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
This paper proposed a new method to study functional non-parametric regression data analysis with conditional expectation in the case that the covariates are functional and the Principal Component Analysis was utilized to de-correlate the multivariate response variables. It utilized the formula of the Nadaraya Watson estimator (K-Nearest Neighbour (KNN)) for prediction with different types of the semi-metrics, (which are based on Second Derivative and Functional Principal Component Analysis (FPCA)) for measureing the closeness between curves. Root Mean Square Errors is used for the implementation of this model which is then compared to the independent response method. R program is used for analysing data. Then, when the cov
... Show More
(4)
(2)
An experiment was carried out in the vegetables field of Horticulture Department / College of Agriculture / Baghdad University , for the three seasons : spring and Autumn of 2005 , and spring of 2007 , to study the type of gene action in some traits of vegetative and flowery growth in summer squash crosses (4 x 3 = cross 1 , 3 x 7 = cross 2 , 3 x 4 = cross 3 , 3 x 5 = cross 4 , 5 x 1 = cross 5 , 5 x 2 = cross 6). The study followed generation mean analysis method which included to each cross (P1 , P2 , F1 , F2 , Bc1P1 , Bc1P2) , and those populations obtained by hybridization during the first and second seasons. Experimental comparison was performed in the second (Two crosses only) and third seasons , (four crosses) by using RCBD with three
... Show More
(5)
Dust is a frequent contributor to health risks and changes in the climate, one of the most dangerous issues facing people today. Desertification, drought, agricultural practices, and sand and dust storms from neighboring regions bring on this issue. Deep learning (DL) long short-term memory (LSTM) based regression was a proposed solution to increase the forecasting accuracy of dust and monitoring. The proposed system has two parts to detect and monitor the dust; at the first step, the LSTM and dense layers are used to build a system using to detect the dust, while at the second step, the proposed Wireless Sensor Networks (WSN) and Internet of Things (IoT) model is used as a forecasting and monitoring model. The experiment DL system
... Show More
(3)
The effect of using three different interpolation methods (nearest neighbour, linear and non-linear) on a 3D sinogram to restore the missing data due to using angular difference greater than 1° (considered as optimum 3D sinogram) is presented. Two reconstruction methods are adopted in this study, the back-projection method and Fourier slice theorem method, from the results the second reconstruction proven to be a promising reconstruction with the linear interpolation method when the angular difference is less than 20°.
(2)
(2)
Groupwise non-rigid image alignment is a difficult non-linear optimization problem involving many parameters and often large datasets. Previous methods have explored various metrics and optimization strategies. Good results have been previously achieved with simple metrics, requiring complex optimization, often with many unintuitive parameters that require careful tuning for each dataset. In this chapter, the problem is restructured to use a simpler, iterative optimization algorithm, with very few free parameters. The warps are refined using an iterative Levenberg-Marquardt minimization to the mean, based on updating the locations of a small number of points and incorporating a stiffness constraint. This optimization approach is eff
... Show MoreThis research had been achieved to identify the image of the subsurface structure representing the Tertiary period in the Galabat Field northeast of Iraq using 2D seismic survey measurements. Synthetic seismograms of the Galabat-3 well were generated in order to identify and pick the reflectors in seismic sections. Structural Images were drawn in the time domain and then converted to the depth domain by using average velocities. Structurally, seismic sections illustrate these reflectors are affected by two reverse faults affected on the Jeribe Formation and the layers below with the increase in the density of the reverse faults in the northern division. The structural maps show Galabat field, which consists of longitudinal Asymmetrical narr
... Show More
(2)
NeighShrink is an efficient image denoising algorithm based on the discrete wavelet
transform (DWT). Its disadvantage is to use a suboptimal universal threshold and identical
neighbouring window size in all wavelet subbands. Dengwen and Wengang proposed an
improved method, which can determine an optimal threshold and neighbouring window size
for every subband by the Stein’s unbiased risk estimate (SURE). Its denoising performance is
considerably superior to NeighShrink and also outperforms SURE-LET, which is an up-todate
denoising algorithm based on the SURE. In this paper different wavelet transform
families are used with this improved method, the results show that Haar wavelet has the
lowest performance among
In today's digital era, the importance of securing information has reached critical levels. Steganography is one of the methods used for this purpose by hiding sensitive data within other files. This study introduces an approach utilizing a chaotic dynamic system as a random key generator, governing both the selection of hiding locations within an image and the amount of data concealed in each location. The security of the steganography approach is considerably improved by using this random procedure. A 3D dynamic system with nine parameters influencing its behavior was carefully chosen. For each parameter, suitable interval values were determined to guarantee the system's chaotic behavior. Analysis of chaotic performance is given using the
... Show More