In the image processing’s field and computer vision it’s important to represent the image by its information. Image information comes from the image’s features that extracted from it using feature detection/extraction techniques and features description. Features in computer vision define informative data. For human eye its perfect to extract information from raw image, but computer cannot recognize image information. This is why various feature extraction techniques have been presented and progressed rapidly. This paper presents a general overview of the feature extraction categories for image.

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class

This research was designed to study the effect of water and alcoholic crude extracts of Calvatia craniiformis in vitro and in vivo On the other hand this study tested the toxic effect of both extracts in normal laboratory mice. The results showed that water and alcoholic extracts relatively have an acute toxic effect in mice in respect to LD50 (85 mg/kg, and 177mg/kg respectively). However the chronic toxicity of water extract at three different concentration (50, 75, 100 mg/kg) and alcoholic extract at concentrations of (100, 150, 200 mg/kg) was investigated in normal mice by (I.P) administration for 30 days alternatively and one drag in 48 hours . The results indicated significant effect (P ? 0.01) increasing in (MI) and (BI) of bone mar

 Prepared zeolite type A was used for theremoval of cesium ions from aqueous solution. The experimental data were analyzed by Langmuir, Freundlich isotherms. Various parameters, such as contact time, zeolite weight, pH, and initial concentration, were studied. The results indicated that the highest removal efficiency was95.53% at (2h time, 0.04 g weight, and pH=6.8). The results also showed that the Freundlic model fits well with the experimental results and is better than the Langmuir model.

This study exposed to use the liquid whey (which was produced from of soft cheese processed) partially or completely instead of milk in fatty cake, this whey residue is still not used, instead it is thrown in rivers which effect different environment and economic problems. Different concentrations was used (25% , 50% , 75% , and 100%) of whey in baked cake , Volume , height and other different properties ( panel taste ) was studied too . Sensory evaluation results showed that an improved in all the character of the baked cake was happen by the used of 25% and 50% of the whey in comparison with the control treatment, the 75% replacement showed a decrease in appearance , texture and tenderness , while the degrees of color and fla

This paper introduces the Multistep Modified Reduced Differential Transform Method (MMRDTM). It is applied to approximate the solution for Nonlinear Schrodinger Equations (NLSEs) of power law nonlinearity. The proposed method has some advantages. An analytical approximation can be generated in a fast converging series by applying the proposed approach. On top of that, the number of computed terms is also significantly reduced. Compared to the RDTM, the nonlinear term in this method is replaced by related Adomian polynomials prior to the implementation of a multistep approach. As a consequence, only a smaller number of NLSE computed terms are required in the attained approximation. Moreover, the approximation also converges rapidly over a