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

Abstract

  Bivariate time series modeling and forecasting have become a promising field of applied studies in recent times. For this purpose, the Linear Autoregressive Moving Average with exogenous variable ARMAX model is the most widely used technique over the past few years in modeling and forecasting this type of data. The most important assumptions of this model are linearity and homogenous for random error variance of the appropriate model. In practice, these two assumptions are often violated, so the Generalized Autoregressive Conditional Heteroscedasticity (ARCH) and (GARCH) with exogenous varia

Protection of the oil pipelineswhich extracted from the wells was found to shut the well and prevent the leakage of oil when broken using safety valve. This valve is automatically activated by loss of pressure between the well and pipelines, which take the pressure, signal from hydraulic pressure sensor through pressure control valve which has constant or variable value but it is regulated manually. The manual regulatory process requires the presence of monitoring workers continuously near the wells which are always found in remote areas. In this paper, a smart system has been proposed that work with proportional pressure control valve and also electronic pressure sensor through Arduino controller, which is programmed in a way that satisfie

In all applications and specially in real time applications, image processing and compression plays in modern life a very important part in both storage and transmission over internet for example, but finding orthogonal matrices as a filter or transform in different sizes is very complex and importance to using in different applications like image processing and communications systems, at present, new method to find orthogonal matrices as transform filter then used for Mixed Transforms Generated by using a technique so-called Tensor Product based for Data Processing, these techniques are developed and utilized. Our aims at this paper are to evaluate and analyze this new mixed technique in Image Compression using the Discrete Wavelet Transfo

ABSTRACT: BACKGROUND: Breast reduction for mammary hypertrophy is a highly effective procedure with high degree of patient satisfaction. There are many methods of breast reduction which involve removal of excess tissue with reshaping of overlying skin while maintaining a viable nipple areolar complex. OBJECTIVE: The purpose of this study is to evaluate the use of the superomedial technique as an effective method for reduction mammoplasty. PATIENTS AND METHODS: A total of 30 patients underwent reduction mammoplasty by utilizing superomedial pedicle technique between 2010 and 2013. Those patients were evaluated postoperatively in terms of their aesthetic and functional satisfaction, viability of nipple – areolar complex and nipple sensory p

Multiple linear regressions are concerned with studying and analyzing the relationship between the dependent variable and a set of explanatory variables. From this relationship the values of variables are predicted. In this paper the multiple linear regression model and three covariates were studied in the presence of the problem of auto-correlation of errors when the random error distributed the distribution of exponential. Three methods were compared (general least squares, M robust, and Laplace robust method). We have employed the simulation studies and calculated the statistical standard mean squares error with sample sizes (15, 30, 60, 100). Further we applied the best method on the real experiment data representing the varieties of