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

Artificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le

The study focuses on assessment of the quality of some image enhancement methods which were implemented on renal X-ray images. The enhancement methods included Imadjust, Histogram Equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE). The images qualities were calculated to compare input images with output images from these three enhancement techniques. An eight renal x-ray images are collected to perform these methods. Generally, the x-ray images are lack of contrast and low in radiation dosage. This lack of image quality can be amended by enhancement process. Three quality image factors were done to assess the resulted images involved (Naturalness Image Quality Evaluator (NIQE), Perception based Image Qual

Artificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le

The primary purpose of the present research was to study the effect of polyvinyl chloride (PVC) powder content on ultrasonic wave velocity in PVC/Epoxy composites. The second part is concerned with the relations of dynamic elastic moduli with the ultrasonic wave velocities, to determine how ultrasonic waves can affect them.
Experimental data have been obtained using the sonic viewer (model -5217 A) device to generate two types of waves, longitudinal waves of frequency 63 kHz and transverse waves of frequency 33 kHz and to measure the transit time required for those waves to travel through individual sample.
The experimental results have shown that the propagation of the ultrasonic velocity increases directly with PVC content in the

In this research, the mechanical properties of natural rubber blends in different proportions (70:30, 85:15, 100: 0 55:45 and phr) was studied through the use of two types of fillers (carbon black and titanium dioxide Nano) which show through tests conducted on the prepared models that increase fillers content which leads to improve the tensile properties (tensile strength, elastic modulus, elongation, hardness and compressibility). As shown by the results that the presence of polypropylene (PP) in the mix combination works to reduce the degree of intumescent and increase its content in the composition of mixtures which leads to get a great resistance to chemicals (acids, bases and oils).

AlO-doped ZnO nanocrystalline thin films from with nano crystallite size in the range (19-15 nm) were fabricated by pulsed laser deposition technique. The reduction of crystallite size by increasing of doping ratio shift the bandgap to IR region the optical band gap decreases in a consistent manner, from 3.21to 2.1 eV by increasing AlO doping ratio from 0 to 7wt% but then returns to grow up to 3.21 eV by a further increase the doping ratio. The bandgap increment obtained for 9% AlO dopant concentration can be clarified in terms of the Burstein–Moss effect whereas the aluminum donor atom increased the carrier's concentration which in turn shifts the Fermi level and widened the bandgap (blue-shift). The engineering of the bandgap by low

Thin films of ZnSxSe1-x with different sulfide content(x)
(0, 0.02, 0.04, 0.06, 0.8, and 0.1), thickness (t) (0.3, 0.5, and 0.7 μm) and annealing temperature (Ta) (R.T 373 and 423K) were fabricated by thermal evaporating under vacuum of 10-5 Toor on glass substrate. The results show that the increasing of sulfide content (x)and annealing temperature lead to decrease the d.c conductivity σDC of and concentration of charge carriers (nH) but increases the activation energy (Ea1,Ea2), while the increasing of t increases σDC and nH but decrease (Ea1,Ea2). The results were explained in different terms