General Background: Deep image matting is a fundamental task in computer vision, enabling precise foreground extraction from complex backgrounds, with applications in augmented reality, computer graphics, and video processing. Specific Background: Despite advancements in deep learning-based methods, preserving fine details such as hair and transparency remains a challenge. Knowledge Gap: Existing approaches struggle with accuracy and efficiency, necessitating novel techniques to enhance matting precision. Aims: This study integrates deep learning with fusion techniques to improve alpha matte estimation, proposing a lightweight U-Net model incorporating color-space fusion and preprocessing. Results: Experiments using the AdobeComposition-1k dataset demonstrate superior performance compared to traditional methods, achieving higher accuracy, faster processing speed, and improved boundary preservation. Novelty: The proposed model effectively combines deep learning with fusion techniques, enhancing matting quality while maintaining robustness across various environmental conditions. Implications: These findings highlight the potential of integrating fusion techniques with deep learning for image matting, offering valuable insights for future research in automated image processing applications, including augmented reality, gaming, and interactive video technologies. Highlights: Better Precision: Fusion techniques enhance fine detail preservation. Faster Processing: Lightweight U-Net improves speed and accuracy. Wide Applications: Useful for AR, gaming, and video processing. Keywords: Deep image matting, computer vision, deep learning, fusion techniques, U-Net
Attention-Deficit Hyperactivity Disorder (ADHD), a neurodevelopmental disorder affecting millions of people globally, is defined by symptoms of hyperactivity, impulsivity, and inattention that can significantly affect an individual's daily life. The diagnostic process for ADHD is complex, requiring a combination of clinical assessments and subjective evaluations. However, recent advances in artificial intelligence (AI) techniques have shown promise in predicting ADHD and providing an early diagnosis. In this study, we will explore the application of two AI techniques, K-Nearest Neighbors (KNN) and Adaptive Boosting (AdaBoost), in predicting ADHD using the Python programming language. The classification accuracies obtained w
... Show MoreThis research aims to solve the nonlinear model formulated in a system of differential equations with an initial value problem (IVP) represented in COVID-19 mathematical epidemiology model as an application using new approach: Approximate Shrunken are proposed to solve such model under investigation, which combines classic numerical method and numerical simulation techniques in an effective statistical form which is shrunken estimation formula. Two numerical simulation methods are used firstly to solve this model: Mean Monte Carlo Runge-Kutta and Mean Latin Hypercube Runge-Kutta Methods. Then two approximate simulation methods are proposed to solve the current study. The results of the proposed approximate shrunken methods and the numerical
... Show MoreThe aim of the research is to identify the cognitive method (rigidity flexibility) of third-stage students in the collage of Physical Education and Sports Sciences at The University of Baghdad, as well as to recognize the impact of using the McCarthy model in learning some of skills in gymnastics, as well as to identify the best groups in learning skills, the experimental curriculum was used to design equal groups with pre test and post test and the research community was identified by third-stage students in academic year (2020-2021), the subject was randomly selected two divisions after which the measure of cognitive method was distributed to the sample, so the subject (32) students were distributed in four groups, and which the pre te
... Show MoreThe study aims at identifying the sources of information and explaining their role in e-learning from the viewpoint of the Iraqi college students. The researchers relied on the descriptive method of the survey method to collect data and know the point of view of undergraduate students from the Department of Information in the College of Arts / Tikrit University and the Department of Quranic Studies at the College of Arts / University of Baghdad. The questionnaire was used as an instrument of the study, the research sample is (120) students; each section has (60) male and female students. The study concluded that there are many types and forms of information sources that students receive through electronic educational platforms from text con
... Show MoreIn this paper, a method for hiding cipher text in an image file is introduced . The
proposed method is to hide the cipher text message in the frequency domain of the image.
This method contained two phases: the first is embedding phase and the second is extraction
phase. In the embedding phase the image is transformed from time domain to frequency
domain using discrete wavelet decomposition technique (Haar). The text message encrypted
using RSA algorithm; then Least Significant Bit (LSB) algorithm used to hide secret message
in high frequency. The proposed method is tested in different images and showed success in
hiding information according to the Peak Signal to Noise Ratio (PSNR) measure of the the
original ima
This paper introduces an innovative method for image encryption called "Two-Fold Cryptography," which leverages the Henon map in a dual-layer encryption framework. By applying two distinct encryption processes, this approach offers enhanced security for images. Key parameters generated by the Henon map dynamically shape both stages of encryption, creating a sophisticated and robust security system. The findings reveal that Two-Fold Cryptography provides a notable improvement in image protection, outperforming traditional single-layer encryption techniques.
In this paper the behavior of the quality of the gradient that implemented on an image as a function of noise error is presented. The cross correlation coefficient (ccc) between the derivative of the original image before and after introducing noise error shows dramatic decline compared with the corresponding images before taking derivatives. Mathematical equations have been constructed to control the relation between (ccc) and the noise parameter.