Mehmet Ali Güven

This project analyzes videos to extract visual features and detect moving objects, helping to understand motion patterns and object movements in video content.

This project is an artificial intelligence system that analyzes real-time video feeds from security cameras to detect weapons and provide necessary alerts.

An AI-powered surveillance system that uses computer vision and deep learning to automatically detect abnormal behaviors and security threats in real-time CCTV footage, featuring mobile camera integration and automated incident reporting.

Online mobile health application integrated with a specially trained artificial intelligence model to both reduce the number of appointments and provide early diagnosis.

A machine learning and image processing-based AI project that can detect diseases from OCT (Optical Coherence Tomography) images without doctor assistance.
View Projects (Page 102)

An AI system that uses the YOLO model to detect objects in uploaded images and performs keyword-based web searches on the detected objects to analyze and present relevant information.

An application that adds subtitles by translating the text in the video into the desired language using an OCR model.

Model that detects text in real time or from images using PaddleOcr.

An artificial intelligence model that detects a pose from a real-time video and translates the detected labels into json format for training.

An artificial intelligence model that translates the sound recorded instantly with a microphone into the desired language and gives it as an output.

A tool for analyzing English accents from audio files or video URLs. Perfect for evaluating spoken English in hiring processes.

Script has been added for adding and removing tags to the desired frames by matching the existing dataset and the frames in the CVAT(Computer Vision Annotation Tool) with md5.