Article
Computer Science, Hardware & Architecture
Xin Liao, Jiaojiao Yin, Mingliang Chen, Zheng Qin
Summary: This article introduces the application of multiple image steganography in the era of cloud storage, discusses payload distribution strategies for enhancing security performance, and provides supporting evidence through experiments.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Computer Science, Information Systems
Jehyeok Rew, Hyungjoon Kim, Eenjun Hwang
Summary: This study proposed a hybrid segmentation scheme for objectively evaluating skin conditions, achieving significant improvements compared to traditional handcraft-based methods. The scheme utilized Deeplab v3+, LightGBM, and morphological processing to enhance pixel segmentation quality and determine skin features accurately.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Chemistry, Multidisciplinary
Kenta Iwai, Hiromu Suzuki, Takanobu Nishiura
Summary: This paper proposes a method for three-dimensional sound image reproduction based on spherical harmonic expansion. The method allows for control of both the direction and distance of the sound image, and can be applied to 22.2 multichannel audio systems.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
E. M. O. Silveira, A. M. Pidgeon, L. S. Farwell, M. L. Hobi, E. Razenkova, B. Zuckerberg, N. C. Coops, V. C. Radeloff
Summary: The dynamic habitat indices (DHIs) derived from satellite data capture patterns of vegetative productivity and are a good predictor of bird species richness. Multi-grain habitat measures obtained from different satellite sensors and data resolutions have better predictive power for bird species richness than high-resolution data derived from resampling. This study highlights the value of DHIs derived from high-resolution satellite data and the potential of multi-resolution remotely-sensed vegetation productivity measures for quantifying biodiversity.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Computer Science, Artificial Intelligence
Wei Gao, Yangming Wu, Cui Hong, Rong-Jong Wai, Cheng-Tao Fan
Summary: This paper proposes a new bird damage recognition network, RCVNet, which addresses the issue of environmental interference in identifying birds around power towers using cameras alone by fusing radio-frequency (RF) images and visual images. The network accurately identifies bird damages in the monitoring area by employing a feature layer fusion approach and incorporating various improved modules and strategies. The experiments conducted using a newly gathered bird dataset called CRB2022 demonstrate that RCVNet achieves a high precision and recall rate in bird identification and an excellent discrimination rate in bird damage recognition.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Chemical
Min Tian, Maojin Tan, Min Wang
Summary: In this study, a method combining the GLCM and RF algorithms is proposed to classify shale lithofacies with different sedimentary structures based on FMI imaging logging and ECS logging. The optimized model achieves favorable performance on training data, validation data, and test data.
Article
Computer Science, Artificial Intelligence
Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
Summary: In this paper, an unsupervised deep image stitching framework was proposed to address the limitations of traditional feature-based image stitching technologies and learning-based methods. The framework consists of two stages aimed at coarse image alignment and image reconstruction. Extensive experiments demonstrate the superiority of the proposed method over other state-of-the-art solutions, with users preferring the image stitching quality even compared to supervised solutions.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Forestry
Cong Li, Qiang Liu, Binrui Li, Luying Liu
Summary: A method for image recognition and classification of forest fires based on fusion of color and textural features was studied. The suspected fire region was first segmented using the fusion RGB-YCbCr color spaces, followed by extraction of textural features using local binary pattern (LBP) and gray-level co-occurrence matrix (GLCM) algorithms. A database of forest fire textural feature vectors was constructed, and recognition of forest fires was achieved using a support vector machine (SVM). The method achieved a recognition rate of 93.15% for forest fires and demonstrated strong robustness in distinguishing fire-like interference.
Article
Computer Science, Information Systems
Subhajit Paul, Deepak Mishra
Summary: This paper explores a new technique of using deep neural networks to hide images within audio, optimizing the perceptual quality of the reconstructed audio and image using mel-spectrogram as the cover medium. The proposed method is robust to different color spectrum images.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Psychology, Multidisciplinary
Koichi Yamagata, Jinhwan Kwon, Takuya Kawashima, Wataru Shimoda, Maki Sakamoto
Summary: Researchers developed a computer vision method using deep convolutional neural networks (DCNN) to express the texture of materials. By focusing on Japanese sound-symbolic words that describe differences in texture sensations, they achieved a certain degree of success.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Forestry
Jyrki Savolainen
Summary: This paper proposes a method for tracking wooden veneer sheets by matching their wet and dry colour images. The method involves image segmentation, extraction of GLCM textural feature arrays, and similarity comparisons. A voting mechanism is introduced for determining the correct match, and an optional shifting procedure is applied for candidates with missing areas. The proposed method achieves a matching accuracy of 99.41% on a real-world dataset, outperforming previous studies and offering practical implications for automated veneer production facilities.
EUROPEAN JOURNAL OF WOOD AND WOOD PRODUCTS
(2023)
Article
Computer Science, Artificial Intelligence
Lucas Jose Cruz de Mendonca, Ricardo Jose Ferrari
Summary: This study proposes a new technique for MR image classification in AD diagnosis using graph kernels constructed from texture features extracted from sMR images. The results show better performance for CNxAD and CNxMCI classifications, but worse for MCIxAD classification.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Ecology
Marcos Cruz, Javier Gonzalez-Villa, Josee Lefebvre, Scott Gilliland, Francis St-Pierre, Matthew English, Christine Lepage
Summary: The ECA Flocks data set consists of manually annotated images of Common Eider and Greater Snow Geese, taken from different surveys in Eastern Canada, to test the precision of the CountEm flock size estimation method. The data set includes a wide range of images with varying quality, resolution, and flock sizes, making it suitable for evaluating methods for estimating animal abundance through imagery analysis.
Article
Computer Science, Information Systems
Ohini Kafui Toffa, Max Mignotte
Summary: This paper introduces a new approach for environmental sound classification using LBP texture features and audio features collaboration, outperforming classical methods. The mixed model of LBP features with audio descriptors achieved state-of-the-art results, surpassing traditional methods and some convolutional neural network-based approaches.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
M. Poongodi, Mounir Hamdi, Huihui Wang
Summary: This paper proposes a computer-based image recognition method that automatically generates appropriate titles and adds specific sounds to images. By training and combining two models, a high level of accuracy has been achieved.
MULTIMEDIA SYSTEMS
(2023)
Article
Ecology
Benjamin L. Gottesman, Dante Francomano, Zhao Zhao, Kristen Bellisario, Maryam Ghadiri, Taylor Broadhead, Amandine Gasc, Bryan C. Pijanowski
FRESHWATER BIOLOGY
(2020)
Article
Ecology
Kristen M. Bellisario, Jack VanSchaik, Zhao Zhao, Amandine Gasc, Hichem Omrani, Bryan C. Pijanowski
ECOLOGICAL INFORMATICS
(2019)
Article
Biodiversity Conservation
Zhao Zhao, Zhi-yong Xu, Kristen Bellisario, Rui-wen Zeng, Ning Li, Wen-yang Zhou, Bryan C. Pijanowski
ECOLOGICAL INDICATORS
(2019)
Review
Computer Science, Information Systems
Luciano Mengarelli, Bruno Kostiuk, Joao G. Vitorio, Maicon A. Tibola, William Wolff, Carlos N. Silla
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Rodolfo M. Pereira, Yandre M. G. Costa, Carlos N. Silla Jr
Article
Engineering, Biomedical
Yi Zhang, Zhao Zhao, Hui-jie Xu, Chong He, Hao Peng, Zhan Gao, Zhi-yong Xu
BIO-MEDICAL MATERIALS AND ENGINEERING
(2020)
Article
Acoustics
Loris Nanni, Yandre M. G. Costa, Rafael L. Aguiar, Rafael B. Mangolin, Sheryl Brahnam, Carlos N. Silla Jr
EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING
(2020)
Article
Computer Science, Interdisciplinary Applications
Rodolfo M. Pereira, Diego Bertolini, Lucas O. Teixeira, Carlos N. Silla Jr, Yandre M. G. Costa
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2020)
Article
Engineering, Electrical & Electronic
Ziyi Wang, Zhao Zhao, Zhiyong Xu
Summary: Microphone arrays are widely used in practical applications, but frequency response mismatches among channels can negatively impact performance. Existing calibration methods have varying accuracy and suffer from passband bandwidth shrinkage. To address these issues, we propose a novel calibration method based on the Newton algorithm.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Zhao Zhao, Hongrui Kan, Jiale Lin, Zhiyong Xu
Summary: In this article, a DOA estimation algorithm for multiple speech sources based on flexible SSZs and concentration weighting is proposed. The algorithm identifies single-source points using correlation coefficients of time delay vectors across adjacent frequency bins and constructs flexible SSZs. The number of single-source points in each flexible SSZ is considered as a weighting factor to form the pooled histogram. A matching pursuit-based approach is used to obtain multisource DOA estimates. Simulation results and real-world experiments demonstrate the effectiveness and improved performance of the proposed method.
IEEE SENSORS JOURNAL
(2023)
Article
Biodiversity Conservation
Zhi-yong Xu, Lei Chen, Bryan C. Pijanowski, Zhao Zhao
Summary: This article discusses the application of passive acoustic monitoring (PAM) in soundscape ecology and the importance of acoustic indices. However, existing acoustic indices are susceptible to noise. To address this issue, a revised acoustic diversity index (FADI) is proposed, which is less affected by noise compared to the original index.
ECOLOGICAL INDICATORS
(2023)
Article
Computer Science, Information Systems
Rafael B. Mangolin, Rodolfo M. Pereira, Alceu S. Britto, Carlos N. Silla, Valeria D. Feltrim, Diego Bertolini, Yandre M. G. Costa
Summary: This paper addresses the multi-label classification of movie genres using a multimodal approach. A large dataset is created, consisting of various sources of information, and different descriptors and classifiers are used for experimental evaluation. The results demonstrate the complementarity among classifiers trained on different sources of information in movie genre classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Proceedings Paper
Engineering, Civil
Zijun Xu, Zhao Zhao, Edmund Sowah
Summary: A novel vehicle speed measurement method based on differential beamforming techniques is proposed in this paper, which shows lower cost and reduced computational complexity. Experimental results demonstrate better accuracy and performance in vehicle speed estimation.
INTERNATIONAL CONFERENCE ON SMART TRANSPORTATION AND CITY ENGINEERING 2021
(2021)
Proceedings Paper
Automation & Control Systems
Muhammad Amjad Iqbal, Zhao Zhao, Xu ZhiYong, Saad Ur Rehman
2020 6TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, CONTROL AND ROBOTICS (EECR 2020)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Bruno Kostiuk, Yandre M. G. Costa, Alceu S. Britto Jr, Xiao Hu, Carlos N. Silla Jr
2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019)
(2019)