An app for segmentation and classification of images of cells from optical microscope. This project uses marker controlled watershed (openCv), and pretrained ResNet-50 model (tensorflow) ...

With the ongoing surge in global coastal development, understanding shoreline dynamics has become a critical issue, given the inherent vulnerability of coastal fringes to significant mobility.

This thesis focuses on leveraging Image Processing, Computer Vision, Machine Learning, and Deep Learning, particularly the Vision Transformer (ViT) model, for early identification of Alzheimer’s ...

ABSTRACT: Clustering is an unsupervised machine learning technique used to organize unlabeled data into groups based on similarity. This paper applies the K-means and Fuzzy C-means clustering ...

Introduction: Deep learning has significantly advanced medical image analysis, enabling precise feature extraction and pattern recognition. However, its application in computational material science ...

"How to crop an image is a decision best made by people." After social media exploded with allegations that Twitter's image-cropping algorithm had a racial bias, the company said it investigated and ...

This project implements three image segmentation algorithms - Region Growing, Watershed, and K-Means, to separate an object from its background, evaluated using the Jaccard Similarity Coefficient.

Abstract: In image processing, due to the presence of noise or other unpredictable interference factors, the use of traditional watershed algorithms often results in excessive segmentation. In order ...