Search
5 articles for “low-label learning”
-
Self-Supervised Learning for Early Disease Detection in Low-Label Medical Image Datasets
Abstract: Getting reliable labeled data for medical image analysis is genuinely difficult. Radiologists, pathologists, and other specialist clinicians are expensive, slow, and not universally available — particularly in low-resource clinical environments across developing nations. Unlike natural image benchmarks such as ImageNet, which provide millions of meticulously labeled training examples, most publicly accessible medical imaging repositories offer only a few hundred to a few thousand annotated scans. Supervised deep learning models trained …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 13, Issue 3, 2026 Read article
-
AI-Powered Emotion Recognition in Dog
Abstract: Understanding animal emotions is important for improving veterinary care, human animal interaction, and overall pet well-being. Inspired by previous research that utilized a modified EfficientNetB5 model for emotion classification in cats and dogs, our study builds upon this foundation with a focus on real-time emotion recognition in dogs. While earlier approaches achieved high accuracy using Dense Residual and Squeeze-and-Excitation blocks, they often lacked real-time applicability and were not optimized for …
Published in International Journal of Machine Systems and Manufacturing Technology · Vol. 4, Issue 1, 2026 · pp. 20–32 Read article
-
Review on CBIR Image Based on Colour, Texture and Shape Features of Biomedical Image Applications
Abstract: This study seeks to understand how different image enhancing methods affect the sensitivity of contrast-based textural measures and morphological traits derived from high-resolution satellite data (three-band SPOT-5). The built-up/non-built-up detection framework is the backbone of every biomedical application. Using supervised learning while working with a low-resolution reference layer reduces uncertainty and boosts the reference layer's quality in a roundabout way. The image's histogram is recalculated based on contrast in order …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 1, 2024 · pp. 8–13 Read article
-
Traffic Density Estimation Using Image Frames in Python
Abstract: Traffic congestion is a critical challenge in modern urban environments, leading to significant delays, environmental pollution, and increased accident rates. With the rapid growth of vehicle populations in metropolitan areas worldwide, the need for intelligent and automated traffic monitoring systems has become increasingly urgent. Traditional monitoring approaches, such as inductive loop detectors and manual surveillance, are limited in scalability, deployment cost, and adaptability to dynamic traffic scenarios. This paper presents …
Published in Trends in Transport Engineering and Applications · Vol. 13, Issue 2, 2026 · pp. 38–45 Read article
-
A Comparative Study of Transfer Learning-Based Deep Learning Models for Breast Cancer Detection
Abstract: Breast cancer is a major concern in the world today, and early and accurate diagnosis is most crucial in the case of breast cancer, as it is among the disorders where the total cost of loss of life is high. Traditional screening processes are subjective and vulnerable to inter-observer reliability issues and diagnostic errors, being primarily based on manual interpretation of medical images. To address these limitations, Deep Learning (DL) …
Published in Research and Reviews : A Journal of Medical Science and Technology · Vol. 15, Issue 1, 2026 · pp. 24–34 Read article