Wyniki wyszukiwania - BazTech

1

Automated diagnosis of COVID stages from lung CT images using statistical features in 2-dimensional flexible analytic wavelet transform

Patel Rajneesh Kumar, Kashyap Manish

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

829--841

EN

TheCOVID-19 epidemic has been causing a global problem since December 2019.COVID-19 is highly contagious and spreads rapidly throughout the world. Thus, early detection is essential. The progression of COVID-19 lung illness has been demonstrated to be aided by chest imaging. The respiratory system is the most vulnerable component of the human body to the COVID virus. COVID can be diagnosed promptly and accurately using images from a chest X-ray and a computed tomography scan. CT scans are preferred over X-rays to rule out other pulmonary illnesses, assist venous entry, and pinpoint any new heart problems. The traditional and trending tools are physical, time-inefficient, and not more accurate. Many techniques for detecting COVID utilizing CT scan images have recently been developed, yet none of them can efficiently detect COVID at an early stage. We proposed a two-dimensional Flexible analytical wavelet transform (FAWT) based on a novel technique in this work. This method is decomposed pre-processed images into sub-bands. Then statistical-based relevant features are extracted, and principal component analysis (PCA) is used to identify robust features. After that, robust features are ranked with the help of the Student’s t-value algorithm. Finally, features are applied to Least Square-SVM (RBF) for classification. According to the experimental outcomes, our model beat state-of-the-art approaches for COVID classification. This model attained better classification accuracy of 93.47%, specificity 93.34%, sensitivity 93.6% and F1-score 0.93 using tenfold cross-validation.

2

An efficient algorithm for adaptive total variation based image decomposition and restoration

Liu X., Huang L.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 2

405--415

EN

With the aim to better preserve sharp edges and important structure features in the recovered image, this article researches an improved adaptive total variation regularization and H-1 norm fidelity based strategy for image decomposition and restoration. Computationally, for minimizing the proposed energy functional, we investigate an efficient numerical algorithm—the split Bregman method, and briefly prove its convergence. In addition, comparisons are also made with the classical OSV (Osher–Sole–Vese) model (Osher et al., 2003) and the TV-Gabor model (Aujol et al., 2006), in terms of the edge-preserving capability and the recovered results. Numerical experiments markedly demonstrate that our novel scheme yields significantly better outcomes in image decomposition and denoising than the existing models.

3

Wavelet-like decomposition based on filtering in domains of discrete trigonometric transforms : case study

Korohoda R., Dąbrowski A.

Elektronika : konstrukcje, technologie, zastosowania

|

2011

|

Vol. 52, nr 5

85-88

EN

In this paper a new wavelet-like decomposition-reconstruction scheme of signals is proposed and experimentally verified. Instead of typical filters, i.e., those referring to the Fourier representation, half-band filters based on the discrete trigonometric transforms (DTTs) are used. A comparison with the standard approach has been carried out and the differences are indicated. A perfect reconstruction condition is formulated for the considered filtering systems and illustrated with an example. The comparative study is supported by two examples of one level 2D image decomposition.

PL

W tym artykule przedstawiono zweryfikowaną doświadczalnie propozycję nowego zafalowaniowo- (falkowo-) podobnego schematu dekompozycji-rekonstrukcji sygnałów. W miejsce typowych filtrów, tzn. związanych z reprezentacją Fouriera, zastosowano filtry półpasmowe oparte na dyskretnych transformacjach trygonometrycznych (ang. DTTs). Wyniki porównano z ujęciem klasycznym oraz wskazano różnice. Sformułowano warunek doskonałej rekonstrukcji dla przypadku rozważanych filtrów i zilustrowano go przykładem. Studium porównawcze zostało poparte dwoma przykładami jednostopniowej dwuwymiarowej (2D) dekompozycji obrazu.

4

New Fast Principal Component Analysis For Real-Time Face Detection

El-Bakry H. M.

Machine Graphics and Vision

|

2009

|

Vol. 18, No. 4

405-425

EN

Principal component analysis (PCA) has various important applications, especially in pattern detection, such as face detection and recognition. In real-time applications, the response time must be as short as possible. In this paper, a new implementation of PCA for fast face detection is presented. Such implementation relies on performing cross-correlation in the frequency domain between the input image and eigenvectors (weights). Furthermore, this approach is developed to reduce the number of computation steps required by fast PCA. The "divide and conquer" principle is applied through image decomposition. Each image is divided into smaller-size sub-images, and then each of them is tested separately using a single fast PCA processor. In contrast to using only fast PCA, the speed-up ratio increases with the size of the input image when using fast PCA and image decomposition. Simulation results demonstrate that the proposed algorithm is faster than conventional PCA. Moreover, experimental results for different images show its good performance. The proposed fast PCA increases the speed of face detection, and at the same time does not affect the performance or detection rate.

5

Generalized convolution for extraction of image features in the primary domain

Korohoda P., Dąbrowski A.

Machine Graphics and Vision

|

2008

|

Vol. 17, No. 3

279-297

EN

In this paper, a class of techniques for flexible extraction of image features is proposed. These techniques are based on the convolution type filtering in the primary domain. The mentioned flexibility results from the fact that any discrete transform suitable for the analysis of desired image features (as, e.g., the Karhunen-Loeve transform) may be designed and the filter with the assumed transform-domain properties may be applied straightforwardly in the image (i.e., primary) domain. The proposed solution creates an entirely new approach to image filtering. After recalling the concept referred to by the authors as generalized convolution and extending it to the 2-dimensional case, the theoretical results are illustrated with several examples based on filtering of the test image with filters designed in the Haar, Hadamard and the DCT II domains. Finally, it is explained how the proposed approach indicates several possible ways for further developments towards the design of image-and-feature based tools.

6

Variables applied in a NMR image decomposition with the aid of GCCA

Grzegorek M.

Journal of Medical Informatics & Technologies

|

2008

|

Vol. 12

183--187

EN

The paper describes the influence of variable selection on an image decomposition. A NMR image is a source of a set of variables describing pixels of the image: gray level, gradient magnitude and seven variables derived from gradient magnitudes of neighbouring pixels. A selection of the variables is the essence of the matter at this stage of the image processing. Two suggestions are proposed and tested: a normalization of gradient magnitude of the pixel by dividing it by a value of the gray level, and development of a nonlinear sequence of thresholds which are used in comparison of adjacent pixels.

7

Decomposition of medical image based on grade multivariate methodology

Grzegorek M.

Biocybernetics and Biomedical Engineering

|

2007

|

Vol. 27, no. 4

29-48

EN

The paper presents disjoint decomposition of the set of pixels of a NMR image and also of its fragment suggested as interesting by a medical consultant. Each pixel is described by the value of gray level gl, gradient module gm and items constructed on the basis of gm and gradient modules of adjacent pixels. The obtained dataset with rows corresponding to pixels and columns corresponding to variables is then processed by the algorithm called GCCA (Grade Correspondence Cluster Analysis). This rearranges the initial ordering of pixels (and also of variables) and then divides the set of rows into a chosen number of clusters. Pixels in each cluster are visualized as a separate subimage. The resulting decomposition (an ordered sequence of sub images) depends on the choice of a threshold parameter b which strongly influences the comparison of gm with gradient modules in pixel's neighborhood. It is shown how b should be selected to specify the edge of the lateral ventricle and to investigate homogeneity of gm's neighborhoods in the area indicated for the consultant.

8

Application of grade methods to medical data: new examples

Pleszczyńska E.

Biocybernetics and Biomedical Engineering

|

2007

|

Vol. 27, no. 3

77-93

EN

Data exploration and visualization based on the Grade Correspondence Analysis is waiting for the final recognition by the statistical community. Its main points will be briefly summarized in the Introduction and Section 2 with reference to the contemporary use of Gini-Lorenz concepts and to contemporary visual approaches in analyzing large multivariate datasets. The summary will be illustrated by three recent applications to medical data: Eurostat data on self-perceived health, questionnaire data from the Children’s Memorial Health Institute in Poland and a set of data specially invented to describe NMR human brain image.

9

Automatic human face recognition using modular neural networks

El-Bakry H. M.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 1

47-73

EN

In this paper, a fast biometric system for personal identification through face recognition is introduced. In the detection phase, a fast algorithm for face detection is combined with cooperative modular neural networks (MNNs) to enhance the performance of the detection process. A simple design for cooperative modular neural networks is described to solve this problem by dividing the data into three groups. Furthermore, a new faster face detection approach is presented through image decomposition into many sub-images and applying cross correlation in frequency domain between each sub-image and the weights of the hidden layer. For the recognition phase, a new concept for rotation invariant based on Fourier descriptors and neural networks is presented. Although, the magnitude of the Fourier descriptors is translation invariant, there is no need for scaling or translation invariance. This is because the face sub-image (20 x 20 pixels) is segmented from the whole image during the detection process. The feature extraction algorithm based on Fourier descriptors is modified to reduce the number of neurons is the hidden layer. The second stage extracts wavelet coefficients of the resulted Fourier descriptors before application to neural network. The final vector is fed to a neural net for face classification. Moreover, a modified hierarchy soft decision tree of neural networks is introduced for face recignition. Compared with previous results, the proposed algorithm shown good performance on recognizing human faces with glass, bread, rotation, scaling, occlusion, noise, or change in illumination. Also, the response time is reduced.