Minufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501Mask R-CNN for Moving Shadow Detection and Segmentation11811945510.21608/ijci.2020.44215.1029ENHendBakrInformation Technology Dept.
Faculty of Computers and Information
Menofia University
EgyptAhmedHamadInformation Technology Dept.
Faculty of Computers and Information
Menofia University
EgyptKhalidAminInformation Technology dept., Faculty of Computers and Information, Menoufia University, EgyptJournal Article20200926One of the primary tasks of completing and developing many computer vision applications is to identify and remove shadow regions. Most existing moving shadow detection methods depend on extracting hand-crafted features of object and shadow regions manually (for example the chromaticity, physical, or geometric properties). Shadow detection using handcrafted features is a challenging task due to different environmental conditions of the shadow such as camouflage and illumination irregularity problems that make these features inefficient to handle such problems. The proposed method uses Convolution Neural Networks (CNN) to automatically learn different distinctive features to model shadow under different environmental conditions. In this paper, the Mask Region Convolution Neural Network (Mask R-CNN) framework is evaluated and tested to automatically perform semantic segmentation in order to detect and classify shadow pixels from the entire video frame. To adapt Mask R-CNN for segmenting and detecting shadow regions, the most significant features are extracted from video frames in a supervised way using deep Residual Network (ResNet-101) architecture. Then, the Region proposal network (RPN) predicts regions of interest (ROI) and their classes that contain foreground objects. Finally, Fully Convolutional Network (FCN) generates a binary segmentation mask for each detected class in ROI. The proposed framework evaluated on common shadow detection datasets that have different environmental issues. Experimental results achieved high performance rates compared to several state-of-the-art methods in terms of average detection rate (96.81%), average discrimination rate (99.42%), and overall accuracy (98.09 %).https://ijci.journals.ekb.eg/article_119455_dde4cab5162dd96c2e4283b2586133f1.pdfMinufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501Memory Pool Publisher Algorithm for Preventing Malicious Fork in the Bitcoin Environment192914721410.21608/ijci.2021.52568.1035ENAhmed HamdyMadkourInformation System, faculty of computer and information, Menoufia university, Shebin Elkom, Menofia, EgyptHatem MAbdel-KaderInformation SystemsDepartment
Faculty of Computers and Information
Menoufia University, EgyptAsmaa HAliInformation System, faculty of computer and information, Menoufia University, Shebin El Kom, Menofia, EgyptJournal Article20201207Abstract— Blockchain technology is used by most Bitcoin systems to store all historical transaction information. Blockchain is a chain of blocks similar to the linked list structure and can be changed to a fork structure, in which there are two types of forks: useful fork or an intentional fork structure. A useful fork may appear when the rules of the Bitcoin system are updated. On the other hand, the intentional fork may appear when a miner has supercomputer properties, generates a set of blocks as a private branch, and does not publish this branch to the blockchain until its length exceeds the length of the main branch. A set of blockchain transactions will be rollbacked when the intentional fork occurs in the Bitcoin system, user waiting times will increase, and miner rewards will illegally increase. A Memory pool publisher algorithm is suggested in this paper to avoid the fork issues in the Bitcoin system, for instance: intentional fork, rollback problem, users waiting time. The proposed algorithm is to make the system a single publisher and divide the block's construction into two phases. A miner constructs a block and sends it to the memory pool as the first phase. The memory pool will send the construction block to the blockchain as the second phase. The findings indicate that the proposed algorithm has a strong potential to avoid the blockchain's intentional fork problem and thus minimize user waiting times for the rollback problem.https://ijci.journals.ekb.eg/article_147214_f2450481808803e938207969e5528117.pdfMinufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501Warped Document Image Correction Based on Checkboard Pattern and Geometric Transformation305415364110.21608/ijci.2021.53176.1036ENMarian WagdyLabibFaculty of Computers and Information, Menofia UnivesityKhalid M.AminInformation technology dept., Faculty of computers and information, Menofia university0000-0002-9594-8827MinaIbrahiminformation technology department, faculty of computers and informationJournal Article20201210Abstract— Document image warping problem refers to the process of geometrically transforming 2D images. In this work we aim to solve the warped document image problems. The idea of the proposed method is inspired from the concept of image registration to align two images (distorted document and undistorted ground truth checkboard). In this paper, we propose document image dewarping method based on checkboard calibration pattern and geometric transformation. Some pairs of control points are selected between the two images to define the mapping function between them. The dewarping process transforms the warped document image according to the geometric transformation defined by the calculated mapping function. Results on document dewarping dataset CBDAR 2007 demonstrate the success of our strategy. OCR (Optical Character Recognition) error metrics are also used to gauge the success of the suggested approach. Based on the quantitative and qualitative metrics the proposed method outperforms the compared state of the art method.https://ijci.journals.ekb.eg/article_153641_8c5078afd0aeed3b0dbc43e5d36438ac.pdfMinufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501Investigation of Deep Convolutional Neural Network (CNN) approaches’ accuracy for the detection of COVID-19556616954010.21608/ijci.2021.63200.1042ENEsraaDawodComputer Science department, Faculty of Computers and Information, Menoufia University, EgyptNaderMahmoudComputer Science Department, Faculty of Computers and Information
Menoufia University, EgyptAshrafElsisiFaculty of Computers and Information,
Menofia University, EgyptJournal Article20210216Abstract— the world those days focuses on protecting human health and combating the irruption of coronavirus patients (COVID-19). As results of its extra ordinarily contagious infection that have caused a disturbance in everyone's lives in various ways. For early screening, Reverse Transcription Protein Chain Reaction (RT-PCR) test is used to examine the onset of the patients by detecting the RNA material of the virus among the patients’ samples. Recent results indicate that the applying of X-ray images and X-radiation (CT) improves the detection accuracy of this disease. However, the classification task of medical images is tough due to several factors such as lack of dataset for COVID-19, and difficulty in identifying type of infection. Recent research works have been proposed for COVID-19 detection that has been applied on specific datasets. Thus, it is vital to validate their performance on various datasets with different imaging disease conditions. The paper presents a comparison study between top performer CNN models that recorded the very best detection accuracy in image detection and classification: COVID-Net, VGG16, ResNet, Bayesian, DenseNet, and DarkNet. Such CNN approaches can assist medical staff in the early detection of infection. Additionally, we improved dataset in terms of quality, clarity, and quantity using augmentation technique. The quantitative results show that Darknet and COVID-net yield high detection accuracy when applied on CT and X-ray dataset. We validated our results by training the models on multiple different datasets, using CPU and GPU with various bach sizes and optimizers.https://ijci.journals.ekb.eg/article_169540_b56f01bc091fa3b0042bc03693a3121d.pdfMinufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501A Hybrid Swarm Intelligence Based Feature Selection Algorithm for High Dimensional Datasets678617197010.21608/ijci.2021.62499.1040ENJomanaYousefFaculty of computers and informationAnasYoussefComputer Science, Faculty of Computers and Information, Menoufia University0000-0002-5821-9035ArabiKeshkFaculty of Computer and Information Menoufia UniversityJournal Article20210210High dimensional datasets expose a critical obstacle in machine learning. Feature selection overcomes this obstacle by eliminating duplicated and unimportant features from the dataset to increase the robustness of learning algorithms. This paper introduces a binary version of a hybrid swarm intelligence approach as a wrapper method for feature selection that gathers between the strengths of both the grey wolf and particle swarm optimizers. This approach is named Improved Binary Grey Wolf Optimization (IBGWO). The original version of this hybrid approach was proposed in the literature with a continuous search space as a high-level hybrid form, which runs the optimizers one after the other. Two different types of transfer functions, named S-Shaped and V-Shaped, are applied in this work to turn continuous data into binary. Nine of high-dimensional small-instance medical datasets are employed to assess the proposed approach. The experimental results demonstrate that IBGWO based on S-Shaped (IBGWO-S) outperforms the binary particle swarm and the binary grey wolf optimizers on six out of nine datasets according to the classification accuracy and fitness values. IBGWO-S selects the fewest features on 100% of the datasets. The results show IBGWO based on V-Shaped (IBGWO-V) outperforms the binary particle swarm and binary grey wolf optimizers on five datasets based on the classification accuracy and fitness values. The results indicate that IBGWO-V outperforms IBGWO-S in terms of all studied evaluation metrics. The results also show that IBGWO-S and IBGWO-V outperform eight meta-heuristics known in the literature in selecting the relevant features with acceptable classification accuracy.https://ijci.journals.ekb.eg/article_171970_0c2c60e404e09d18463e7eff9e5b7f70.pdfMinufiya University; Faculty of Computers and InformationIJCI. International Journal of Computers and Information1687-78538120210501A Substitution-Based Method for Data Hiding in DNA Sequences8710517202410.21608/ijci.2021.56184.1037ENAmanyEl-deebNational Liver Institute, Shibin elKom, MenoufiaAshrafElsisiComputer Science, Faculty of Computers and Information, Menoufia UniversityAnasYoussefComputer Science, Faculty of Computers and Information, Menoufia University0000-0002-5821-9035Journal Article20210104Abstract—To transmit data securely between different parties, a variety of security approaches have been proposed in the literature. Specifically, DNA based cryptography and steganography approaches were used to secure data transmission. In this paper, a substitution-based method for data hiding in DNA sequences is proposed. In the proposed data hiding method, data is encoded using a binary coding rule then the data is hidden into a DNA sequence. The proposed method provides an enhancement on a previously proposed DNA substitution method named Least Significant Base method. The proposed enhancement is based on a simple idea that, to the best of our knowledge, was not applied before. It was noticed that the DNA Amino acids can be organized into groups where each DNA codon in one of the groups can be used to encode two bits of the hidden message rather than only one bit as proposed by the Least Significant Base method. Like the Least Significant Base method, the proposed method is blind, preserves the DNA original biological structure in the fake DNA sequence and provides no expansion in the DNA sequence. The proposed method is evaluated using a public DNA sequences dataset named BALIBASE. The evaluation results showed that the proposed method achieved about 50% increase in the data hiding capacity when compared with the Least Significant Base method. Moreover, the results showed that the proposed method resulted in significant decrease in the cracking probability of the Least Significant Base method.https://ijci.journals.ekb.eg/article_172024_71061da7391a6c30f9bbe8a59e54cc13.pdf