يعد تصنيف الجسم المتداخل أحد التحديات الرئيسية التي يواجهها الباحثون الذين يعملون في اكتشاف الأشياء والتعرف عليها. معظم الخوارزميات المتاحة التي تم تطويرها قادرة فقط على تصنيف أو التعرف على الأشياء التي تكون إما منفصلة بشكل فردي عن بعضها البعض أوجسم واحد في مشهد (مشاهد) ، ولكن لا تتداخل مع اجسام أدوات المطبخ. في هذا المشروع ، تم اقتراح خوارزميات Faster R-CNN و YOLOv5 لاكتشاف وتصنيف جسم متداخل في منطقة المطبخ. تم تطبيق YOLOv5 و Faster R-CNN على االاجسام المتداخلة حيث من المتوقع أن يتمكن المرشح أو النواة من فصل االجسم المتداخل في الطبقة المخصصة لتطبيق النماذج. تم استخدام قاعدة بيانات الصور المعيارية لأدوات المطبخ وأدوات المطبخ المتداخلة من الإنترنتااجسام مرجعية أساسية. تم تعيين مجموعات التقييم والتدريب / التحقق عند 20٪ و 80٪ على التوالي. قام هذا المشروع بتقييم أداء هذه التقنيات وتحليل نقاط قوتها وسرعاتها بناءً على الدقة والدقة ودرجةF1. خلصت نتائج التحليل في هذا المشروع إلى أن YOLOv5 ينتج مربعات إحاطة دقيقة بينما يكتشف Faster R-CNN المزيد من االاجسام. في بيئة اختبار مماثلة ، يُظهر YOLOv5 أداءً أفضل من خوارزمية R-CNN الأسرع. بعد التشغيل في نفس البيئة، حصل هذا المشروع...

Steganography is one of the method to communicate in a hidden way. In another word, steganography literally means the practice of hiding messages or information within another data. Previous studies have proposed various steganography techniques using different approaches including Least Significant Bit (LSB), Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT). However, different approaches still have its own weaknesses. Therefore image stenography using Knight Tour Algorithm with Least Significant Bit (LSB) technique is presented. The main objective is to improve the security factor in the stego image. Basically, the proposed technique is divided into two parts which are the sender and receiver side. Then, steganalysis which is a type of attack on stenography algorithm is used to detect the secret message in the cover image by the statistical analysis of pixel values. Chi Square Statistical Attach which is one of the type of steganalysis is used to detect these near-equal Po Vs in images and bases the probability of embedding on how close to equal the even pixel values and their corresponding odd pixel values are in the test image. The Knight Tour Algorithm is applied due to the common Least Significant Bit technique that is weak in security and easily decoded by outsider.

Coronavirus often called COVID-19 is a deadly viral disease that causes as a result of severe acute respiratory syndrome coronavirus-2 that needs to be identified especially at its early stages, and failure of which can lead to the further spread of the virus. Despite with the huge success recorded towards the use of the original convolutional neural networks (CNN) of deep learning models. However, their architecture needs to be modified to design their modified versions that can have more powerful feature layer extractors to improve their classification performance. This research is aimed at designing a modified CNN of a deep learning model that can be applied to interpret X-rays to classify COVID-19 cases with improved performance. Therefore, we proposed a modified convolutional neural network (shortened as modification CNN) approach that uses X-rays to classify a COVID-19 case by combining VGG19 and ResNet50V2 along with putting additional dense layers to the combined feature layer extractors. The proposed modified CNN achieved 99.24%, 98.89%, 98.90%, 99.58%, and 99.23% of the overall accuracy, precision, specificity, sensitivity, and F1-Score, respectively. This demonstrates that the results of the proposed approach show a promising classification performance in the classification of COVID-19 cases.

Entropy algorithms are widely applied in signal analysis to quantify the irregularity of data. In the realm of two-dimensional data, their two-dimensional forms play a crucial role in analyzing images. Previous works have demonstrated the effectiveness of one-dimensional increment entropy in detecting abrupt changes in signals. Leveraging these advantages, we introduce a novel concept, two-dimensional increment entropy (IncrEn2D), tailored for analyzing image textures. In our proposed method, increments are translated into two-letter words, encoding both the size (magnitude) and direction (sign) of the increments calculated from an image. We validate the effectiveness of this new entropy measure by applying it to MIX_2D(p) processes and synthetic textures. Experimental validation spans diverse datasets, including the Kylberg dataset for real textures and medical images featuring colon cancer characteristics. To further validate our results, we employ a support vector machine model, utilizing multiscale entropy values as feature inputs. A comparative analysis with well-known bidimensional sample entropy (SampEn_2D) and bidimensional dispersion entropy (DispEn_2D) reveals that IncrEn_2D achieves an average classification accuracy surpassing that of other methods. In summary, IncrEn_2D emerges as an innovative and potent tool for image analysis and texture characterization, offering superior performance compared to existing bidimensional entropy measures.

Detecting fake news through deep learning: a current systematic review