ỨNG DỤNG TEACHABLE MACHINE TRONG NHẬN DIỆN KHUÔN MẶT THEO THỜI GIAN THỰC

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Thị Chang Đỗ, Sinh Biên Trần

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học & Công nghệ - Trường Đại học Công nghiệp Hà Nội, 2023

Mô tả vật lý: tr.51

Bộ sưu tập: Metadata

ID: 337828

Thêm vào giỏ Liên kết toàn văn

Ngày nay, AI (Artificial Intelligence) và ML (Machine Learning) là hai trongnhững lĩnh vực ứng dụng hứa hẹn nhất trên thế giới. Tuy nhiên, với một ngườikhông chuyên công nghệ thông tin, rất khó để họ có thể tiếp cận và ứng dụng AIhay ML vào trong các nghiên cứu của mình. Để khắc phục vấn đề này, tác giả xinđề cập tới một công cụ do Google phát hành có tên Teachable Machine,Teachable Machine sẽ giúp chúng ta có được những trải nghiệm cơ bản nhất vềtrí thông minh nhân tạo (AI). Teachable Machines được xây dựng dựa trên mạngnơ-ron tích chập (CNN - Convolutional neural networks) - một trong những môhình Deep Learning tiên tiến, nó giúp cho chúng ta xây dựng được những hệthống thông minh với độ chính xác cao. Trong phạm vi bài báo này, tác giả cũngsẽ xây dựng một mô hình máy học dựa trên công cụ Teachable Machine nhằmxây dựng hệ thống nhận diện khuôn mặt trong thời gian thực. Bài báo sẽ tậptrung vào vấn đề thu thập dữ liệu từ các đối tượng khác nhau, từ đó sử dụng côngcụ Teachcble Machine để xây dựng mô hình, và sau đó sẽ tiến hành nhận diệnngười trong thời gian thực thông qua camera. Sau 2 lần training mô hình, độchính xác (accuracy) của mô hình đã đạt tới 100%.These days, AI (Artificial Intelligence) and ML (Machine Learning) are two ofthe most promising application areas in the world. However, for a non-IT person, itis very difficult for them to approach and apply AI or ML in their research. To solvethis problem, the author would like to mention a tool released by Google calledTeachable Machine, Teachable Machine will help us get the most basic experienceof artificial intelligence (AI). Teachable Machines is built based on a convolutionalneural network (CNN - Convolutional neural networks) - one of the advanced DeepLearning models, it helps us build intelligent systems with high accuracy. Manyusers in 201 countries use Teachable Machine to create more than 125,000classification models [2]. Within the scope of this paper, the author will also build amachine learning model based on the Teachable Machine tool to build a facerecognition system in real-time. The article will focus on the problem of collectingdata from different objects, then using the Teachable Machine tool to build amodel, and then proceeding to identify people in real-time through the camera.After 2 times of training the model, the model's accuracy reached 100%.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR