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
Background/Objectives: The purpose of this study was to classify Alzheimer’s disease (AD) patients from Normal Control (NC) patients using Magnetic Resonance Imaging (MRI). Methods/Statistical analysis: The performance evolution is carried out for 346 MR images from Alzheimer's Neuroimaging Initiative (ADNI) dataset. The classifier Deep Belief Network (DBN) is used for the function of classification. The network is trained using a sample training set, and the weights produced are then used to check the system's recognition capability. Findings: As a result, this paper presented a novel method of automated classification system for AD determination. The suggested method offers good performance of the experiments carried out show that the
... Show MoreThe aim of this study is to compare the effects of three methods: problem-based learning (PBL), PBL with lecture method, and conventional teaching on self-directed learning skills among physics undergraduates. The actual sample size comprises of 122 students, who were selected randomly from the Physics Department, College of Education in Iraq. In this study, the pre- and post-test were done and the instruments were administered to the students for data collection. The data was analyzed and statistical results rejected null hypothesis of this study. This study revealed that there are no signifigant differences between PBL and PBL with lecture method, thus the PBL without or with lecture method enhances the self-directed learning skills bette
... Show MoreFG Mohammed, HM Al-Dabbas, Iraqi journal of science, 2018 - Cited by 6
(10)
(29)
(30)
(10)
(8)
Diabetic retinopathy is an eye disease in diabetic patients due to damage to the small blood vessels in the retina due to high and low blood sugar levels. Accurate detection and classification of Diabetic Retinopathy is an important task in computer-aided diagnosis, especially when planning for diabetic retinopathy surgery. Therefore, this study aims to design an automated model based on deep learning, which helps ophthalmologists detect and classify diabetic retinopathy severity through fundus images. In this work, a deep convolutional neural network (CNN) with transfer learning and fine tunes has been proposed by using pre-trained networks known as Residual Network-50 (ResNet-50). The overall framework of the proposed
... Show More
(4)
Face recognition is a crucial biometric technology used in various security and identification applications. Ensuring accuracy and reliability in facial recognition systems requires robust feature extraction and secure processing methods. This study presents an accurate facial recognition model using a feature extraction approach within a cloud environment. First, the facial images undergo preprocessing, including grayscale conversion, histogram equalization, Viola-Jones face detection, and resizing. Then, features are extracted using a hybrid approach that combines Linear Discriminant Analysis (LDA) and Gray-Level Co-occurrence Matrix (GLCM). The extracted features are encrypted using the Data Encryption Standard (DES) for security
... Show More
Until recently, researchers have utilized and applied various techniques for intrusion detection system (IDS), including DNA encoding and clustering that are widely used for this purpose. In addition to the other two major techniques for detection are anomaly and misuse detection, where anomaly detection is done based on user behavior, while misuse detection is done based on known attacks signatures. However, both techniques have some drawbacks, such as a high false alarm rate. Therefore, hybrid IDS takes advantage of combining the strength of both techniques to overcome their limitations. In this paper, a hybrid IDS is proposed based on the DNA encoding and clustering method. The proposed DNA encoding is done based on the UNSW-NB15
... Show More
(3)
Recently, Image enhancement techniques can be represented as one of the most significant topics in the field of digital image processing. The basic problem in the enhancement method is how to remove noise or improve digital image details. In the current research a method for digital image de-noising and its detail sharpening/highlighted was proposed. The proposed approach uses fuzzy logic technique to process each pixel inside entire image, and then take the decision if it is noisy or need more processing for highlighting. This issue is performed by examining the degree of association with neighboring elements based on fuzzy algorithm. The proposed de-noising approach was evaluated by some standard images after corrupting them with impulse
... Show More