Найдено 20
Ничего не найдено
A morphologically driven gradient and marker controlled distance regularised level sets for nuclear segmentation in histopathological images
Nagabhushan T.N., Prasad B., Basavaraj V., Shivamurthy P.M.
Q4
International Journal of Signal and Imaging Systems Engineering,
2019,
цитирований: 0,
open access
,
doi.org,
Abstract
,
The extraction of suitable biomarkers over a tissue image plays a vital role in the diagnosis and prognosis of cancer disease. Nuclear pleomorphism is one such trait, which serves as an important shape-based biomarker. An effective segmentation of the nuclei objects leads to an accurate diagnosis by an expert pathologist, which otherwise would be erroneous due to inter and intra-observer variability. In this research, a novel approach for segmenting the nuclei objects, using distance regularised level sets (DRLS), has been presented. It is shown that the shape prior based morphological transformation of the image achieves: a) centroid detection for accurate contour initialisation; b) gradient computation for an effective contour evolution. Experiments have been conducted on benign and malignant tissue images followed by a performance study using the object detection and the overlap resolution accuracy. Segmentation accuracy is assessed in comparison with the geodesic active contours, based on the ground truth.
A thresholding scheme of eliminating false detections on vehicles in wide-area aerial imagery
Gao X.
Q4
International Journal of Signal and Imaging Systems Engineering,
2018,
цитирований: 4,
open access
,
doi.org,
Abstract
,
Post-processings are usually necessary to reduce false detections on vehicles in wide-area aerial imagery. In order to improve the performance of vehicle detection, we propose a two-stage scheme, which consists of a thresholding method by constructing a pixel-weight based thresholding policy to classify pixels in the greyscale feature map of an automatic detection algorithm followed by morphological filtering. We use two aerial videos for performance evaluation, and compare the automatic detection results with the ground-truth objects. We compute average F-score and percentage of wrong classifications towards six detection algorithms before and after applying the proposed scheme. We measure the variation of overlap ratios from detections to objects, and establish sensitivity analysis to evaluate the performance of proposed scheme by combining it on each of two representative algorithms. Simulation results verify both validity and efficiency of the proposed thresholding scheme, also display the difference of detection performance between datasets and among algorithms.
Early detection of Parkinson's disease through multimodal features using machine learning approaches
Prasad B., Pushkarna R., Pahuja G., Nagabhushan T.N.
Q4
International Journal of Signal and Imaging Systems Engineering,
2018,
цитирований: 0,
open access
,
doi.org,
Abstract
,
This research establishes a relation between objective biomarkers of Parkinson's disease (PD) based on T1-weighted MRI scans and other clinical biomarkers. It shall aid doctors in identifying the onset and progression of PD among the patients. Voxel-based morphometry has been used for feature extraction from MRI scans. These extracted features are combined with biochemical biomarkers for dataset enrichment. A genetic algorithm is applied to this dataset to remove the redundancies and to obtain an optimal set of features. Subsequently, we used Self-adaptive resource allocation network (SRAN), extreme learning machine (ELM) and support vector machines (SVM) to classify different subjects. It is observed that SRAN classifier gave the best performance when compared with ELM and SVM. Finally, it is found that a variation of grey matter in Thalamus is responsible for PD. The obtained results corroborate the earlier findings from the literature.
Comparative analysis of two leading evolutionary intelligence approaches for multilevel thresholding
Ye Z., Yin H., Ye Y.
Q4
International Journal of Signal and Imaging Systems Engineering,
2018,
цитирований: 0,
open access
,
doi.org,
Abstract
,
The rapid advance of artificial intelligence has made complex image processing in real time possible. Multilevel thresholding has become a feasible way for image segmentation, even in the presence of poor contrast and external artefacts. Genetic algorithms (GAs) and particle swarm optimisation (PSO) are broadly recognised by far to be two dominating schemes which outperform classical ones on multilevel thresholding. Qualitative analysis can usually be applied to observe their superiority to all classical approaches. However, no convincing result is reached with respect to differences in performance between GAs and PSO. The existing segmentation practices are either examined by visual appeals exclusively, or evaluated quantitatively assuming perfect statistical distributions. To make thorough comparisons, comparative analysis of two leading multilevel thresholding approaches is conducted for true colour image segmentation. The information theory is also employed to analyse the outcomes of systematic approaches using diverse quantitative metrics from various aspects.
Compressed fixed-point data formats with non-standard compression factors
Richey M., Saiedian H.
Q4
International Journal of Signal and Imaging Systems Engineering,
2017,
цитирований: 0,
open access
,
doi.org,
Abstract
,
Sign bit compression in fixed-point numbering systems can improve the dynamic range and round-off noise for signal processing algorithms. This paper analyses non-standard compression factors (CF) for compressed fixed-point data formats, where sign bit compression is performed on each individual fixed-point number. Although these compression techniques are applicable to other fixed-point formats, the compressed two's complement data format is selected for illustration. A brief background on compressed two's complement is provided. Obvious compression factors are powers of two due to binary formatting, but compression factors other than standard powers of two are presented. Compression factors of 3 and 5 are analysed in greater detail. Motivation for and advantages of non-power-of-two compression factors are identified.
System level design of adaptive arithmetic encoder/decoder for JPEG 2000 standard
Reza A.M.
Q4
International Journal of Signal and Imaging Systems Engineering,
2016,
цитирований: 1,
open access
,
doi.org,
Abstract
,
System level design for adaptive arithmetic encoder and decoder used in the JPEG 2000 standard is proposed. The encoder design is based on the assumption that the bit-sequence and its corresponding context, obtained through bit modelling for the encoder, are input to the system in their proper order. The original bit-sequence provides the context based on the assumption that the first pass is the clean-up pass and the first context is the run-length context. All other contexts are recursively evaluated as an arithmetic encoder encodes the bit sequence. The final encoding is lossless which results in perfect recovery of the original block image when proper decoding algorithm is used. The decoder design is also based on the assumption that the compressed bit-sequence and its corresponding context, obtained through bit modelling for the decoder, are input to the system in their proper order. The output bit-sequence is also used as an input to the decoder bit modelling.
BayWave: BAYesian WAVElet-based image estimation
Pande A., Mittal S.
Q4
International Journal of Signal and Imaging Systems Engineering,
2015,
цитирований: 6,
open access
,
doi.org,
Abstract
,
Image denoising is an important step in image compression and other image processing algorithms. Hard and soft thresholding algorithms are often used to denoise the images. Recently wavelet transform has been used as a tool to denoise the images. However, there are problems associated with the thresholding algorithms. There is no subjective way to determine the threshold. In this work, we implement a simple Bayesian theory to obtain optimal threshold for such algorithms. MATLAB simulations were performed to validate the working of Bayesian thresholding method.
Effective and accurate modelling of multiconductor transmission lines in multilayer dielectric media
Musa S.M., Sadiku M.N.
Q4
International Journal of Signal and Imaging Systems Engineering,
2014,
цитирований: 0,
open access
,
doi.org,
Abstract
,
Development of very high speed integrated circuits is currently of great interest for today's technologies. This paper presents the quasi–TEM approach for accurate parameter extraction of multiconductor transmission line interconnects in single–, two– and three–layered dielectric regions using the Finite Element Method (FEM). We illustrate that FEM is accurate and effective for modelling multilayered multiconductor transmission lines in strongly inhomogeneous media. We mainly focus on designing of five transmission lines embedded in single–, two– and three–layered dielectric media. We compute the capacitance matrices for these configurations. We also determine the quasi–TEM spectral for the potential distribution of the multiconductor transmission lines in multilayer dielectric media.
Image database categorisation using robust modelling of finite generalised Dirichlet mixture
Ismail M.M., Frigui H.
Q4
International Journal of Signal and Imaging Systems Engineering,
2012,
цитирований: 0,
open access
,
doi.org,
Abstract
,
We propose a novel image database categorisation approach using Robust Modelling of finite Generalised Dirichlet Mixture (RM-GDM). The proposed algorithm is based on optimising an objective function that associates two types of memberships with each data sample. The first one is the posterior probability and indicates how well a sample fits each estimated distribution. The second membership represents the degree of typicality and is used to identify and discard noise points and outliers. These properties make RM-GDM suitable for noisy and high-dimensional feature spaces. We use the RM-GDM to categorise a large collection of colour images. Its performance is illustrated and compared to similar algorithms.
A pattern tracking algorithm for lossless data compression
Hebert T.J., Karulkar S.N.
Q4
International Journal of Signal and Imaging Systems Engineering,
2011,
цитирований: 0,
open access
,
doi.org,
Abstract
,
Where digital data is costly or subject to federal law (space, seismic or medical imaging), importance of the data may lead to exclusive use of lossless encoding. We present a pattern-tracking algorithm for lossless encoding, complete with a file header. This algorithm is based upon the expectation that data contain patterns that re-occur with varying amplitudes. This algorithm is compared to standard lossless coding algorithms using 24 data sets from four signal applications. Compression ratios were 1.6 to 2.7. The pattern-tracking algorithm performed best on certain data sets, while competing algorithms performed best on other data sets.
Novel biological metamaterials, nanoscale optical devices, and Polarimetric Exploratory Data Analysis (pEDA)
Giakos G.C.
Q4
International Journal of Signal and Imaging Systems Engineering,
2010,
цитирований: 12,
open access
,
doi.org,
Abstract
,
This study reports that certain biological macromolecules, colloidal suspensions, or organic molecular structures, with very large optical activities, exhibit enhanced transmission, backscattering and signal characteristics. Although by definition, these molecular nanocomposite structures can be classified as metamaterials, whether these macromolecules exhibit uniquely defined metamaterial characteristics, deserves a careful study before any assessment can be made. Based on the above, a new optical polarimetric metrics definition is introduced, namely, the Polarimetric Exploratory Data Analysis (pEDA) aimed to quantify the signal characteristics of photons interacting with optically active media, in terms of enhanced contrast and potential discriminant descriptors, without excluding expansion of the same metrics to other areas of research.
Network resource allocation of e-learning videos for scalable video delivery using content-based compression
Pande A., Verma A., Mittal A., Agrawal A.
Q4
International Journal of Signal and Imaging Systems Engineering,
2010,
цитирований: 1,
open access
,
doi.org,
Abstract
,
Multimedia QoS is a big concern, especially for the scarce resource networks. This paper deals with the issue of intelligent transmission of important segments of the video sequence over the network. An estimate of the available network bandwidth is obtained, which is then distributed optimally between the different frame constituents based on their relative importance and motion by the bandwidth allocation module. Colour Embedded Zerotree Wavelet (CEZW) coding is used to obtain a scalable bitstream that provides dynamic response to changing network conditions. This scheme is robust and operational for all low motion videos with identifiable VOs.
Performance of auto-configuring RBF networks trained with significant patterns
Nagabhushan T.N., Padma S.K., Prasad B.
Q4
International Journal of Signal and Imaging Systems Engineering,
2009,
цитирований: 1,
open access
,
doi.org,
Abstract
,
This paper presents two new ideas to improve the performance of Radial Basis Function (RBF) networks. In the first instance, we choose a set of patterns for training, which are closer to decision boundaries, from different classes of training samples that constitute the input space. We call those set of patterns significant patterns and discuss their selection process from the given data set. Secondly, we use these significant patterns to train Adaptive incremental learning RBF network and Resource Allocating Network (RAN). The learning curves and generalisation characteristics of the generated RBF networks are presented. The performance results are discussed.
Infrasound signal classification using parallel RBF Neural Networks
Ham F.M., Rekab K., Acharyya R., Lee Y.C.
Q4
International Journal of Signal and Imaging Systems Engineering,
2009,
цитирований: 7,
open access
,
doi.org,
Abstract
,
A classification system is presented for discriminating different infrasound events using a Parallel Neural Network Classifier Bank (PNNCB) consisting of Radial Basis Function (RBF) networks. The classifier architecture and the pre-processing steps are unique and yield results that are superior when compared with those previously reported. Three-dimensional Receiver Operating Characteristic (ROC) curves are used to optimally set the output thresholds at each of the classification modules in the PNNCB for a particular class. A process is presented that enables optimising certain parameters of the classifier system. An application of the classification system to four infrasound classes is presented along with performance results and associated Confidence Intervals (CIs).
Variational phase unwrapping and wavelet denoising of interferometric SAR data using Mumford-Shah framework
Sartor K., Tenali G.B., Kozaitis S.P.
Q4
International Journal of Signal and Imaging Systems Engineering,
2008,
цитирований: 1,
open access
,
doi.org,
Abstract
,
We introduce a variational approach to wavelet denoising and phase unwrapping of interferometric SAR data using the Mumford-Shah framework. The Mumford-Shah variational framework can handle discontinuities in the scene besides unifying the phase unwrapping and denoising in one mathematical formalism.
Improved feature detection in ECG signals through denoising
Kozaitis S.P.
Q4
International Journal of Signal and Imaging Systems Engineering,
2008,
цитирований: 0,
open access
,
doi.org,
Abstract
,
We identified important features in ECG signals after using a third-order, correlation-based method for denoising. Using a small sample of test and actual clean ECG signals, we found that the third-order method for denoising preserved the values and location of important peaks better than a conventional second-order wavelet-based method for denoising.
Using denoising to improve image fusion performance
Ouendeno M., Kozaitis S.P.
Q4
International Journal of Signal and Imaging Systems Engineering,
2008,
цитирований: 0,
open access
,
doi.org,
Abstract
,
We applied an image fusion approach that uses different wavelet transforms for the forward and reconstruction transforms to efficiently compact energy for improved reconstruction. In addition, we used denoising to reduce the error induced by this approach. We found that using such an approach generally increases the Average Relative Entropy (ARE) of the fused result when compared to a conventional image fusion method.
Aqueous insulin and alcohol macromolecules and multiphasic molecular systems with enhanced photophysical signal characteristics and multifunctional properties
Giakos G.C.
Q4
International Journal of Signal and Imaging Systems Engineering,
2008,
цитирований: 1,
open access
,
doi.org,
Abstract
,
This study presents a theoretical formalism accompanied with experimental evidence which demonstrates that aqueous insulin macromolecules, and complex metaphase macromolecules exhibit enhanced photophysical and metamaterial-like characteristics leading to an overall enhancement of the interacting optical fields. Clathrate-like structures, filled with different index of refraction water, introduce a 'lensing' or guiding effects of the incident photons. Changing the ratio between hydrophobic and hydrophilic surfaces of multiphasic composites by several mechanisms give rise to an enhanced index of refraction contrast. The outcome of this study opens new horizons in the exploring of applications related to molecular imaging, nanophotonics, and optical devices.
Failure precursor detection in complex electrical systems using symbolic dynamics
Patankar R.P., Rajagopalan V., Ray A.
Q4
International Journal of Signal and Imaging Systems Engineering,
2008,
цитирований: 4,
open access
,
doi.org,
Abstract
,
Failures in a plant's electrical components are a major source of performance degradation and plant unavailability. In order to detect and monitor failure precursors and anomalies early in electrical systems, we have developed a signal processing method that can detect and map patterns to an anomaly measure. Application of this technique for failure precursor detection in electronic circuits resulted in robust detection. This technique was observed to be superior to conventional pattern recognition techniques such as neural networks and principal component analysis for anomaly detection. Moreover, this technique based on symbolic dynamics offers superior robustness due to averaging associated with experimental probability calculations. It also provided a monotonically increasing smooth anomaly plot which was experimentally repeatable to a remarkable accuracy.
