Results 41 to 50 of about 17,494 (194)

TriCrackNet: Trilateral Segmentation Network for Real‐Time Crack Segmentation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT To achieve high‐precision real‐time crack segmentation, we propose TriCrackNet, an efficient network based on a tri‐branch collaborative architecture incorporating boundary constraints, semantic parsing, and spatial refinement. In the semantic branch, efficient atrous spatial pyramid pooling (EASPP) is integrated.
Haixin Jia, Han Wang, Xiaoqiang Shi, Guoying Zhang, Hanqi Jiang, Jianbo Peng   +5 more
wiley   +1 more source

Behind the Mask: Detection and Recognition Based-on Deep Learning

IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 2022
COVID-19 prevention procedures are executed to support public services and business continuity in a pandemic situation. Manual mask use monitoring is not efficient as it requires resources to monitor people at all times.
Ade Nurhopipah, Irfan Rifai Azziz, Jali Suhaman   +2 more
doaj   +1 more source

EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devices

, 2019
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring.
Almeida, Mario, Lane, Nicholas D., Laskaridis, Stefanos, Leontiadis, Ilias, Venieris, Stylianos I.   +4 more
core   +1 more source

Demand Estimation with Text and Image Data

The RAND Journal of Economics, EarlyView.
ABSTRACT We propose a demand estimation approach that leverages unstructured data to infer substitution patterns. Using pre‐trained deep learning models, we extract embeddings from product images and textual descriptions and incorporate them into a mixed logit demand model.
Giovanni Compiani, Ilya Morozov, Stephan Seiler   +2 more
wiley   +1 more source

Textile and colour defect detection using deep learning methods

Coloration Technology, EarlyView.
Abstract Recent advances in deep learning (DL) have significantly enhanced the detection of textile and colour defects. This review focuses specifically on the application of DL‐based methods for defect detection in textile and coloration processes, with an emphasis on object detection and related computer vision (CV) tasks.
Hao Cui, Abdel‐Fattah Seyam, Renzo Shamey   +2 more
wiley   +1 more source

Implementation of AlexNet and Xception Architectures for Disease Detection in Orange Plants

Journal of Applied Informatics and Computing
Oranges are one of Indonesia's primary horticultural commodities, with production increasing each year. However, pest and disease infestations often go undetected, leading to significant reductions in crop yields.
Venus Al Fatah, Moh. Ali Romli
doaj   +1 more source

One-Shot Learning with Pseudo-Labeling for Cattle Video Segmentation in Smart Livestock Farming

Animals, 2022
Computer vision-based technologies play a key role in precision livestock farming, and video-based analysis approaches have been advocated as useful tools for automatic animal monitoring, behavior analysis, and efficient welfare measurement management ...
Yongliang Qiao, Tengfei Xue, He Kong, Cameron Clark, Sabrina Lomax, Khalid Rafique, Salah Sukkarieh   +6 more
doaj   +1 more source

Artificial Intelligence in Periodontology: A Systematic Review

Journal of Periodontal Research, EarlyView.
AI shows promise across periodontology, with deep learning achieving strong performance for image‐based diagnosis of periodontitis. However, limited data diversity, inconsistent metrics, and scarce external validation raise concerns about generalizability and clinical applicability.
Antonin Tichy, Nils Werner, Helena Dujic, Charlotte Wetzel, Vinay Pitchika, Caspar Victor Bumm, Matthias Folwaczny, Falk Schwendicke   +7 more
wiley   +1 more source

Automated Tuberculosis Detection in Chest Radiographs: A Hybrid Deep Learning Framework for Clinical Decision Support

Applied AI Letters, Volume 7, Issue 2, June 2026.
A hybrid deep learning framework integrating VGG16, ResNet50, and DenseNet121 is proposed for automated tuberculosis detection from chest X‐ray images. Feature‐level fusion enhances robustness and generalization, achieving 97.4% accuracy across multiple public datasets, supporting reliable clinical decision‐making in resource‐limited healthcare ...
Md. Tahmid Hossain, Hrittik Mural, Monowar Wadud Hridoy   +2 more
wiley   +1 more source

Classification Of Mustard Leaf Diseases Using Convolutional Neural Network Architecture

Journal of Electrical Engineering and Computer
Diseases in mustard leaves can reduce productivity if not detected early. This study aims to develop and evaluate a disease classification system for mustard leaves using Convolutional Neural Network (CNN) architectures, specifically Xception and VGG19 ...
M. Hafidurrohman, K Kusrini
doaj   +1 more source