Machine Learning Engineer - Computer Vision Sign Language Recognition
Developed a custom dataset of hand pose landmark images for the creation of a sign language recognition system. Labeled images were used to train a CNN model to detect and classify Ecuadorian Sign Language vowels in real time. Implemented end-to-end data collection and labeling using live video capture for model training support. • Built real-time annotation workflow using OpenCV and MediaPipe. • Collected and labeled image data for gesture recognition. • Applied classification labels to hand poses representing vowels. • Integrated labeled dataset with TensorFlow for model training.