Search

Detecting and subtracting the Motion objects from backgrounds is one of the most important areas. The development of cameras and their widespread use in most areas of security, surveillance, and others made face this problem. The difficulty of this area is unstable in the classification of the pixels (foreground or background). This paper proposed a suggested background subtraction algorithm based on the histogram. The classification threshold is adaptively calculated according to many tests. The performance of the proposed algorithms was compared with state-of-the-art methods in complex dynamic scenes. [ABSTRACT FROM AUTHOR]

Cancer is an acute disease that kills many people around the world, so early detection is a vital need. This study aims to investigate the effectiveness of techniques used in detecting, isolating and extracting tumors in PET/CT images using clustering techniques: K-means, Fuzzy C-mean, and hybrid technique. The results showed that the applied methods were sufficient to detect, isolate and extract areas of the tumor. The calculated tumor area was compared with the nuclear medicine specialist demarcation area, and the percent relative difference ranged between 0.135%-4.86%. As well as the results indicated that implementing the hybrid technique reduced the elapsed time required, and the reduction percentage ranged between 43.03%-97.45%. [ABSTRACT FROM AUTHOR]

This paper presents a system for diagnosing osteoporosis using x-rays by leveraging transfer learning in the same domain. The proposed system consists of phase 1 and phase 2; each phase includes several stages, as the pre-processing stage appropriately prepares the source image via noise reduction by the average filter, contrast enhancement using histogram equalization, and obtaining the region of interest by employing K-mean and edge detection, followed by the smudging stage through a mean filter with a large window size, which subsequently contributed to facilitating the diagnosis. The stages mentioned in both phases are similar. In phase 1, the model is trained on a large unlabeled x-ray dataset collected from different orthopedic centers to identify the general features of the image. In phase 2, fine-tune the trained model with the target dataset; this approach is beneficial when the target task has limited labeled data or when training a model from scratch is computationally expensive. It is worth noting that two datasets were used as target datasets. The accuracy of diagnosing osteoporosis using the proposed deep convolutional neural network (DCNN) model was 94.5 with the osteoporosis knee x-ray database (Dataset A). The accuracy of diagnosing osteoporosis using transfer learning in the same field was 98.91 when training the proposed DCNN model with a large unlabeled dataset and fine-tuning with the target database, osteoporosis knee x-ray database (Dataset A). The accuracy of diagnosing osteoporosis using the proposed DCNN model was 91.5 with the knee x-ray osteoporosis database (Dataset B). The accuracy of diagnosing osteoporosis using transfer learning in the same field was 96.61 when training the proposed DCNN model with a large unlabeled dataset and fine-tuning with the target knee x-ray osteoporosis database (Dataset B). [ABSTRACT FROM AUTHOR]

Image texture is an important part of many types of images, for example medical images. Texture Analysis is the technique that uses measurable features to categorize complex textures. The main goal is to extract discriminative features that are used in different pattern recognition applications and texture categorization. This paper investigates the extraction of most discriminative features for different texture images from the “Colored Brodatz” dataset using two types of image contrast measures, as well as using the statistical moments on five bands (red, green, blue, grey, and black). The Euclidean distance measure is used in the matching step to check the similarity degree. The proposed method was tested on 112 classes of textures. The achieved results showed that the proposed method is accurate and fast concerning classification accuracy with low computational complexity. The achieved Recognition Rate (RR) was 100%. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) is a complex signal that may require several years of training, advanced signal processing, and feature extraction methodologies to interpret correctly. Recently, many methods have been used to extract and classify EEG data. This study reviews 62 papers that used EEG signals to detect driver drowsiness, published between January 2018 and 2022. We extract trends and highlight interesting approaches from this large body of literature to inform future research and formulate recommendations. To find relevant papers published in scientific journals, conferences, and electronic preprint repositories, researchers searched major databases covering the domains of science and engineering. For each investigation, many data items about (1) the data, (2) the channels used, (3) the extraction and classification procedure, and (4) the outcomes were extracted. These items were then analyzed one by one to uncover trends. Our analysis reveals that the amount of EEG data used across studies varies. We saw that more than half the studies used simulation driving experimental. About 21% of the studies used support vector machine (SVM), while 19% used convolutional neural networks (CNN). Overall, we can conclude that drowsiness and fatigue impair driving performance, resulting in drivers who are more exposed to risky situations. [ABSTRACT FROM AUTHOR]

Managing big data backups is challenging due to high volumes of redundant data. Data deduplication is widely used but incurs significant computational and time costs. This paper proposes a hybrid deduplication system that combines file-level and block-level methods to enhance deduplication while reducing costs. File-level deduplication eliminates duplicate files, while block-level deduplication is applied to non-duplicated files using a dynamic list of divisors to enhance deduplication. A multi-hash function generates three hash values for each file or chunk to improve chunking speed and reduce hash collisions. The proposed hybrid system outperforms other state-of-the-art methods in terms of time, data deduplication ratio, and deduplication gain. Experimental results show reductions of 97.2%, 91.6%, and 82.1% in data size for Dataset 1, Dataset 2, and Dataset 3, respectively, and demonstrate that the proposed multi-hash function is faster and requires less storage than other hash functions. [ABSTRACT FROM AUTHOR]

Landsat7 of Enhanced thematic mapper plus (ETM+) was launched on April 15, 1999. Four years later, images start degrading due to the scan line corrector (SLC). SLC is a malfunction that results in pixel gaps in images captured by the sensor of Landsat7. The pixel gap regions extend from about one pixel near the image center and reach up to about 14 pixels in width near the image edge. The shape of this loss is like a zigzag line; however, there are different studies about repairing these gaps. The challenge of all studies depends on retrieving inhomogeneous areas because the homogenous area can be retrieved quickly depending on the surrounding area. This research focuses on filling these gaps by utilizing pixels around them gaps. Pixels from different satellites with the same resolution at the approximate equal date and exact location would be utilized. Mean and standard deviation were used in gap pixel predicting. For complete pixels gap predicting, an image registration should be applied for predicted a good result— image registration comprised of geometric and radiometric registration. Translation and rotation was the main effect of geometric registration, while pixel tone was mainly related to radiometric registration. Two images of Landsat8 (before and after) with nearly the date of Landsat 7 were used. The fidelity criteria (mean square error and mean absolute error) were utilized to evaluate the results. The results showed a good prediction of the gap pixels in the Landsat 7 image, considering the geometric and radiometric parts. [ABSTRACT FROM AUTHOR]

Driver drowsiness is one of the top causes of road fatalities and transportation industry risks. Electroencephalography (EEG) has been regarded as one of the most reliable physiological signs for detecting drowsiness in drivers since it directly assesses neurophysiological brain activity. If possible, a system that monitors driver drowsiness and warnings can prevent the greatest number of traffic incidents. This study presents a simple and inexpensive method for detecting driver drowsiness or sleep onset with single-channel EEG signal processing. The primary contribution of this study is the identification of sleepiness detection from a publicly available graph signal dataset using only two discriminated features (standard deviation and entropy) and a filter that is easily implementable in any microcontroller device or smartphone. This study employed the least square support vector machine to categorize driver status into two groups (awake or drowsy). The proposed method can be implemented in real-time with high efficiency and precision. Furthermore, this method can be readily applied on a smartphone to create and expand a sleepiness detection and alert system for vehicle drivers. The trial findings indicate an accuracy of 95.5 percent. [ABSTRACT FROM AUTHOR]

The data deduplication technique efficiently reduces and removes redundant data in big data storage systems. The main issue is that the data deduplication requires expensive computational effort to remove duplicate data due to the vast size of big data. The paper attempts to reduce the time and computation required for data deduplication stages. The chunking and hashing stage often requires a lot of calculations and time. This paper initially proposes an efficient new method to exploit the parallel processing of deduplication systems with the best performance. The proposed system is designed to use multicore computing efficiently. First, The proposed method removes redundant data by making a rough classification for the input into several classes using the histogram similarity and k-mean algorithm. Next, a new method for calculating the divisor list for each class was introduced to improve the chunking method and increase the data deduplication ratio. Finally, the performance of the proposed method was evaluated using three datasets as test examples. The proposed method proves that data deduplication based on classes and a multicore processor is much faster than a single-core processor. Moreover, the experimental results showed that the proposed method significantly improved the performance of Two Threshold Two Divisors (TTTD) and Basic Sliding Window BSW algorithms. [ABSTRACT FROM AUTHOR]