Preferred Language
Articles
/
zhiHlJUBVTCNdQwCuXxB
Deep Learning and Fusion Techniques for High-Precision Image Matting:
...Show More Authors

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

View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed Jun 27 2018
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Production of High Surface Area Activated Carbon from Grass (Imperata)
...Show More Authors

In this work the production of activated carbon (AC) from Imperata is done by microwave assisted Potassium hydroxide (KOH) activation and using this activated carbon for the purpose of the uptake of amoxicillin (AMX) by adsorption process from aqueous solution. The effects for irradiation power (450-800W), irradiation time (6-12min) as well as impregnation ratio (0.5-1 g/g) on the AMX uptake and yield AMX uptake at an initial concentration of AMX (150 mg/g). The optimum conditions were 700 W irradiation power, 10 min time of irradiation, as well as 0.8 g/g impregnation ratio with 14.821% yield and 12.456 mg/g AMX uptake. Total volume of hole and the area of the surface (BET) are 0.3027 m³/g, and 552.7638 m²/g respectively. The properti

... Show More
View Publication Preview PDF
Publication Date
Sat Dec 30 2017
Journal Name
Al-khwarizmi Engineering Journal
Design & Implementation of High Switching & Low Phase Noise Frequency Synthesizer
...Show More Authors

This research  describes the design & implementation of frequency synthesizer using single loop Phase lock loop with the following specifications: Frequency range (1.5 – 2.75) GHz,Step size (1 MHz), Switching time 36.4 µs, & phase noise @10 kHz = -92dBc & spurious -100 dBc

  The development in I.C. technology provide the simplicity in the design of frequency synthesizer because it implements the phase frequency detector(PFD) , prescalar &  reference divider in single chip. Therefore our system consists of  a single chip contains (low phase noise PFD, charge pump, prescalar  & reference divider), voltage controlled oscillator , loop filter & reference oscillator. The single chip

... Show More
View Publication Preview PDF
Publication Date
Thu Feb 01 2024
Journal Name
Ain Shams Engineering Journal
Performance enhancement of high degree Charlier polynomials using multithreaded algorithm
...Show More Authors

View Publication
Scopus (4)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Fri Jul 03 2020
Journal Name
Agriculture
Potato Phosphorus Response in Soils with High Value of Phosphorus
...Show More Authors

Phosphorus (P) is an element that is potatoes require in large amounts. Soil pH is a crucial factor impacting phosphorus availability in potato production. This study was conducted to evaluate the influence of P application rates on the P efficiency for tuber yield, specific gravity, and P uptake. Additionally, the relationship between soil pH and total potato tuber yield was determined. Six rates of P fertilization (0–280 kg P ha−1) were applied at twelve different sites across Northern Maine. Yield parameters were not responsive to P application rates. However, regression analysis showed that soil pH was significantly correlated with total potato tuber yield(R2 = 0.38). Sites with soil pH values < 6 had total tuber yields,

... Show More
View Publication
Crossref (27)
Crossref
Publication Date
Wed Apr 30 2025
Journal Name
Iraqi Journal Of Science
Numerical Simulation of Solar Granulation Dynamics Using Optical Correction Techniques
...Show More Authors

High-resolution imaging of celestial bodies, especially the sun, is essential for understanding dynamic phenomena and surface details. However, the Earth's atmospheric turbulence distorts the incoming light wavefront, which poses a challenge for accurate solar imaging. Solar granulation, the formation of granules and intergranular lanes on the sun's surface, is important for studying solar activity. This paper investigates the impact of atmospheric turbulence-induced wavefront distortions on solar granule imaging and evaluates, both visually and statistically, the effectiveness of Zonal Adaptive Optics (AO) systems in correcting these distortions. Utilizing cellular automata for granulation modelling and Zonal AO correction methods,

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Sun Dec 30 2018
Journal Name
Baghdad Science Journal
Geomorphological Mapping of Razzaza–Habbaria Area using Remote Sensing Techniques
...Show More Authors

Landforms on the earth surface are so expensive to map or monitor. Remote Sensing observations from space platforms provide a synoptic view of terrain on images. Satellite multispectral data have an advantage in that the image data in various bands can be subjected to digital enhancement techniques for highlighting contrasts in objects for improving image interpretability. Geomorphological mapping involves the partitioning of the terrain into conceptual spatial entities based upon criteria. This paper illustrates how geomorphometry and mapping approaches can be used to produce geomorphological information related to the land surface, landforms and geomorphic systems. Remote Sensing application at Razzaza–Habbaria area southwest of Razz

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Sep 03 2018
Journal Name
Al-academy
Transformer Technician in Pop Art (Study in techniques of show)
...Show More Authors

The popular art movement emerged in the mid-fifties in Britain in parallel with its appearance in America.. It was linked to contemporary social reality and what distinguishes this art is the most sophisticated and less aesthetic means and the most blatant in the field of media, ie back to the image used in the media, journalism, magazines, television and photo Which reflect the reality of the neutral artist. This research included the methodological framework represented by the research problem that emerged from pop art as a new experimental vision that emerged in the twentieth century and the importance of the research and its objectives and limits and the definition of terms. The theoretical framework dealt with evolution Technology,

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat May 01 2021
Journal Name
Journal Of Physics: Conference Series
The Prediction of COVID 19 Disease Using Feature Selection Techniques
...Show More Authors
Abstract<p>COVID 19 has spread rapidly around the world due to the lack of a suitable vaccine; therefore the early prediction of those infected with this virus is extremely important attempting to control it by quarantining the infected people and giving them possible medical attention to limit its spread. This work suggests a model for predicting the COVID 19 virus using feature selection techniques. The proposed model consists of three stages which include the preprocessing stage, the features selection stage, and the classification stage. This work uses a data set consists of 8571 records, with forty features for patients from different countries. Two feature selection techniques are used in </p> ... Show More
View Publication Preview PDF
Scopus (31)
Crossref (24)
Scopus Crossref
Publication Date
Sat Jan 01 2022
Journal Name
Latin American Journal Of Solids And Structures
Peak Ground Acceleration Models Predictions Utilizing Two Metaheuristic Optimization Techniques
...Show More Authors

Scopus (15)
Crossref (15)
Scopus Clarivate Crossref
Publication Date
Sat Jan 01 2022
Journal Name
Latin American Journal Of Solids And Structures
Peak Ground Acceleration Models Predictions Utilizing Two Metaheuristic Optimization Techniques
...Show More Authors

View Publication
Crossref (15)
Crossref