properties measurement of concrete spalling with machine vision for post-earthquake safety assessments

The current procedures in post-earthquake safety and structural assessment are performed manually by a skilled triage team of structural engineers/certified inspectors. These procedures, and particularly the physical measurement of the damage properties, are time-consuming and qualitative in nature. This paper proposes a novel method that automatically detects spalled regions on the surface of reinforced concrete columns and measures their properties in image data. Spalling has been accepted as an important indicator of significant damage to structural elements during an earthquake. According to this method, the region of spalling is first isolated by way of a local entropy-based thresholding algorithm. Following this, the exposure of longitudinal reinforcement (depth of spalling into the column) and length of spalling along the column are measured using a novel global adaptive thresholding algorithm in conjunction with image processing methods in template matching and morphological operations. The method was tested on a database of damaged RC column images collected after the 2010 Haiti earthquake, and comparison of the results with manual measurements indicate the validity of the method.

Artificial Neural Network to Predict Leaf Population Chlorophyll Content from Cotton Plant Images

Leaf population chlorophyll content in a population of crops, if obtained in a timely manner, served as a key indicator for growth management and diseases diagnosis. In this paper, a three-layer multilayer perceptron (MLP) artificial neural network (ANN) based prediction system was presented for predicting the leaf population chlorophyll content from the cotton plant images. As the training of this prediction system relied heavily on how well those leaf green pixels were separated from background noises in cotton plant images, a global thresholding algorithm and an omnidirectional scan noise filtering coupled with the hue histogram statistic method were designed for leaf green pixel extraction. With the obtained leaf green pixels, the system training was carried out by applying a back propagation algorithm. The proposed system was tested to predict the chlorophyll content from the cotton plant images. The results using the proposed system were in sound agreement with those obtained by the destructive method. The average prediction relative error for the chlorophyll density (μg cm −2) in the 17 testing images was 8.41%.

The influence of quantization process on the performance of global entropic thresholding algorithms using electrical capacitance tomography data

In measuring component fraction in multiphase flows using tomographic techniques, it is desirable to use a high speed tomography system capable of generating 100 tomograms per second. The electrical capacitance tomography system in this regard is considered to be the best among the available tomographic techniques. However, due to its inherent limitations the system generates distorted reconstructed tomograms necessitating the use of extra signal processing techniques such as thresholding to minimize these distortions. Whilst thresholding technique has been effective in minimizing distortions, the additional computation associated with the process limits the speed of tomogram generation desired from the system. Further, the accuracy of the techniques is limited to higher ranges of the full component fraction range. However, since its performance can be influenced by the nature of the quantization process required a priori, optimal quantization parameters can be found and used to improve performance. In this article the influence of quantization resolution and its rate on the performance of global entropic thresholding algorithms have been investigated. Measurement of gas volume component fraction in a multiphase flow of gas/liquid mixture using electrical capacitance tomography system has been used for evaluation using simulated and online capacitance measurement data. Results show that an optimal quantizer resolution is flow regime dependent. Higher resolutions are optimal for annular flow and vice versa for stratified flow regimes. Also, higher resolution significantly minimizes the dependency of the thresholding algorithm on the object to be searched, thereby reducing complexity of designing a thresholder. Overall, the optimal quantization resolution is 256. Tanzania Journal of Science Vol. 31 (2) 2005: pp. 63-76

Threshold algorithm to recover the deformation of optical surfaces

The global optimization threshold algorithm is reported to obtain the deformations of an optical surface. The advantage of these types of algorithm is that they can be solved for the correlation problem presented in Seidel polynomials. We obtain the 2D deformations of a surface test with the transversal aberration along one direction only. In order to apply this algorithm we used exact ray tracing to simulate the transversal aberration adapting the same mathematical theory for the Ronchi test. The error obtained in sagitta recovering deformation was 1 microm.

Image processing of underwater multispectral imagery

Capturing in situ fluorescence images of marine organisms presents many technical challenges. The effects of the medium, as well as the particles and organisms within it, are intermixed with the desired signal. Methods for extracting and preparing the imagery for analysis are discussed in reference to a novel underwater imaging system called the low-light-level underwater multispectral imaging system (LUMIS). The instrument supports both uni- and multispectral collections, each of which is discussed in the context of an experimental application. In unispectral mode, LUMIS was used to investigate the spatial distribution of phytoplankton. A thin sheet of laser light (532 nm) induced chlorophyll fluorescence in the phytoplankton, which was recorded by LUMIS. Inhomogeneities in the light sheet led to the development of a beam-pattern-correction algorithm. Separating individual phytoplankton cells from a weak background fluorescence field required a two-step procedure consisting of edge detection followed by a series of binary morphological operations. In multispectral mode, LUMIS was used to investigate the bio-assay potential of fluorescent pigments in corals. Problems with the commercial optical-splitting device produced nonlinear distortions in the imagery. A tessellation algorithm, including an automated tie-point-selection procedure, was developed to correct the distortions. Only pixels corresponding to coral polyps were of interest for further analysis. Extraction of these pixels was performed by a dynamic global-thresholding algorithm.

Real-time image segmentation system for IC die patterns

A real-time image segmentation system realized for extracting the bond pads in IC die images is presented. The system can work in current IC manufacturing machines with binary-level pattern recognition systems under nearly uniform lighting conditions. The system uses a general-purpose digital signal processor DSP56001 to realize the global thresholding algorithm, and most of the functional blocks are implemented using programmable logic devices. The selection of the thresholding algorithm is based on the characteristics of industrial IC die images.

An Analysis of Histogram-Based Thresholding Algorithms

Eleven histogram-based global thresholding algorithms are presented in a common notational framework. Relationships among them are identified from 654 mixtures of two Gaussian distributions, plus effects of mixed pixels. The iterated version of Kittler and Illingworth′s minimum error algorithm (Pattern Recognition, 19, 1986, 41-47) is found to be best.

An Analysis of Histogram-Based Thresholding Algorithms

Eleven histogram-based global thresholding algorithms are presented in a common notational framework. Relationships among them are identified from 654 mixtures of two Gaussian distributions, plus effects of mixed pixels. The iterated version of Kittler and Illingworth′s minimum error algorithm (Pattern Recognition, 19, 1986, 41-47) is found to be best.

A comparative performance study of several global thresholding techniques for segmentation

A comparative performance study of five global thresholding algorithms for image segmentation was investigated. An image database with a wide variety of histogram distribution was constructed. The histogram distribution was changed by varying the object size and the mean difference between object and background. The performance of five algorithms was evaluated using the criterion functions such as the probability of error, shape, and uniformity measures Attempts also have been made to evaluate the performance of each algorithm on the noisy image. Computer simulation results reveal that most algorithms perform consistently well on images with a bimodal histogram. However, all algorithms break down for a certain ratio of population of object and background pixels in an image, which in practice may arise quite frequently. Also, our experiments show that the performances of the thresholding algorithms discussed in this paper are data-dependent. Some analysis is presented for each of the five algorithms based on the performance measures.