Image compression plays an important role in reducing the size and storage of data while increasing the speed of its transmission through the Internet significantly. Image compression is an important research topic for several decades and recently, with the great successes achieved by deep learning in many areas of image processing, especially image compression, and its use is increasing Gradually in the field of image compression. The deep learning neural network has also achieved great success in the field of processing and compressing various images of different sizes. In this paper, we present a structure for image compression based on the use of a Convolutional AutoEncoder (CAE) for deep learning, inspired by the diversity of human eyes' observation of the different colors and features of images. We propose a multi-layer hybrid system for deep learning using the unsupervised CAE architecture and using the color clustering of the K-mean algorithm to compress images and determine their size and color intensity. The system is implemented using Kodak and Challenge on Learned Image Compression (CLIC) dataset for deep learning. Experimental results show that our proposed method is superior to the traditional compression methods of the autoencoder, and the proposed work has better performance in terms of performance speed and quality measures Peak Signal To Noise Ratio (PSNR) and Structural Similarity Index (SSIM) where the results achieved better performance and high efficiency With high compression bit rates and low Mean Squared Error (MSE) rate the results recorded the highest compression ratios that ranged between (0.7117 to 0.8707) for the Kodak dataset and (0.7191 to 0.9930) for CLIC dataset. The system achieved high accuracy and quality in comparison to the error coefficient, which was recorded (0.0126 to reach 0.0003) below, and this system is onsidered the most quality and accurate compared to the methods of deep learning compared to the deep learning methods of the autoencoder
The issue of image captioning, which comprises automatic text generation to understand an image’s visual information, has become feasible with the developments in object recognition and image classification. Deep learning has received much interest from the scientific community and can be very useful in real-world applications. The proposed image captioning approach involves the use of Convolution Neural Network (CNN) pre-trained models combined with Long Short Term Memory (LSTM) to generate image captions. The process includes two stages. The first stage entails training the CNN-LSTM models using baseline hyper-parameters and the second stage encompasses training CNN-LSTM models by optimizing and adjusting the hyper-parameters of
... Show More
(11)
(8)
(5)
(55)
(50)
Abstract
This study identified the developing of a range of students' geography learning skills and the change in their attitudes toward fieldwork as a consequence of leaning experiences that occurred within a field trip. The sample of the study consisted of (27) students within a special topic course enrolled in Geography Department at Umm Al-Qura University in Saudi Arabia in semester 2, 2018. A range of students' geography learning skills were measured by the skills questionnaire that consisted of 12 geography skills after completing field work. Changes in students' at
... Show Moreimportumt educational institution as (kindergartens) need teachers which qualified ownes modalities in their education for children , as Marzanu method in a way of learning and own methods of crisis management, because the teachers that own those styles of learning ginekindergarten children knowledge and the childrenIeaving based on theMeaing and knowledge and integration of their information, And teachers that earn methods of crisis management provide for the children of the kindergarten security within the educational institution which in turn affect the growth and development of the Child and then abilities, health physical, mental, psychological …etc.., The aims of the current research have identified to recognize: 1- the dimension
... Show MoreResearch Summary The aim of the search for knowledge of the effect generative learning strategy in: 1 - Achievement of the second grade. 2 - Systemic thinking for the second grade students when studying the biology. The study sample increased (60) students distributed into two equal experimental and control groups. Prepare the test of 40 pieces of multiple choice type and prepare a test for systematic thinking according to three skills 1. Understand the relationships between the parts of the systemic form and complement the sentences given 2 - complement the relationships between parts of the systemic form 3. Building the systemic form. It was a search result 1- There is a difference of statistical significance (at level 0.05) between th
... Show MoreThe research aims to identify how to enhance the quality of the human resources, focusing on four dimensions (efficiency, effectiveness, flexibility, and reliability), by adopting an adventure learning method that combines theoretical and applied aspects at the same time, when developing human resources and is applied using information technology, and that Through its dimensions, which are (cooperation, interaction, communication, and understanding), as the research problem indicated a clear deficiency in the cognitive perception of the mechanism of employing adventure learning dimensions in enhancing human resources quality, so the importance of research was to present treatments and proposals to reduce this problem. To achieve
... Show More
(1)
LED is an ultra-lightweight block cipher that is mainly used in devices with limited resources. Currently, the software and hardware structure of this cipher utilize a complex logic operation to generate a sequence of random numbers called round constant and this causes the algorithm to slow down and record low throughput. To improve the speed and throughput of the original algorithm, the Fast Lightweight Encryption Device (FLED) has been proposed in this paper. The key size of the currently existing LED algorithm is in 64-bit & 128-bit but this article focused mainly on the 64-bit key (block size=64-bit). In the proposed FLED design, complex operations have been replaced by LFSR left feedback technology to make the algorithm perform more e
... Show More
(2)
(1)