segmentation-based-detection

This project was made for nails segmentation using deep learning models. __DeepLabV3Plus__ was used for segmentation problem. ResNet101 were used as encoder and imagenet weights were used as encoder weights.

OCR for recognizing Arabic text in images/ printed documents

This is an auto-scoring system for the game of billiards implemented with YoloV3 and OpenCV in Python

Python-based OpenCV program for detecting leaves and creating segmentation masks based on images in the Komatsuna dataset.

Implementation of SqueezeSeg, convolutional neural networks for LiDAR point clout segmentation https://arxiv.org/abs/1710.07368

Flood Segmentation on SAR [Frontiers in Remote Sensing: https://doi.org/10.3389/frsen.2022.1060144]

This is a repository for the project Detection of Polyps in Colonoscopy. We implement the pipeline for detecting and segmenting the polyps from the capsule endoscopy video feed.

A Brief Analysis of the Iterative Next Boundary Detection Network for Tree Rings Delineation in images of Pinus Taeda

Code & data splits for the paper "S-VVAD: Visual Voice Activity Detection by Motion Segmentation" WACV 2021

This repository contains models for Multi-class disease detection using Chest X ray. A detail analysis of our approach is mentioned.

Multi-Agentic adaptive FreeSurfer/FSL Registration, ROI-detection, Segmentation, Clustering, Visualisation and Anomaly detection System for DiCOM and NiFTi images and sequences

The Dark Sky Multi-Cam provides event detection for faint or small objects such as satellites and meteors. Utilizing multi-camera systems & a wisdom of the crowds approach, this can distinguish astronomical events from random noise better than traditional all-sky cameras.

Automatic organ segmentation in clinically normal and abnormal paediatric (4D) DCE-MRI and research-participant 3D MRI of different modalities.

Automated 3D and 4D organ and muscle segmentation in medical images of different modalities.

DAMAGESCOPE detects and classifies building and infrastructure damage by comparing pre-event and post-event satellite GeoTIFF imagery.

Применение классических методов обработки изображений для поиска на фотографии фигур тримино и определения их маркировки.

Кодирование изображений ладоней в векторное описание при помощи скелетизации исходной картинки. Последующей анализ полученных признаковых описаний с целью выявления кластерной структуры.

Projects for the subject on Object Detection and Segmentation of the Master in Computer Vision (UAB)

SegForge is an interactive tool for generating segmentation datasets using the Segment Anything Model. Upload images, generate masks automatically, assign labels, preview results, and export datasets in formats like COCO or YOLO through a simple Gradio or Streamlit interface.

deep learning segmentation for skin injuries