Results 61 to 70 of about 9,112 (254)

Uncertainty‐Guided Selective Adaptation Enables Cross‐Platform Predictive Fluorescence Microscopy

Advanced Intelligent Discovery, EarlyView.
Deep learning models often fail when transferred to new microscopes. A novel framework overcomes this by selectively adapting the early layers governing low‐level image statistics, while freezing deep layers that encode morphology. This uncertainty‐guided approach enables robust, label‐free virtual staining across diverse systems, democratizing ...
Kai‐Wen K. Yang, Andrew Bai, Alexandra Bermudez, Yunqi Hong, Zoe Latham, Iris Sloan, Michael Liu, Vishrut Goyal, Cho‐Jui Hsieh, Neil Y. C. Lin   +9 more
wiley   +1 more source

Detecting Image Splicing Using Merged Features in Chroma Space

The Scientific World Journal, 2014
Image splicing is an image editing method to copy a part of an image and paste it onto another image, and it is commonly followed by postprocessing such as local/global blurring, compression, and resizing.
Bo Xu, Guangjie Liu, Yuewei Dai
doaj   +1 more source

AI‐BioMech: Deep Learning Prediction of Mechanical Behavior in Aperiodic Biological Cellular Materials

Advanced Intelligent Discovery, EarlyView.
AI‐BioMech is a deep learning framework that predicts the mechanical behavior of biological cellular materials directly from 2D images. By replacing traditional finite element analysis with semantic segmentation, it identifies stress and strain distributions with 99% accuracy, offering a high‐speed, scalable alternative for analyzing complex, aperiodic
Haleema Sadia, Marcelo A. Dias, Parvez Alam   +2 more
wiley   +1 more source

No-Reference Image Quality Assessment Combining Swin-Transformer and Natural Scene Statistics

Sensors
No-reference image quality assessment aims to evaluate image quality based on human subjective perceptions. Current methods face challenges with insufficient ability to focus on global and local information simultaneously and information loss due to ...
Yuxuan Yang, Zhichun Lei, Changlu Li
doaj   +1 more source

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni, Md. Alif Sheakh, Mst. Sazia Tahosin, Md. Zahid Hasan, Taslima Ferdaus Shuva, Touhid Bhuiyan, Muhammad Ali Abdullah Almoyad, Nabil Anan Orka, Md. Tanvir Rahman, Risala Tasin Khan, M. Shamim Kaiser, Mohammad Ali Moni   +11 more
wiley   +1 more source

MDSC: Unsupervised Multipath Decomposition and Synergistic Correction for Efficient Low‐Light Image Enhancement with Detail‐Aware Smoothing

Advanced Intelligent Systems, EarlyView.
This work proposes MDSC, an unsupervised low‐light enhancement framework integrating three core innovations: detail‐aware smoothing, multipath decomposition, and synergistic correction. It suppresses noise, handles rapid illumination variations, and prevents reflectance‐contrast amplification inherent to Retinex separation.
Yong Cheng, De Yu, Yongqi Yuan, Mengjie Ye, Huan Wang, Qian Zhang, Ge Jin   +6 more
wiley   +1 more source

An Adaptive Image Resizing Algorithm in DCT Domain

IEICE Transactions on Information and Systems, 2007
A novel image resizing algorithm is proposed. In our method, three steps are included in the downsampling: the first-round downsampling, the interim upsampling and the second-round downsampling. The downsampling operation unit size is selected between one single 16 × 16 block size and four 8 × 8 block sizes during the first-round downsampling ...
Hai-Feng Xu, Song-Yu Yu, Ci Wang
openaire   +1 more source

Enhanced Monocular Depth Estimation Using ResNet Backbone and Multiscale Feature Decoding for Precise Object Distance Measurement

Advanced Intelligent Systems, EarlyView.
A lightweight monocular perception framework generates high‐fidelity depth maps and integrates YOLOv8 detection to estimate object‐wise distances from a single RGB image. Evaluated on KITTI and the proposed D‐Far250 dataset, the system demonstrates accurate long‐range perception up to 250 m while maintaining real‐time performance, enabling scalable ...
Faseeh Muhammad, Misbah Bibi, Murad Ali Khan, Syed Shehryar Ali Naqvi, Adnan Ejaz Muhammad, Do-Hyeun Kim   +5 more
wiley   +1 more source

Resizing image uploads in Django

, 2022
It should be an easy task to resize image uploads in Django, but it turns out to be a bit more complicated than one would hope. Here are my findings.
openaire   +2 more sources

Diabetic Retinopathy Classification With Convolutional Neural Networks Designed by the Fuzzy Grey Wolf Optimizer With Parameter Adaptation

AI &Innovation, EarlyView.
ABSTRACT The detection and classification of diseases have become a field of interest for artificial intelligence in recent years, where the development of methods and models that allow support for specialists in different health fields has allowed early detection of diseases and the provision of timely treatment to patients.
Rodrigo Cordero‐Martínez, Daniela Sánchez, Patricia Melin   +2 more
wiley   +1 more source