8 results · ● Live web index
techscience.com article

CMC | Special Issues: Deep Learning: Emerging Trends, Applications and Research Challenges for Image Recognition

https://www.techscience.com/cmc/special_detail/image_recognition

Home / Journals / CMC / Special Issue / Deep Learning: Emerging Trends, Applications and Research Challenges for Image Recognition. # Deep Learning: Emerging Trends, Applications and Research Challenges for Image Recognition. **Research Interests:** artificial intelligence, deep learning, machine learning, big data, image recognition. The field of computer vision and image processing has seen advances continually thanks to innovation in deep learning. Convolution Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Network (GNN), Long Short-Term Memory (LSTM), etc., are a few deep learning algorithms that achieve significant success in computer vision and image processing. This special issue aims to bring together all the potential research scholars worldwide to contribute and submit their original research articles that include algorithms, architecture, and empirical results for computer vision and image recognition applications using deep learning and AI-related technologies. • Deep Learning-based feature extraction for computer vision and image processing. Artificial Intelligence, Deep Learning, Machine Learning, Image Recognition, Image Processing, Computer Vision.

Visit
preprints.org article

Developments in Deep Learning Artificial Neural Networks Techniques for Medical Image Analysis and Interpretation[v1] | Preprints.org

https://www.preprints.org/manuscript/202504.0449/v1

This article explores recent developments in deep learning techniques applied to medical imaging, including Convolutional Neural Networks (CNNs) for classification and segmentation, Recurrent Neural Networks (RNNs) for temporal analysis, Autoencoders for feature extraction, and Generative Adversarial Networks (GANs) for image synthesis and augmentation. Generative adversarial networks (GANs) are groups of deep learning artificial neural networks that can be used for generating synthetic medical images, data augmentation, and improving image resolution. The U-shaped architectures with skip connections help to delineate objects in images, making it highly effective in medical image analysis, particularly in tasks like tumors detection, organ delineation, and segmentation of medical images from various modalities and they have been widely embraced variants among the many different deep learning networks [52]. Despite the significant successes recorded in the enhancement of the diagnostic accuracy of deep learning models such as CNN, RNN and U-Net in the classification and segmentation of medical images, there have remained some limitations. A low resource 3D U-Net based deep learning model for medical image analysis.

Visit
ijcaonline.org article

Deep Learning for Image Analysis: Trends, Challenges, and Future Directions

https://ijcaonline.org/archives/volume187/number9/deep-learning-for-image-ana…

##### Random Articles. ###### Reseach Article. ### Deep Learning for Image Analysis: Trends, Challenges, and Future Directions. | International Journal of Computer Applications |. Deep Learning for Image Analysis: Trends, Challenges, and Future Directions. International Journal of Computer Applications. We Only Look Once (YOLO), and hybrid models have achieved significant results—CNN-based diagnostic tools now surpass 95% accuracy in detecting cancers, while YOLO variants carry out real-time detection at over 30 FPS with high precision. In the field of image forensics, deep learning models can detect splicing and copy-move forgeries with an accuracy of over 90% by extracting fine-grained artifacts invisible to the human eye. Techniques like transfer learning and data augmentation partially improve results on smaller datasets, while Explainable AI (XAI) methods—such as Grad-CAM and SHAP—are becoming essential for model transparency, interpretability, and trustworthiness. Current research is focused on enhancing model-generalizability, interpretability, and fostering interdisciplinary collaboration. As these challenges are progressively overcome, deep learning is expected to fully unlock its transformative potential across diverse image-processing domains. ###### This digital library is running on.

Visit