PDF recognition system
LabelBox is used to mark the text area in the PDF image.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
As a versatile AI specialist with a deep focus on image processing and natural language processing (NLP), leveraging a variety of models including Resnet, YOLO, CycleGAN, Transformation, BERT, GPT. My AI expertise extends to developing solutions for image classification, object detection/tracking, image generation, audio recognition, face recognition, translation and chatbot/chatGPT, where I ensure high performance and accuracy. Alongside AI, I am a proficient full-stack web developer, adept at integrating complex AI models into web applications. Using React for front-end interfaces, Django for back-end services, and MongoDB for database management, I create AI-powered web solutions that provide users with real-time insights and automation.
LabelBox is used to mark the text area in the PDF image.
I built a system to automatically identify fruits from images taken by the robot's built-in camera, and labeled the image set collected by the robot myself using LabelImg.
Bachelor's in Computer Science, Computer Science
Chatbot Developer
AI Specialist