Narrow Results

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.

A new vortex identification method is proposed for extracting vortical structures from homogeneous isotropic turbulence. The method is compared with other identification schemes such as the high rotational method ($Q$), the vorticity magnitude method ($\omega$), the negative eigenvalue method (${\lambda }_2$) and the normalized vorticity method ($\mathrm{\Omega }$). A new normalization method based on the probability distribution function (PDF) of the identification invariants is also introduced. In addition, a modification for the discriminant criterion known as the $\mathrm{\Delta }$ method is carried out and it is denoted as the modified delta method (${\mathrm{\Delta }}_m$). The velocity of the isotropic turbulent field is simulated using the lattice Boltzmann method with resolution $256^3$. The new identification method depends on the higher-orders of the invariants of the velocity gradient tensor as well as the strain rate and the enstrophy production terms. The elongated tube-like vortices are extracted successfully using the new method and several features of the vortices are demonstrated and compared with the vortical structures that are extracted using the $Q$, $\omega$, ${\lambda }_2$, $\mathrm{\Omega }$, $\mathrm{\Delta }$ and ${\mathrm{\Delta }}_m$ identification methods. The recommended normalization method enabled the justification of the visualization threshold value to be within the order of unity and the threshold value $0.55$ is used in all identification methods. A remarkably similar geometrical worm-like vortices are extracted and a high similarity between the identification methods is observed and statistically studied.

Introduction: The expansion of pulmonary tumors and their alterations take place in a dynamic manner, so that vigorous segmentation of the obtained images is accurately required.

Methods: In this research, an extended algorithm in region growing was executed on CT lung tumors to investigate precise tumor region and edges. First, a new threshold via definition of greater target region around the initial tumor was implemented in MATLAB software. Second, nearby points were settled in an array and then these points were updated established upon the tumor growth to delineate the fresh tumor edges. Here, farthest distance from the center of color intensity point of the initial tumor was selected to grow the region in the algorithm. Third, fresh tumor boundary was determined via an interpolation between these fresh points by sketching lines from the tumor midpoint. Then, the edge correction was implemented and the fresh region was attached to the principal region to attain a segmented tumor exterior.

Results: The proposed technique enhanced the tumor recognition by 96% and 91% maximum and minimum accuracy, respectively, in comparison with basilar method. In inclusive algorithm, the percentage of conformity had a positive effect on realization of the threshold value and renewal of the relative amount by 13% enhancement over accuracy assessment. Also when compared to basilar algorithm, it was found that at least 12% of the percentage differences in conformity segment the tumor area in lung CT images. The proposed algorithm with sufficient accuracy accelerates the segmentation process to delineate and improve the tumor edges by growing multiple selected regions. The algorithm also guarantees the independence of the results from the starting point.

Conclusion: According to the definition of the center of mass of the tumor color intensity, the proposed extended algorithm may be generalized to the 3D images regardless of the matrix size and the image thickness. The combination of techniques such as machine learning is expected to improve segmentation accuracy for different types of nodule and tumor CT images.

Implications for practice: Proposed extended algorithm with sufficient accuracy accelerates the segmentation process to delineate and improve the tumor edges by growing multiple selected regions.

There is wide application for the extraction of textual information from low-contrast, complex natural images. We are particularly interested in segmentation and thresholding algorithms for use in a portable text-to-speech system for the vision impaired. Reading low-contrast LCD displays is the target application. We present a low-complexity method for automatically extracting text of any size, font, and format from images acquired by a video camera that may be poorly focused and aimed, under conditions of inadequate and uneven illumination. The new method consists of fast thresholding that combines a local variance measure with a logical stroke-width method, and with a low-complexity statistical and contextual noise segmentation. The performance of this method compares favorably with more complex methods for the extraction of characters from scene images. Initial results are encouraging for application in a robust portable reader.

Wavelet-based techniques are suitable for recovering a signal corrupted by noise. The time- and frequency-localization capabilities of wavelets provide better noise reduction and less signal distortion than conventional filtering methods. The noise reduction technique used in this paper is based on the hidden Markov model (HMM) structure, which can efficiently shape the statistical characteristics of practical data. As confirmed by numerical results, the HMM based approach provides a significant performance improvement over competing methods.

Thresholding algorithms are being increasingly used in a wide variety of disciplines to objectively discern patterns and objects in micrographs, still pictures or remotely-sensed images. Our experience has shown that three common thresholding algorithms exhibit indeterminacy, in that different operator inputs may lead to very different pattern characterizations. A grayscale image of a soil profile is used to illustrate this phenomemon in the case of the intermeans (IM), minimum error (ME), and Besag's iterated conditional modes (ICM) algorithms. For the illustrative example, the IM algorithm depends only weakly on the starting point of the iterative process — it converges to only two adjacent threshold values. In contrast, the ME algorithm converges to 14 different threshold values plus a segmentation that identifies the entire image as dye, and one that identifies none of it as dye. The ICM algorithm converges to an even wider variety of final segmentations, depending on its starting point. A noniterative modification of the IM and ME algorithms is proposed, providing a consistent method for choosing from among a set of apparently equally-valid segmentations.

The denoising of a natural signal/image corrupted by Gaussian white noise is a classical problem in signal/image processing. However, it is still in its infancy to denoise high dimensional data. In this paper, we extended Sendur and Selesnick's bivariate wavelet thresholding from two-dimensional (2D) image denoising to three-dimensional (3D) data cube denoising. Our study shows that bivariate wavelet thresholding is still valid for 3D data cubes. Experimental results show that bivariate wavelet thresholding on 3D data cube is better than performing 2D bivariate wavelet thresholding on every spectral band separately, VisuShrink, and Chen and Zhu's 3-scale denoising.

K-means is undoubtedly the most widely used partitional clustering algorithm. Unfortunately, due to its gradient descent nature, this algorithm is highly sensitive to the initial placement of the cluster centers. Numerous initialization methods have been proposed to address this problem. Many of these methods, however, have superlinear complexity in the number of data points, making them impractical for large data sets. On the other hand, linear methods are often random and/or order-sensitive, which renders their results unrepeatable. Recently, Su and Dy proposed two highly successful hierarchical initialization methods named Var-Part and PCA-Part that are not only linear, but also deterministic (nonrandom) and order-invariant. In this paper, we propose a discriminant analysis based approach that addresses a common deficiency of these two methods. Experiments on a large and diverse collection of data sets from the UCI machine learning repository demonstrate that Var-Part and PCA-Part are highly competitive with one of the best random initialization methods to date, i.e. k-means++, and that the proposed approach significantly improves the performance of both hierarchical methods.

The theory of formation of an ideal image has been described which shows that the gray level in an image follows the Poisson distribution. Based on this concept, various algorithms for object background classification have been developed. Proposed algorithms involve either the maximum entropy principle or the minimum χ² statistic. The appropriateness of the Poisson distribution is further strengthened by comparing the results with those of similar algorithms which use conventional normal distribution. A set of images with various types of histograms has been considered here as the test data.

Image binarization is a task to convert gray-level images into bi-level ones. Its underlying notion can be simply thought of as threshold selection. However, the result of binarization will cause significant influence on the process of image recognition or understanding. In this paper we discuss a new binarization method, named CMB (connectionist model binarization), which uses the connectionist model. In the method a gray-level histogram is input to a multilayer network trained with the back-propagation algorithm to obtain a threshold which gives a visually suitable binarized image. From the experimental results, it was verified that CMB is an effective binarization method in comparison with other methods.

This paper presents the results of a study on the use of morphological skeleton transformation to segment gray-scale images into bilevel images. When a bilevel image (such as printed texts and machine tools) is digitized, the result is a gray-scale image due to the point spread function of digitizer, non-uniform illumination and noise. Our method can recover the original bilevel image from the gray-scale image. The theoretical basis of the algorithm is the physical structure of the skeleton set. A connectivity property of the gray-scale skeleton transformation is used to separate and remove the background terrain. The object pixels can then be obtained by applying a global threshold. Experimental results are given.

This paper describes a new method for character recognition of typewritten text. The proposed approach is based on the approximation of character signatures by rational functions. Specifically, after the preprocessing operation, a separation procedure is applied to each character and its one-dimensional signatures are derived. These signatures are then approximated by rational functions via a linear programming technique and according to the minimax criterion. The values of the approximation errors for each signature are specified as character features. Through this technique only six powerful features are derived for each character. The classification technique employed is simple, adapted to the features selected and is based on features’ similarities in combination with the minimum Euclidean distance classifier.

We have developed a generalized alphanumeric character extraction algorithm that can efficiently and accurately locate and extract characters from complex scene images. A scene image may be complex due to the following reasons: (1) the characters are embedded in an image with other objects, such as structural bars, company logos and smears; (2) the characters may be painted or printed in any color including white, and the background color may differ only slightly from that of the characters; (3) the font, size and format of the characters may be different; and (4) the lighting may be uneven.

The main contribution of this research is that it permits the quick and accurate extraction of characters in a complex scene. A coarse search technique is used to locate potential characters, and then a fine grouping technique is used to extract characters accurately. Several additional techniques in the postprocessing phase eliminate spurious as well as overlapping characters. Experimental results of segmenting characters written on cargo container surfaces show that the system is feasible under real-life constraints. The program has been installed as part of a vision system which verifies container codes on vehicles passing through the Port of Singapore.

Visual illusion is the fallacious perception of reality or some actually existing object. In this paper, we imitate the mechanism of Ehrenstein illusion, neon color spreading illusion, watercolor illusion, Kanizsa illusion, shifted edges illusion, and hybrid image illusion using the Open Source Computer Vision Library (OpenCV). We also imitate these illusions using Cellular Neural Networks (CNNs). These imitations suggest that some illusions are processed by high-level brain functions. We next apply the morphological gradient operation to anomalous motion illusions. The processed images are classified into two kinds of images, which correspond to the central drift illusion and the peripheral drift illusion, respectively. It demonstrates that the contrast of the colors plays an important role in the anomalous motion illusion. We also imitate the anomalous motion illusions using both OpenCV and CNN. These imitations suggest that some visual illusions may be processed by the illusory movement of animations.

An improved fuzzy C-means (FCM) clustering method is proposed. It incorporates Otsu thresholding with conventional FCM to reduce FCM's susceptibility to local minima, as well as its tendency to derive a threshold that is biased towards the component with larger probability, and derive threshold values with greater accuracy. Thresholding is performed at the cluster boundary region in feature space. A comparison of the results produced by improved and conventional algorithms confirms the superior performance of the former.

The selection of optimal thresholds is still a challenging task for researchers in case of multilevel thresholding. Many swarm and evolutionary computation techniques have been applied for obtaining optimal values of thresholds. The performance of all these computation techniques is highly dependent on proper selection of algorithm-specific parameters. In this work, a new hybrid optimization technique, membrane computing inspired teacher-learner-based-optimization (MCTLBO), is proposed which is based on the structure of membrane computing (MC) and teacher-learner-based-optimization (TLBO) algorithm. To prove the efficacy of proposed algorithm, it is applied to solve multilevel thresholding problem in which the Kapur's entropy criterion is considered as figure-of-merit. In this experiment, four benchmark test images are considered for multilevel thresholding. The optimal values of thresholds are obtained using TLBO, MC and particle swarm optimization (PSO) in addition to proposed algorithm to accomplish the comparative study. To support the superiority of proposed algorithm over others, various quantitative and qualitative results are presented in addition to statistical analysis.

Binarization of gray scale document images is one of the most important steps in automatic document image processing. In this paper, we present a two-stage document image binarization approach, which includes a top-down region-based binarization at the first stage and a neural network based binarization technique for the problematic blocks at the second stage after a feedback checking. Our two-stage approach is particularly effective for binarizing text images of highlighted or marked text. The region-based binarization method is fast and suitable for processing large document images. However, the block effect and regional edge noise are two unavoidable problems resulting in poor character segmentation and recognition. The neural network based classifier can achieve good performance in two-class classification problem such as the binarization of gray level document images. However, it is computationally costly. In our two-stage binarization approach, the feedback criteria are employed to keep the well binarized blocks from the first stage binarization and to re-binarize the problematic blocks at the second stage using the neural network binarizer to improve the character segmentation quality. Experimental results on a number of document images show that our two-stage binarization approach performs better than the single-stage binarization techniques tested in terms of character segmentation quality and computational cost.

Speckles are inherent to SAR. They hide and undermine several relevant information contained in the SAR images. In this paper, a despeckling algorithm using the shrinkage of two-dimensional discrete orthonormal S-transform (2D-DOST) coefficients in the transform domain along with shock filter is proposed. Also, an attempt has been made as a post-processing step to preserve the edges and other details while removing the speckle. The proposed strategy involves decomposing the SAR image into low and high-frequency components and processing them separately. A shock filter is used to smooth out the small variations in low-frequency components, and the high-frequency components are treated with a shrinkage of 2D-DOST coefficients. The edges, for enhancement, are detected using a ratio-based edge detection algorithm. The proposed method is tested, verified, and compared with some well-known models on C-band and X-band SAR images. A detailed experimental analysis is illustrated.

India is rich in its heritage and culture. It has many historical monuments and temples where the walls are made of inscribed stones and rocks. The stone inscriptions play a vital role in portraying about the ancient incidents. Hence, the digitization of these stone inscriptions is necessary and contributes much for the epigraphers. Recently, the digitizing of these inscriptions began with the binarization process of stone inscriptions. This process mainly depends on the thresholding technique. In this paper, the binarization of terrestrial and underwater stone inscription images is preceded by a contrast enhancement and succeeded by edge-based filtering that minimizes noise and fine points the edges. A new method called modified bi-level thresholding (MBET) algorithm is proposed and compared with various existing thresholding algorithms namely Otsu method, Niblack method, Sauvola method, Bernsen method and Fuzzy C means method. The obtained results are evaluated with the performance metrics such as peak signal-to-noise ratio (PSNR) and standard deviation (SD). It is observed that the proposed method has an improvement of 49% and 39%, respectively, on an average by the metrics considered.

An accurate measurement of the different electrocardiogram (ECG) intervals is dependent on the accurate identification of the beginning and the end of the P, QRS, and T waves. Available commercial systems provide a good QRS detection accuracy. However, the detection of the P and T waves remains a serious challenge due to their widely differing morphologies in normal and abnormal beats. In this paper, a new algorithm for the detection of the QRS complex as well as for P and T waves identification is provided. The proposed algorithm is based on different approaches and methods such as derivations, thresholding, and surface indicator. The proposed algorithm is tested and evaluated on ECG signals from the universal MIT-BIH database. It shows a good ability to detect P, QRS, and T waves for different cases of ECG signal even in very noisy conditions. The obtained QRS, sensitivity and positive predictivity are respectively 95.39% and 98.19%. The developed algorithm is also able to separate the overlapping P and T waves.