Article
Computer Science, Artificial Intelligence
Jie-chun Chen, Pin-qing Yu, Chun-ying Yao, Li-ping Zhao, Yu-yang Qiao
Summary: In this paper, a video-based eye detector that adopts a coarse-to-fine strategy is proposed. The detector consists of three classifiers and a method for coarse pupil localization is also proposed. Experimental results show that the eye detector has high detection rate and localization speed.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Waleed El Nahal, Hatim G. Zaini, Raghad H. Zaini, Sherif S. M. Ghoneim, Ashraf Mohamed Ali Hassan
Summary: The proposed CHMCEP algorithm is a pupil detection algorithm for eye-tracking. It achieves higher accuracy and robustness under various real-world conditions by using different filtering methods to remove blur and noise, and performing a second filtering process before the circular Hough transform.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Hardware & Architecture
Zhong-Hua Wan, Cai-Hua Xiong, Wen-Bin Chen, Han-Yuan Zhang
Summary: This study proposes a new method for pupil detection, which utilizes compact pupil region detection and ellipse fitting techniques to improve the accuracy and success rate of pupil detection. Compared with state-of-the-art methods, the detection success ratio and 5-pixels error ratio have increased by 7.1% and 3.9%, respectively, demonstrating the effectiveness of the proposed method.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Chemistry, Analytical
Andoni Larumbe-Bergera, Gonzalo Garde, Sonia Porta, Rafael Cabeza, Arantxa Villanueva
Summary: This paper proposes a video-oculography method based on convolutional neural networks for pupil center detection, achieving outstanding performance by manual labeling of pupil centers and testing on multiple databases. Results show the importance of using high quality training data and well-known architectures for achieving exceptional performance.
Article
Geriatrics & Gerontology
Shin-ichi Tokushige, Hideyuki Matsumoto, Shun-ichi Matsuda, Satomi Inomata-Terada, Naoki Kotsuki, Masashi Hamada, Shoji Tsuji, Yoshikazu Ugawa, Yasuo Terao
Summary: This study investigated the pattern of gaze exploration in visual tasks as a potential tool for detecting cognitive decline in Alzheimer's disease patients at an early stage. The results showed that patients with Alzheimer's disease exhibited impaired attentional allocation and inefficient visual processing in visual memory and search tasks. By combining these tasks, cognitive decline can be detected with high sensitivity and specificity and its progression can be evaluated.
FRONTIERS IN AGING NEUROSCIENCE
(2023)
Article
Psychology, Multidisciplinary
Sharath Koorathota, Kaveri Thakoor, Linbi Hong, Yaoli Mao, Patrick Adelman, Paul Sajda
Summary: There is a growing interest in how pupil dynamics can reflect cognitive processes and brain states. Through modeling pupil responses in real-world environments using deep recurrent neural networks, researchers were able to extract a residual signal better indicative of cognition and performance. The study found that deep learning sequence models could effectively differentiate between components of pupil responses linked to environmental factors and those related to cognition and arousal.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Chemistry, Analytical
Luca Antonioli, Andrea Pella, Rosalinda Ricotti, Matteo Rossi, Maria Rosaria Fiore, Gabriele Belotti, Giuseppe Magro, Chiara Paganelli, Ester Orlandi, Mario Ciocca, Guido Baroni
Summary: The study explored the potential of using eye tracking techniques based on deep learning in ocular proton therapy applications. A fully automatic approach utilizing convolutional neural networks was implemented to detect and evaluate iris and pupil positions, showing comparable results to manually labeled ground truths.
Article
Computer Science, Artificial Intelligence
Lu Shi, ChangYuan Wang, Feng Tian, HongBo Jia
Summary: The paper introduces an integrated pupil tracking framework LVCF based on deep learning, consisting of VCF and LSTM, which was trained and evaluated on multiple datasets and outperformed the state of the art technologies.
Article
Chemistry, Multidisciplinary
Wei-Liang Ou, Tzu-Ling Kuo, Chin-Chieh Chang, Chih-Peng Fan
Summary: A pupil tracking methodology based on deep-learning technology was developed for visible-light wearable eye trackers, achieving high accuracy and small errors with the YOLO model. The proposed visible-light wearable gaze tracking system performs up to 20 frames per second on the GPU platform.
APPLIED SCIENCES-BASEL
(2021)
Article
Neurosciences
Babak Zandi, Moritz Lode, Alexander Herzog, Georgios Sakas, Tran Quoc Khanh
Summary: This study developed an open-source pupillometry platform competitive with high-end commercial stereo eye-tracking systems, offering a selection of advanced pupil detection algorithms and high-precision measurement capabilities to meet the requirements of professional pupil response research.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Neurosciences
Vivien Rabadan, Camille Ricou, Marianne Latinus, Nadia Aguillon-Hernandez, Claire Wardak
Summary: Wearing a face mask affects the visual exploration and pupil reactivity to a face, but does not significantly impact emotional perception.
FRONTIERS IN NEUROSCIENCE
(2022)
Review
Neurosciences
Mariana de Mello Gusso, Gabriele Serur, Percy Nohama
Summary: The pupil diameter serves as a reliable indirect measure of brain states and can evaluate various emotions and cognitive processes. The processing of tactile perception is similar to other perceptual modalities, and future studies should avoid issues such as low sampling rate and confounding factors.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Behavioral Sciences
Alessio Bellato, Iti Arora, Puja Kochhar, Danielle Ropar, Chris Hollis, Madeleine J. Groom
Summary: Attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) may have different profiles of visual attention orienting, which may be influenced by dysregulated autonomic arousal. The co-occurrence of ADHD and autism also affects visual attention orienting. In this study, saccadic reaction times (SRTs) and pupil size were measured in children/adolescents with and without ADHD and/or autism. Faster orienting was found for baseline trials, face stimuli, and multi-modal stimuli. A negative linear association was found between pre-saccadic pupil size and SRTs in autistic participants, while a quadratic association was found in children with ADHD. These findings suggest the possible effect of dysregulated autonomic arousal on oculomotor mechanisms in autism and ADHD.
Article
Computer Science, Artificial Intelligence
Camilo A. Ruiz-Beltran, Adrian Romero-Garces, Martin Gonzalez, Antonio Sanchez Pedraza, Juan A. Rodriguez-Fernandez, Antonio Bandera
Summary: This paper presents a hardware-based embedded solution for real-time eye detection. By redesigning the popular Viola-Jones method, highly parallel single-pass image processing is achieved. Experimental validation shows that the proposed solution achieves 100% accuracy in eye detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Engineering, Biomedical
K. Malinowski, K. Saeed
Summary: The method proposed in this article for pupil and iris segmentation is independent of size and shape and insensitive to light reflections and mirrored images. The algorithm shows high segmentation accuracy on both noisy and clear images, effectively detecting eyelid boundaries and eliminating shadows and eyelashes.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Chenglong Li, Xiaobin Yang, Guohao Wang, Aihua Zheng, Chang Tan, Jin Tang
Summary: License plate recognition is crucial in various practical applications, however, recognizing license plates of large vehicles is challenging due to low resolution, contamination, low illumination, and occlusion. To address this problem, a novel data generation framework based on the Disentangled Generation Network is proposed to ensure the generation diversity and integrity for robust enlarged license plate recognition.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Sara Casao, Alvaro Serra-Gomez, Ana C. Murillo, Wendelin Bohmer, Javier Alonso-Mora, Eduardo Montijano
Summary: This paper presents a hybrid camera system that combines static and mobile cameras, exploiting the cooperation between tracking and control modules to achieve high-level scene understanding. The static camera network provides global awareness, while the mobile cameras enhance the information about the people on the scene.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Anh-Dzung Doan, Bach Long Nguyen, Surabhi Gupta, Ian Reid, Markus Wagner, Tat-Jun Chin
Summary: To ensure reliable object detection in autonomous systems, the detector needs to adapt to changes in appearance caused by environmental factors. We propose a selective adaptation approach using domain gap as a criterion to improve the efficiency of the detector's operation.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan
Summary: This study proposes a novel frequency-guided deep neural network (FHDRNet) for high dynamic range (HDR) imaging from multiple low dynamic range (LDR) images, aiming to address ghosting artifacts. By conducting HDR fusion in the frequency domain, the network utilizes low-frequency signals to remove specific ghosting artifacts and high-frequency signals to preserve details. Extensive experiments demonstrate that this approach achieves state-of-the-art performance.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Guobin Li, Reyer Zwiggelaar
Summary: Breast cancer is the most commonly diagnosed female malignancy worldwide. Recent developments in deep convolutional neural networks have shown promising performance for breast cancer detection and classification. However, biased features can be learned due to variations in appearance and small datasets. To address this issue, a densely connected convolutional network (DenseNet) was trained using texture features representing different physical morphological representations as inputs. The use of connectivity estimation and nearest neighbors improved the network's unbiased prediction. The approach achieved higher diagnostic accuracy and provided visual explanations for model predictions.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yuezun Li, Cong Zhang, Honggang Qi, Siwei Lyu
Summary: Deep Neural Networks (DNNs) are vulnerable to adversarial perturbations, limiting their applicability in safe-critical scenarios. To address this, a new method called AdaNI is proposed to increase feature randomness through adaptive noise injection, improving adversarial robustness. Extensive experiments demonstrate the efficacy of AdaNI against various white-box and black-box attacks, as well as its applicability in DeepFake detection.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Chengyin Hu, Weiwen Shi, Ling Tian, Wen Li
Summary: In this study, we introduce a pioneering black-box light-based physical attack called Adversarial Neon Beam (AdvNB). Our method excels in attack modeling, efficient attack simulation, and robust optimization, striking a balance between robustness and efficiency. Through rigorous evaluation, we achieve impressive attack success rates in both digital and real-world scenarios. AdvNB demonstrates its stealthiness through comparisons with baseline samples and consistently achieves high success rates when targeting advanced DNN models.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Hang Wang, Zhenyu Ding, Cheng Cheng, Yuhai Li, Hongbin Sun
Summary: Learning-based super resolution has made remarkable progress in improving image quality, but the performance decreases when the degradation kernel changes. Blind SR networks can estimate the degradation kernel and adapt well in realistic scenarios, improving performance and runtime. This paper proposes a design that imposes constraints for the kernel estimation network in both the image domain and kernel domain, resulting in high-quality images and efficient runtime.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yuantao Chen, Runlong Xia, Kai Yang, Ke Zou
Summary: This paper proposes an improved image inpainting network using a multi-scale feature module and improved attention module. The network addresses issues in deep learning-based image inpainting algorithms, such as information loss in deep level features and the neglect of semantic features. The proposed network generates better inpainting results by reducing information loss and enhancing the ability to restore texture and semantic features.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yi-Tung Chan
Summary: This study proposes a novel maritime background subtraction method based on ensemble learning theory to address the challenges posed by dynamic marine environments and noise, improving the detection accuracy and enhancing maritime transportation security for autonomous ships in open waters.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)