No abstract

Most image processing applications use edge detection to extract information as a preliminary step to object segmentation and feature extraction. Edge accuracy is one of the edge detector challenges; The current work presents the design of the fractional-order Sobel filters based on Yi_Fei-1 to Yi_Fei-5. A comparison among the proposed filters has been implemented for edge detection based on a supervised assessment, using mean square error, misclassification error, and symmetric distance. Many images with their ground truths have been used in the evaluation. Results showed that the fractional-order of Sobel-based Yi_Fei-2 has the best edge map among the proposed filters.

The main <span>problems that encounter the traffic light detection algorithm have become a handicap to the performance of the algorithms. Problems associated with the change of sign color due to bad weather and illumination changes of sunlight make the detection hard task. In the current work, we discuss these problems and propose a new idea of an efficient real time color sign recognition that relies only on color information. The proposed approach is based on building a red-model in hypothetical red, green, blue (RGB) cube using a large database of traffic signs. The segmentation has been implemented on the traffic signs that hold red color only as an example to illustrate the proposed approach. Results showed that the proposed algorithm is accurate as well as the computational cost is reduced.</span>

Background: Coronavirus (COVID-19) has appeared first time in Wuhan, China, as an acute respiratory syndrome and spread rapidly. It has been declared a pandemic by the WHO. Thus, there is an urgent need to develop an accurate computer-aided method to assist clinicians in identifying COVID-19-infected patients by computed tomography CT images. The contribution of this paper is that it proposes a pre-processing technique that increases the recognition rate compared to the techniques existing in the literature. Methods: The proposed pre-processing technique, which consists of both contrast enhancement and open-morphology filter, is highly effective in decreasing the diagnosis error rate. After carrying out pre-processing, CT images are fed to a 15-layer convolution neural network (CNN) as deep-learning for the training and testing operations. The dataset used in this research has been publically published, in which CT images were collected from hospitals in Sao Paulo, Brazil. This dataset is composed of 2482 CT scans images, which include 1252 CT scans of SARS-CoV-2 infected patients and 1230 CT scans of non-infected SARS-CoV-2 patients. Results: The proposed detection method achieves up to 97.8% accuracy, which outperforms the reported accuracy of the dataset by 97.3%. Conclusion: The performance in terms of accuracy has been improved up to 0.5% by the proposed methodology over the published dataset and its method.