I developed a Python-based application to identify whether an animal in an image is a dog. I tested and compared the accuracy of multiple architectures, including ResNet, AlexNet, and VGG, to determine the most effective model.
.gif)
I developed this computer vision program that detects poker cards by their value and suit with 91% mAP accuracy. This program detects poker cards by their value and suit. It utilizes YOLOv8 for real-time object detection and Roboflow for dataset annotation, and OpenCVÂ for image processing.
Worked with Resilience Inc. as an AI/ML developer to work on the AIMEE project that is currently deployed on the App Store and Google Play Store. AIMEE is an app designed for learning and practicing mindfulness to maintain and enhance mental and emotional resilience and well-being.
I conducted a small research project on using Google's Mediapipe and OpenCV in Python to perform real-time hand tracking. This project was used to learn the fundamentals of image / video processing capabilities of OpenCV and how to integrate third party frameworks.
I implemented different types of classification algorithms from scratch, including a Decision Tree and a Multi-Layer Perceptron (MLP), for optical-digit classification in Python, focusing on training, tuning parameters, and evaluating prediction accuracy - comparing both to each other.
