ملخص البحث :

ملخص البحث :

An edge is where an image’s intensity values rapidly change from low to high-intensity values or vice versa. The edge itself is at the midpoint of this change. Edge detection remains a challenge in computer vision despite recent advances. It cannot be applied to an image with excessive brightness and contrast. This paper produces a new method based on the standard deviation histogram feature to reduce the onerousness. The proposed method aims to prepare the input image for the edge detection approaches by performing a histogram feature extraction. The main characteristics of the proposed approach are simplicity and functionality. The authors utilize twenty MATLAB standard images as well as ADNI brain images. The authors use the Canny edge detection method to defect edges from the proposed method. The authors use edge detection evaluation metrics such as Figure of Merit (FOM), Structural Similarity Index Metric (SSIM), Peak Signal to Noise Ratio (PSNR), and Mean Square Error (MSE) measures for evaluating and justifying edge quality. The experimental results show that the proposed method performs better in visual and statistical edge quality than both classical and fractional-order edge detection methods

ملخص البحث :

One of the most common image operation analyses is the edge detection technique. Edge detection is used for shaping the edge of an image. Also, it is used for enhancing images. This paper presents a new approach to detecting the edge of color image using the Mamdani fuzzy inference classifier based on the Fuzzy Set Membership Function (FSMF). Here, Gaussian Curve Membership Function (GCMF) is used as a FSMF. GCMF is used for each class to assign that class to each pixel. In this approach, two windows/filters are used in size (1x2) and (2x1). Several standard color images are used to test our proposed algorithm (City, Jelly_cc11, Baboon, Lena, and Peppers). In order to parametric evaluation of selected images, Peak Signal Noise Ratio (PSNR) and Mean Square Error (MSE) are considered. However, the performance of our proposed algorithm compared with other well-known approaches (Canny, Prewitt, and Sobel) is somehow very similar but significantly faster.

ملخص البحث :

Image segmentation is a critical step in computer-aided diagnosis that could speed up Leukemia detection. Leukemia is a cancer of the blood that has a reputation for being particularly lethal. Based on the immunohistochemical method, the leukocytes can be manually counted in a stained peripheral blood smear image to detect Acute Lymphoblastic Leukemia (ALL). Regrettably, the manual diagnosis process takes about 3 to 24 hours to complete, which is insufficient. This paper introduced a new and straightforward ALL image segmentation approach based on color image transformation. First, Leukemia, ALL-IDB1, ALL-IDB2, and ALL image datasets were used in this paper. The Leukemia dataset includes 208 ALL-IDB1 and ALL-IDB2 images, while The ALL dataset has 3256 images. Next, we use the HSV model to transform ALL images. In addition, we modified the HSV model by pre-processing the saturation channel for better results. Then, the pre-processed images were segmented based on a fixed threshold. After that, various metrics are utilized to measure the output of the proposed method. Finally, the proposed methodology is compared to currently used benchmarks. The proposed method outperforms previous approaches regarding accuracy, specificity, sensitivity, and time. In addition, results show that the proposed technique improves performance measures significantly.

ملخص البحث :

Coronavirus is considered the first virus to sweep the world in the twenty-first century, it appeared by the end of 2019. It started in the Chinese city of Wuhan and began to spread in different regions around the world too quickly and uncontrollable due to the lack of medical examinations and their inefficiency. So, the process of detecting the disease needs an accurate and quickly detection techniques and tools. The X-Ray images are good and quick in diagnosing the disease, but an automatic and accurate diagnosis is needed. Therefore, this paper presents an automated methodology based on deep learning in diagnosing COVID-19. In this paper, the proposed system is using a convolutional neural network, which is considered one of the mostly prominent techniques used today for its reliability and ability to generate rapid results. The system was trained on a set of X-Ray images taken of the chest area of infected and uninfected people. The CNN structure gave accuracy, Precision, Recall and F-Measure 98%. This model is characterized by its ability to distinguish efficiently and adapt to different cases.