Article
Biochemical Research Methods
Bryan Herrera-Romero, Diego Almeida-Galarraga, Graciela M. Salum, Fernando Villalba-Meneses, Marco Esteban Gudino-Gomezjurado
Summary: This paper reports the development of an informatics tool based on computer vision for processing and analysis of digital images to analyze the expression of the GUS signal in A. thaliana roots. The tool provides quantitative results of image intensity levels, allowing researchers to understand how plants modify their hormonal pathways depending on environmental conditions.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Chemistry, Multidisciplinary
Marcelo Leite, Wemerson Delcio Parreira, Anita Maria da Rocha Fernandes, Valderi Reis Quietinho Leithardt
Summary: This paper proposes a method that can segment skin and non-skin pixels in digital images from uncontrolled or unknown environments, overcoming challenges such as lighting conditions, compression, and scene complexity.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Yushun Zhang, Fuzhu Han
Summary: This paper presents the development of an on-machine inspection system for cutting edge dimensions of PCD tools. The system establishes a method to obtain the surface of rotation (SOR) generatrix and calculates the shapes and dimensions of the cutting edges based on the axis equation of the tool shank. Experimental results validate the potential of the proposed system.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Engineering, Multidisciplinary
Yusheng Wang, Zhixiang Huang, Pengfei Zhu, Rui Zhu, Tianci Hu, Dahai Zhang, Dong Jiang
Summary: Digital image correlation (DIC) accurately measures subpixel displacement field based on speckle images. To address the high data transmission and storage requirements caused by extensive high-resolution images, a framework combining image compression techniques with DIC methods is proposed. The framework reduces the memory footprint of images while preserving the primary speckle features with subpixel errors.
Article
Computer Science, Artificial Intelligence
Lukasz Karbowiak, Janusz Bobulski
Summary: This article introduces the importance of background segmentation and proposes a method to compare algorithms under severe weather conditions. Through testing in different weather conditions, interesting differences in detail detection and detection noise were observed.
PEERJ COMPUTER SCIENCE
(2022)
Article
Engineering, Industrial
Ru Yang, Yang Li, Danielle Zeng, Ping Guo
Summary: Traditional digital image correlation (DIC) methods have limitations in dealing with large deformations and poor speckle pattern quality. To overcome these challenges, we propose a new deep learning-based DIC approach, Deep DIC, which achieves accurate, robust, and real-time displacement and strain prediction in experiments.
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY
(2022)
Article
Chemistry, Analytical
Jannis Holtkotter, Rita Amaral, Rute Almeida, Cristina Jacome, Ricardo Cardoso, Ana Pereira, Mariana Pereira, Ki H. Chon, Joao Almeida Fonseca
Summary: Long-term adherence to medication is crucial for managing chronic diseases, but current objective tools for tracking adherence are lacking or inconvenient. To address this issue, a pill intake detection tool was developed using digital image processing. The tool showed promising results in detecting the presence of round pills.
Review
Food Science & Technology
Hanieh Amani, Katalin Badak-Kerti, Amin Mousavi Khaneghah
Summary: The smartphone has gained attention in food quality assessment due to its high-resolution cameras and programmability. It shows potential as a nondestructive technique for quality control, but challenges in implementation and industrialization remain.
CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION
(2022)
Article
Computer Science, Artificial Intelligence
Rui Dou, Jiawen Li, Xujie Wan, Heyou Chang, Hao Zheng, Guangwei Gao
Summary: The article introduces an architecture called the Decoder Structure Guided CNN-Transformer Network (DCTNet) for face image super-resolution. DCTNet utilizes a decoder structure as its backbone, focusing primarily on Global-Local Feature Extraction Units (GLFEU).
IET COMPUTER VISION
(2023)
Article
Computer Science, Artificial Intelligence
Farzane Maghsoudi Ghombavani, Mohammad Javad Fadaeieslam, Farzin Yaghmaee
Summary: This paper introduces a generative adversarial network model called ARDA-UNIT, which aims to tackle the challenges of image-to-image translation by generating images close to the target domain while preserving important features of the source domain. The model enhances its generating capability and reduces training parameters by applying a recurrent dense self-attention module in the generator latent space. Experimental results demonstrate that the model achieves better qualities by reducing computational loads, transferring structures effectively, and improving evaluation criteria such as FID, KID, and IS.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Fugang Liu, Songnan Duan, Wang Juan
Summary: In this study, a deep learning-based method for pedestrian trajectory prediction is proposed. The method combines YOLOv7, StrongSORT, and improved LSTM algorithm to solve the problems of target switch and jump, and improves the prediction performance.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Hao Zhang, Yan Piao, Nan Qi
Summary: The authors propose a novel Transformer-based tracker that fuses spatial and temporal features, achieving comprehensive feature extraction and improved information interaction. The tracker achieves state-of-the-art results on multiple benchmark datasets.
IET COMPUTER VISION
(2023)
Article
Computer Science, Artificial Intelligence
Lingbing Meng, Mengya Yuan, Xuehan Shi, Le Zhang, Qingqing Liu, Dai Ping, Jinhua Wu, Fei Cheng
Summary: An end-to-end framework for RGB-D salient object detection (SOD) is proposed, which includes multiple modules for feature enhancement, contextual feature interaction, boundary feature extraction, and boundary attention guidance. The proposed model outperforms state-of-the-art RGB-D SOD models on multiple evaluation metrics.
IET COMPUTER VISION
(2023)
Article
Computer Science, Artificial Intelligence
Zhanqiang Huo, Yanan Wang, Yingxu Qiao, Jing Wang, Fen Luo
Summary: Crowd counting is crucial in computer vision, aiming to estimate the number of people in an image. By regressing density maps, researchers have greatly improved the counting accuracy in recent years. However, due to domain shift, models trained on richly labeled datasets (source domain) do not perform well on datasets with limited labels (target domain). To address this issue, a novel dynamic scale aggregation network (DSANet) is proposed to bridge the gap in style and cross-domain head scale variations.
IET COMPUTER VISION
(2023)
Article
Environmental Sciences
William Yamada, Wei Zhao, Matthew Digman
Summary: An automatic method using monovision un-crewed aerial vehicle imagery was developed to obtain geographic coordinates of bales, with YOLOv3 algorithm identified as the best option in terms of accuracy and speed. Lowering image quality resulted in decreased performance.