Article
Green & Sustainable Science & Technology
Saeed Aligholi, Reza Khajavi, Manoj Khandelwal, Danial Jahed Armaghani
Summary: In this paper, a rotation-invariant local binary pattern operator equipped with a local contrast measure is proposed to characterize the type of mineral twinning by inspecting the texture properties of crystals. The proposed system achieves high sensitivity and accuracy in texture identification and can be applied in various fields for classification and feature recognition tasks.
Article
Computer Science, Artificial Intelligence
Qiwu Luo, Jiaojiao Su, Chunhua Yang, Olli Silven, Li Liu
Summary: In this paper, a novel image descriptor, called SNELBP, is proposed to address scale transformation and noise interference simultaneously. It achieves competitive results compared to classical LBP variants and typical deep learning methods.
PATTERN RECOGNITION
(2022)
Article
Engineering, Electrical & Electronic
Tiecheng Song, Jie Feng, Lin Luo, Chenqiang Gao, Hongliang Li
Summary: In this paper, two novel operators, local grouped order pattern (LGOP) and non-local binary pattern (NLBP), are proposed for texture description. Experimental results demonstrate that combining LGOP and NLBP to construct discriminative histogram features as texture descriptor LGONBP shows superiority over state-of-the-art LBP variants for texture classification.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Software Engineering
Shaokun Lan, Jie Li, Shiqi Hu, Hongcheng Fan, Zhibin Pan
Summary: In this paper, a neighbourhood feature-based local binary pattern (NF-LBP) is proposed to improve the classification performance of the local binary pattern (LBP) in texture feature analysis. The NF-LBP method combines the neighbourhood feature, local sign component, and centre pixel component to provide better texture information and is robust to noise.
Article
Computer Science, Information Systems
E. Rachdi, I. El Khadiri, Y. El merabet, Y. Rhazi, C. Meurie
Summary: This paper introduces a novel local feature extraction operator called MTSP, which is composed of two single-scale encoders, STP and SSP, designed based on a novel set theory pattern encoding scheme. Unlike other parametric texture operators, MTSP incorporates dynamic thresholds and can capture more detailed image information through the fusion of STP and SSP encoders. Experimental results demonstrate that MTSP achieves reliable performance stability on ten texture datasets and outperforms several representative methods in texture modeling, as verified by statistical tests.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Hardware & Architecture
Monika Sharma, Mantosh Biswas
Summary: The authors proposed a novel method for HSI classification, which includes enhanced texture-based classification paradigm, spatial uniformity maintenance technique, label enhancement method, superpixel segmentation, and feature fusion. Evaluation on multiple datasets confirmed that the proposed RILBP-WGCN algorithm outperforms other competing classification schemes significantly.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Environmental Sciences
Yameng Hong, Chengcai Leng, Xinyue Zhang, Zhao Pei, Irene Cheng, Anup Basu
Summary: This paper introduces a new method called HOLBP for image registration, which improves traditional methods by redefining gradient and angle calculation and adding gradient direction information to form a 138-dimension descriptor vector. The experimental results demonstrate the stability and efficiency of this method for different test images.
Article
Computer Science, Artificial Intelligence
Tiecheng Song, Yuanjing Han, Shuang Li, Chuchu Zhao
Summary: The paper introduces an enhanced local ternary derivative pattern with dominant structure encoding (DLTDP) descriptor to overcome the limitations of traditional LTP descriptors. Experimental results demonstrate the superiority of DLTDP in texture classification.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Shan Zhao, Yan Wu, Yongmao Wang, Yu Han
Summary: This study introduces a new image descriptor, MLOSTP, which captures color, texture, and local spatial information through the combination of different channels. The results show that MLOSTP outperforms other descriptors in image retrieval.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Materials Science, Multidisciplinary
Ibtissam Al Saidi, Mohammed Rziza, Johan Debayle
Summary: CPLBP is a novel texture classification descriptor that extends the neighborhood region using polar coordinates, enhancing feature extraction efficiency. By dividing the circle and calculating the average value of each part, CPLBP captures discriminating relationships among pixels in the local neighborhood effectively.
IMAGE ANALYSIS & STEREOLOGY
(2021)
Article
Multidisciplinary Sciences
Sayyad Alizadeh, Hossein B. Jond, Vasif V. Nabiyev, Cemal Kose
Summary: In this paper, a novel automatic method called Modified Multi-Block Local Binary Pattern (MMB-LBP) was proposed to maintain the local features of a shoeprint image and place a pattern in a block. The proposed method outperforms other methods in terms of retrieving complete and incomplete shoeprints, and shows significant resistance to distortions like rotation, salt and pepper noise, and Gaussian white noise.
Article
Computer Science, Artificial Intelligence
Saeed Najafi Khanbebin, Vahid Mehrdad
Summary: This paper presents a local pattern-based DR_LBP approach for extracting more discriminative features in face recognition. Compared to traditional LBP, this method utilizes more pixel information in the LBP box, leading to successful experimental results.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Xin Shu, Hui Pan, Jinlong Shi, Xiaoning Song, Xiao-Jun Wu
Summary: This paper proposes a novel global refined local binary pattern (GRLBP) for texture feature extraction. By analyzing the nature of pixel intensity distribution in local neighborhoods, GRLBP can effectively describe and distinguish local neighborhoods with similar structures but different contrasts or grayscales. Experimental results demonstrate that GRLBP can represent detailed information of texture images and outperforms state-of-the-art LBP variants in terms of classification accuracy, feature dimension, and computational complexity.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Hung Phuoc Truong, Thanh Phuong Nguyen, Yong-Guk Kim
Summary: A novel framework for efficient and robust facial feature representation, Weighted Statistical Binary Pattern, is proposed, which utilizes a new variance moment containing distinctive facial features and a weighting approach for constructing sign and magnitude components. Through comprehensive evaluation on six public face datasets, the framework outperforms state-of-the-art methods in terms of accuracy.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Yijie Luo, Jiming Sa, Yuyan Song, He Jiang, Chi Zhang, Zhushanying Zhang
Summary: This paper proposes an improved LBP operator by using a local binary pattern operator based on magnitude ranking and a global threshold segmentation operator, to further improve the performance. This improved LBP achieves excellent texture classification accuracy across six common datasets, with an average of 1% lower than the best LBP variants. Meanwhile, the computational complexity of the proposed improved LBP is several times lower than that of the best LBP variants.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Tong Zhang, Yuan Zong, Wenming Zheng, C. L. Philip Chen, Xiaopeng Hong, Chuangao Tang, Zhen Cui, Guoying Zhao
Summary: This paper discusses the challenges and importance of cross-database micro-expression recognition (CDMER) and contributes to this field by establishing an evaluation protocol, conducting benchmark experiments, and proposing a novel DA method.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Xiaohua Huang, Abhinav Dhall, Roland Goecke, Matti Pietikainen, Guoying Zhao
Summary: This article proposes a new method to effectively analyze group behavior and emotion from a group-level image, using a combination of global alignment kernels and support vector machine. The distance between two group-level images is measured using a global alignment kernel, and a global weight sort scheme is used to optimize the performance of the kernel. Experimental results demonstrate promising performance for group-level emotion recognition.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Beijing Chen, Xin Liu, Yuhui Zheng, Guoying Zhao, Yun-Qing Shi
Summary: This paper presents experimental findings on detecting post-processed GAN-generated face images and proposes a new method to improve detection performance and robustness.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Haitao Zhang, Beijing Chen, Jinwei Wang, Guoying Zhao
Summary: In this paper, an effective local perturbation generation method is proposed to expose the vulnerability of state-of-the-art forensic detectors for GAN-generated faces. The method mines the common areas of concern in multiple detectors' decision-making and generates local anti-forensic perturbations using GANs to enhance the visual quality and transferability of anti-forensic faces. Experimental results demonstrate the method's advantage over the state-of-the-art methods in terms of anti-forensic success rate, imperceptibility, and transferability.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao
Summary: Hyperbolic deep neural networks (HDNNs) have shown superior performance and better physical interpretability in hierarchical structured data, and have been widely applied in different scientific fields. This paper provides a comprehensive review of the neural components in HDNN, demonstrating the potential of extending leading deep approaches to hyperbolic space and applications in various tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Dengxin Dai, Arun Balajee Vasudevan, Jiri Matas, Luc Van Gool
Summary: This work develops an approach for scene understanding purely based on binaural sounds, which can predict the semantic masks, motion, and depth of sound-making objects. By leveraging cross-modal distillation and spatial sound super-resolution, the performance of auditory perception tasks is significantly improved. Experimental results show good performance in all tasks, mutual benefits between tasks, and importance of microphone quantity and orientation.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Guoying Zhao, Xiaobai Li, Yante Li, Matti Pietikainen
Summary: Micro-expression (ME) is an involuntary, fleeting, and subtle facial expression that can provide essential clues to people's true feelings. In recent years, ME analysis, especially automatic ME analysis in computer vision, has gained much attention due to its practical importance. This survey provides a comprehensive review of ME development in the field of computer vision, discussing various computational ME analysis methods and future directions.
PROCEEDINGS OF THE IEEE
(2023)
Article
Computer Science, Artificial Intelligence
Sajid Javed, Martin Danelljan, Fahad Shahbaz Khan, Muhammad Haris Khan, Michael Felsberg, Jiri Matas
Summary: Accurate and robust visual object tracking is a challenging problem in computer vision. This survey reviews more than 90 Discriminative Correlation Filters (DCFs) and Siamese trackers, based on results in nine tracking benchmarks. It presents the background theory, research challenges, and performance analysis of both DCFs and Siamese trackers, and provides recommendations for future research.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Zitong Yu, Yunxiao Qin, Xiaobai Li, Chenxu Zhao, Zhen Lei, Guoying Zhao
Summary: This paper presents the first comprehensive review of recent advances in deep learning based face anti-spoofing (FAS), including pixel-wise supervision, domain generalization, and multi-modal sensors. It aims to stimulate future research in the field.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Kaijie Ma, Yifan Feng, Beijing Chen, Guoying Zhao
Summary: Synthetic speech attacks pose a great threat to ASV systems. A Dual-Branch Network is proposed, using LFCC and CQT as inputs, to enhance the generalization ability for attacks generated by unknown synthesis algorithms. The system outperforms existing state-of-the-art systems and shows good generalization for unknown forgery types.
IEEE SIGNAL PROCESSING LETTERS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Vasyl Borsuk, Roman Vei, Orest Kupyn, Tetiana Martyniuk, Igor Krashenyi, Jiri Matas
Summary: We introduce FEAR, a family of efficient Siamese visual trackers that achieve high accuracy and robustness. By incorporating dual-template representation and pixel-wise fusion block, FEAR trackers outperform most Siamese trackers in terms of accuracy and efficiency. The optimized version, FEAR-XS, offers significantly faster tracking while maintaining near state-of-the-art results.
COMPUTER VISION, ECCV 2022, PT XXII
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tetiana Martyniuk, Orest Kupyn, Yana Kurlyak, Igor Krashenyi, Jiri Matas, Viktoriia Sharmanska
Summary: This paper presents a dense and diverse large-scale dataset, DAD-3DHeads, as well as a robust model for 3D Dense Head Alignment in-the-wild. The dataset contains annotations of over 3.5K landmarks that accurately represent 3D head shape. The data-driven model, DAD-3DNet, learns shape, expression, and pose parameters, and performs 3D reconstruction of a FLAME mesh.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoyan Xing, Yanlin Qian, Sibo Feng, Yuhan Dong, Jiri Matas
Summary: In this paper, we propose PCCC, an algorithm for illumination chromaticity estimation using point clouds. By leveraging depth information from a ToF sensor and RGB intensities, PCCC applies the PointNet architecture to derive the illumination vector and make a global decision about the global illumination chromaticity. PCCC outperforms state-of-the-art algorithms on popular RGB-D datasets and a novel benchmark, with a simple and fast method that requires a small input size.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yash Patel, Giorgos Tolias, Jiri Matas
Summary: This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach. The suggested method achieves state-of-the-art performance in several image retrieval benchmarks when used for deep metric learning.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Computer Science, Artificial Intelligence
Muhterem Dindar, Sanna Jarvela, Sara Ahola, Xiaohua Huang, Guoying Zhao
Summary: This article explores the potential of emotional mimicry in identifying leader and follower students in collaborative learning settings. The findings suggest that video-based facial emotions recognition combined with cross-recurrence quantification analysis can accurately identify leaders and followers. This research highlights the importance of using these methods in collaborative learning research and their ability to explain social and affective dynamics within the setting.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)