Article
Automation & Control Systems
Feng Shao, Zhenqi Fu, Qiuping Jiang, Gangyi Jiang, Yo-Sung Ho
Summary: This paper proposes a new method for assessing the quality of image retargeting by measuring geometric distortion and content loss to determine the retargeting quality. Experimental results show that the proposed method performs better on two databases.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Information Systems
Ankit Garg
Summary: The objective of this paper is to optimize image retargeting operations by using hybrid sequences to minimize the deficiencies. Three frameworks are developed and combined to achieve this goal. Framework 1 overcomes the limitations of existing seam carving technique, while Framework 2 combines multiple retargeting operators for improved efficiency. Framework 3 introduces an improved affine transformation function to replace the scaling operator.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Bo Wang, Hongyang Si, Huiting Fu, Ruao Gao, Minjuan Zhan, Huili Jiang, Aili Wang
Summary: A novel content-aware image resizing mechanism is proposed to address the lack of esthetic perception in current algorithms. It introduces a composition detection module for detecting input image composition and selects corresponding composition rules in computational esthetics. The algorithm performs seam carving using the selected esthetic rules, resulting in a resized image that protects important content and optimizes overall visual effect.
Article
Computer Science, Software Engineering
Dov Danon, Moab Arar, Daniel Cohen-Or, Ariel Shamir
Summary: This paper introduces a novel method of image resizing in feature space using deep neural network layers. By adjusting image feature maps directly, important semantic information can be preserved while reducing noticeable artifacts.
COMPUTATIONAL VISUAL MEDIA
(2021)
Article
Geochemistry & Geophysics
Julian Luis Gomez, Danilo R. Velis
Summary: Seam carving is a computer vision algorithm used for resizing images while preserving important structures and textures. The method utilizes gradients and dynamic optimization to find the optimal adjustment, and employs Gaussian kernels to compute data derivatives.
Article
Computer Science, Information Systems
Mohammad Reza Naderi, Mohammad Hossein Givkashi, Nader Karimi, Shahram Shirani, Shadrokh Samavi
Summary: This study proposes an image retargeting method that aims to change the size of images while preserving important content and minimizing distortions. By utilizing techniques such as inpainting, seam carving, super-resolution, and optimization, the proposed method demonstrates commendable performance in improving visual quality.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Ankit Garg, Ashish Negi, Prakhar Jindal
Summary: This technique proposes a novel approach to minimize distortion in salient objects of images by restricting the intersection or overlapping of multiple seams in horizontal and vertical directions. It surpasses traditional techniques by showing remarkable results in terms of low distortion percentage, especially for shrinkage and enlargement of a single image multiple times.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Article
Computer Science, Information Systems
Zhenqi Fu, Feng Shao, Qiuping Jiang, Xiangchao Meng, Yo-Sung Ho
Summary: The study aims to propose a quality assessment method for binocular stereoscopic image retargeting, establishing a database with 720 stereoscopic images and introducing an objective metric based on grid deformation and information loss. Experimental results demonstrate the superiority of the proposed metric over existing methods in measuring the quality of stereoscopic retargeted images.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Yingchun Guo, Dan Wang, Gang Yan, Ye Zhu
Summary: With the increasing variety of display devices, image retargeting has become necessary to adjust the aspect ratio of images for different terminals. This paper reviews the state-of-the-art technologies in image retargeting quality assessment (IRQA), discusses image registration algorithms, and investigates feature measurement methods. It also provides publicly open datasets and evaluates the performance of mainstream methods. Promising research directions towards IRQA are pointed out, benefiting engineers and researchers in improving image retargeting systems and conducting innovative work.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Yuzhen Niu, Shuai Zhang, Zhishan Wu, Tiesong Zhao, Weiling Chen
Summary: In this paper, a new IRQA framework based on RCM and NBP is proposed, integrating registration confidence measurement, noticeability-based pooling, and visual attention fusion to evaluate the quality of retargeted images. Experimental results demonstrate that this metric outperforms the state-of-the-art approaches in assessing image retargeting quality.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Xuejin Wang, Feng Shao, Qiuping Jiang, Xiongli Chai, Mengxiang Chao, Yo-Sung Ho
Summary: This paper explores the perceptual quality issues of retargeted stereoscopic images and proposes a new quality evaluation metric for SIR, which is more consistent with 3D perception and image degradation mechanisms.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Thiago L. Gomes, Renato Martins, Joao Ferreira, Rafael Azevedo, Guilherme Torres, Erickson R. Nascimento
Summary: Transferring human motion and appearance between videos remains a key challenge in Computer Vision, and strict setup compliance is needed for successful retargeting. The proposed shape-aware approach, utilizing image-based rendering technique, shows competitive visual retargeting quality compared to state-of-the-art approaches. This method considers physical constraints of motion in both 3D and 2D image domain, ensuring successful transfer of human appearance between actors.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Engineering, Electrical & Electronic
Pooryaa Cheraaqee, Zahra Maviz, Azadeh Mansouri, Ahmad Mahmoudi-Aznaveh
Summary: Objective image quality assessment plays an important role in various scenarios, and evaluating screen content images requires consideration of their unique characteristics. This paper proposes using distortions in the horizontal and vertical structures of an image to predict its quality, with wavelet analysis as the means to achieve this strategy.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Hardware & Architecture
Bindu Agarwalla, Shirshendu Das, Nilkanta Sahu
Summary: As the demand for larger-sized Last Level Cache (LLC) grows due to modern data-intensive applications, employing high-density DRAM technology to design LLC is an alternative approach. By shutting down some unused banks, the size of the LLC can be reduced to lower energy consumption, and the affected banks can be reopened when the LLC capacity is increased. The proposed Process Variation Aware LLC Resizing (PVAR) strategy reduces energy usage by up to 47% more than existing solutions.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Engineering, Electrical & Electronic
Ziqing Huang, Shiguang Liu
Summary: Perceptual hashing is an effective way to manage the security and content understanding of screen content images (SCIs). The proposed perceptual hashing method for SCIs in this article shows superior performance in classification, robustness, and discrimination compared to state-of-the-art algorithms. Additionally, experiments conducted on SCIs databases demonstrate accurate predictions in reduced-reference screen content image quality assessment.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Ali Hosseini, Mahdi Hashemzadeh, Nacer Farajzadeh
Summary: Fire is a recurring event that causes significant damage in various environments, making machine vision-based fire detection an important task. In this research, a unified flame and smoke detection approach called UFS-Net, based on deep learning, is proposed. UFS-Net can classify video frames into eight classes to identify fire hazards and achieve high performance through extensive experiments and comparisons with state-of-the-art methods.
JOURNAL OF COMPUTATIONAL SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mahdi Hashemzadeh, Nacer Farajzadeh, Milad Heydari
Summary: Early detection of fire, particularly smoke, is crucial in various environmental applications. Traditional machine learning approaches and deep learning-based methods have limitations in terms of transparency of smoke and motion characteristics. This study introduces a hybrid approach based on deep learning, spatio, and spatio-temporal characteristics to accurately detect smoke. The proposed method achieves high performance and accuracy in experiments, outperforming competitors in terms of false alarm rate.
APPLIED SOFT COMPUTING
(2022)
Article
Biology
Nacer Farajzadeh, Nima Sadeghzadeh, Mahdi Hashemzadeh
Summary: Early cancer detection is crucial for effective treatment and recovery. This study proposes a method to mask cancerous nuclei in histopathology images, making them easily distinguishable by experts. The proposed method achieves high accuracy in quantitative and qualitative evaluations.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Shahin Pourbahrami, Mahdi Hashemzadeh
Summary: In this paper, a geometric-based clustering method is proposed which utilizes the concept of natural neighborhoods to extract the local density of data points. The algorithm forms primary clusters, extracts the heads of the clusters, and identifies weak or noise data points by recognizing points with a low number of natural neighbors. The desired clusters are obtained by disregarding the weak/noise points.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Mehrad Aria, Mahdi Hashemzadeh, Nacer Farajzadeh
Summary: This study presents an image forgery detection method called QDL-CMFD, which is based on deep learning. QDL-CMFD utilizes generative adversarial networks for image quality enhancement and convolutional neural networks for forgery detection. Unlike existing methods, QDL-CMFD is able to simultaneously detect multiple forged areas and determine the source and target of the forgery. Experimental results demonstrate its excellent performance in detecting low-quality forged images and small areas.
Article
Computer Science, Interdisciplinary Applications
Nasim Abdolmaleki, Leyli Mohammad Khanli, Mahdi Hashemzadeh, Shahin Pourbahrami
Summary: This paper introduces an Apollonius Circle-based Quantum Clustering (ACQC) method, which adaptively sets the kernel bandwidth without prior knowledge, resulting in improved accuracy and efficiency in clustering.
JOURNAL OF COMPUTATIONAL SCIENCE
(2022)
Article
Computer Science, Cybernetics
Nacer Farajzadeh, Nima Sadeghzadeh, Mahdi Hashemzadeh
Summary: Music genres are important tools for organizing music and targeting different markets. This research introduces a new deep neural network-based method for automatically classifying Persian music genres, which shows acceptable accuracy in the dataset test.
ENTERTAINMENT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Saeed Hamdollahi Oskouei, Mahdi Hashemzadeh
Summary: In order to choose appropriate food based on people's preferences, an intelligent system is needed. This study presents a deep learning-based food recommender system called FoodRecNet, which utilizes various characteristics and features of users and foods. A large annotated dataset is created to evaluate the system, and experiments confirm its effectiveness. The implementation source codes and datasets of this research are publicly available.
KNOWLEDGE AND INFORMATION SYSTEMS
(2023)
Article
Engineering, Biomedical
Nacer Farajzadeh, Nima Sadeghzadeh, Mahdi Hashemzadeh
Summary: Osteoarthritis is the most common musculoskeletal disorder worldwide, particularly in the knee joint. Accurate diagnosis of osteoarthritis has been challenging due to the low quality and indistinctness of clinical radiographic images. This research proposes a deep residual neural network named IJES-OA Net, which focuses on the distance of the bone edges inside the knee joint to automatically grade the severity of knee osteoarthritis via radiographs. Experimental results demonstrate that IJES-OA Net achieves high accuracy and precision with less complexity compared to other methods, and the generated attention maps enhance experts' reliance on the results.
MEDICAL ENGINEERING & PHYSICS
(2023)
Article
Computer Science, Artificial Intelligence
Nacer Farajzadeh, Nima Sadeghzadeh, Mahdi Hashemzadeh
Summary: Detecting brain tumors is crucial for patients' survival, and Magnetic Resonance Imaging (MRI) has been proven to be the most accurate method. However, the accuracy of evaluation by human specialists can be compromised due to fatigue, lack of expertise, and insufficiency of information in the images. This study proposes a segmentation approach to assist specialists in accurately detecting brain tumors, achieving the highest accuracy compared to previous studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Paria Soltanzadeh, M. Reza Feizi-Derakhshi, Mahdi Hashemzadeh
Summary: This research proposes an under-sampling approach based on a metaheuristic method to address the problems of imbalanced class distribution and class overlap, achieving significant performance improvement compared to competitors.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Vahid Mohammadian Takaloo, Mahdi Hashemzadeh, Jalil Ghavidel Neycharan
Summary: In this study, a method called DiagCovidPNA is proposed to diagnose and differentiate COVID-19 disease and viral and bacterial pneumonia (PNA) from chest X-ray (CXR) images. The method is based on application-specific convolutional neural networks (CNNs) and offers two different systems: DiagCovidPNA and Hybrid DiagCovidPNA. Extensive experiments were conducted to evaluate both systems, and the results showed that the diagnostic accuracy of DiagCovidPNA and Hybrid DiagCovidPNA is 95% and 97.50% respectively. Hybrid DiagCovidPNA improves accuracy by approximately 8% compared to other deep learning-based methods with the same structure. All implementation source codes and the compiled CXR database are publicly available.
Article
Computer Science, Software Engineering
Amin Golzari Oskouei, Mahdi Hashemzadeh
Summary: CGFFCM is a clustering-based color image segmentation approach that mitigates initialization sensitivity through an automatic cluster weighting strategy, improves clustering accuracy using a group-local feature weighting technique, and enhances image segmentation quality by combining image features from different groups.
Article
Engineering, Electrical & Electronic
Alam Abbas Syed, Hassan Foroosh
Summary: This paper presents effective methods using spherical polar Fourier transform data for two different applications: 3D volumetric registration and machine learning classification network. The proposed method for registration offers unique and effective techniques, handling arbitrary large rotation angles and showing robustness. The modified classification network achieves robust classification results in processing spherical data.
Article
Engineering, Electrical & Electronic
Ruibo Fan, Mingli Jing, Jingang Shi, Lan Li, Zizhao Wang
Summary: In this study, a new low-rank sparse decomposition algorithm named TVRPCA+ is proposed for foreground-background separation. The algorithm combines spectral norm, structured sparse norm, and total variation regularization to suppress noise and obtain cleaner foregrounds. Experimental results demonstrate that TVRPCA+ achieves high performance in complex backgrounds and noise scenarios.
Article
Engineering, Electrical & Electronic
Omair Aldimashki, Ahmet Serbes
Summary: This paper proposes a coarse-to-fine FrFT-based algorithm for chirp-rate estimation of multi-component LFM signals, which achieves improved performance and a reduced signal-to-noise breakdown threshold by utilizing mathematical models for coarse estimation and a refined estimate-and-subtract strategy. Extensive simulation results demonstrate that the proposed algorithm performs very close to the Cramer-Rao lower bound, with the advantages of eliminating leakage effect, avoiding error propagation, and maintaining acceptable computational cost compared to other state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Xinlei Shi, Xiaofei Zhang, Yuxin Sun, Yang Qian, Jinke Cao
Summary: In this paper, a low-complexity localization approach for multiple sources using two-dimensional discrete Fourier transform (2D-DFT) is proposed. The method computes the cross-covariance and utilizes phase offset method and total least square solution to obtain accurate position estimates.
Article
Engineering, Electrical & Electronic
Prabhanjan Mannari, Ratnasingham Tharmarasa, Thiagalingam Kirubarajan
Summary: This paper discusses the problem of extended target tracking for a single 2D extended target with a known convex polytope shape and dynamics. It proposes a framework based on the existing point multitarget tracking framework to address the challenges of uncertainty in shape and kinematics, as well as self-occlusion. The algorithm developed using this framework is capable of dynamically changing the number of parameters used to describe the shape and estimating the whole target shape even when different parts of the target are visible at different frames.
Article
Engineering, Electrical & Electronic
Yongsong Li, Zhengzhou Li, Jie Li, Junchao Yang, Abubakar Siddique
Summary: This paper proposes a weighted adaptive ring top-hat transformation (WARTH) for extracting infrared small targets in complex backgrounds. The WARTH method effectively measures local and global feature information using an adaptive ring-shaped structural element and a target awareness indicator, resulting in accurate detection of small targets with minimized false alarms.
Article
Engineering, Electrical & Electronic
Yu Wang, Zhen Qin, Jun Tao, Yili Xia
Summary: In this paper, an enhanced sparsity-aware recursive least squares (RLS) algorithm is proposed, which combines the proportionate updating (PU) and zero-attracting (ZA) mechanisms, and introduces a general convex regularization (CR) function and variable step-size (VSS) technique to improve performance.
Article
Engineering, Electrical & Electronic
Neil J. Bershad, Jose C. M. Bermudez
Summary: This paper analyzes the impact of processing delay on the Least Mean Squares (LMS) algorithm in system identification, highlighting bias issues in the resulting weight vector.
Article
Engineering, Electrical & Electronic
Kanghui Jiang, Defu Jiang, Mingxing Fu, Yan Han, Song Wang, Chao Zhang, Jingyu Shi
Summary: In this paper, a novel method for velocity estimation using multicarrier signals in a single dwell is proposed, which effectively addresses the issue of Doppler ambiguity in pulse Doppler radars.
Article
Engineering, Electrical & Electronic
Xiao-Jun Zhang, Peng-Lang Shui, Yu-Fan Xue
Summary: This paper proposes a method for low-velocity small target detection in maritime surveillance radars. It models sea clutter sequences using the spherical invariant random vector (SIRV) model with block tridiagonal speckle covariance matrix and inverse Gamma distributed texture. The proposed detector, which is a long-time adaptive generalized likelihood ratio test with linear threshold detector (GLRT-LTD), shows competitive detection performance in experiments.
Article
Engineering, Electrical & Electronic
Aiyi Zhang, Fulai Liu, Ruiyan Du
Summary: This paper proposes an adaptive weighted robust data recovery method with total variation regularization for hyperspectral image. The method models the HSI recovery problem as a tensor robust principal component analysis optimization problem, decomposing the data into low-rank HSI data, outliers, and noise component. An adaptive weighted strategy is then defined to impose on the tensor nuclear norm and outliers, using the priori information of singular values and strengthening the sparsity of outliers.
Article
Engineering, Electrical & Electronic
Hamid Asadi, Babak Seyfe
Summary: This paper presents a novel approach for estimating the model order in the presence of observation errors. The proposed method is based on correntropy estimation of eigenvalues in the observation space, which is further enhanced by resampling the observations using the bootstrap method. The algorithm partitions the observation space into signal and noise subspaces using the covariance matrix of mixtures, and determines the model order based on a correntropy estimator with kernel functions. Theoretical analysis and comparative evaluations demonstrate the superiority of this information-theoretic approach.
Article
Engineering, Electrical & Electronic
Buket colak Guvenc, Engin Cemal Menguc
Summary: In this paper, a novel family of online censoring based complex-valued least mean kurtosis (CLMK) algorithms is proposed. The algorithms censor less informative complex-valued data streams and reduce the costs of data processing without affecting accuracy. Robust algorithms are also developed to handle outliers. The simulation results confirm the attractive features of the proposed algorithms in large-scale system identification and regression scenarios.
Article
Engineering, Electrical & Electronic
Yun Su, Weixian Tan, Yifan Dong, Wei Xu, Pingping Huang, Jianxin Zhang, Diankun Zhang
Summary: In this study, a novel method for detecting low-resolution and small targets in millimeter wave radar images is proposed. The Wavelet-Conv structure and Wavelet-Attention mechanism are introduced to overcome the limitations of existing detectors. Experimental results demonstrate that the proposed method improves recall and mean average precision while maintaining competitive inference speed.
Article
Engineering, Electrical & Electronic
Xin Wang, Xingxing Jiang, Qiuyu Song, Jie Liu, Jianfeng Guo, Zhongkui Zhu
Summary: This study proposes a variational mode extraction (VME) method for extracting specific modes from complicated signals. By exploring the convergence property of VME, strategies for identifying ICF and determining the balance parameter are designed, and a bandwidth estimation strategy is constructed. The effectiveness of the proposed method for bearings fault diagnosis is verified and compared with other methods.