StreamLit OpenCV Computer Vision Web App

Name: StreamLit OpenCV Computer Vision Web App
Rating: 4.4 (17 reviews)

How to build a Computer Vision Web Application using StreamLit MediaPipe in Python & OpenCV

Created byAugmented AI

Last updated 9/2021

English

English [Auto],

What you'll learn

Build a StreamLit Analytics Dashboard
Integrate Computer Vision into StreamLit
Learn how to use MediaPipes Face Landmark Detection on Images and Video
Implement Widgets, Sliders and checkboxes
OpenCV Python and StreamLit WebApp Development

Course content

1 section • 9 lectures • 1h 21m total length

Introduction0:55
Today we are going to learn how to build from scratch a Computer Vision using an interface using StreamLit in Python and OpenCV. We'll start off by codding the StreamLit interface with Python only and then combine it with Googles' Media Pipe Library to perform face landmark detection in real-time. From there we'll create three pages:
The first page will tell us a little about the Web App and the Author,
The second one helps us to input Face Mesh on a single image, and
The third will allow us to implement real-time face landmark detection on a video.
What's really great about this is that unlike native OpenCV apps is that you can actually interact with the app and make adjustments and create neat and --- dashboards with this.
If you don't already know, StreamLit done data scripts into shareable web apps in minutes. All in Python. All for free. No front-end experience required.
Getting the Project Files2:02
Begin with project files from the vision store to build a facial landmark detection app using streamlet on cpu, install dependencies, run the app with a webcam, and explore demos.
StreamLit Framework8:10
Streamlit Image Resize Function and Sidebar6:51
About Me Page Design4:15
Image Detection Page21:06
Learn to build an image detection page with streamlit, opencv, and mediapipe that detects faces and face mesh landmarks, with image upload and adjustable max faces and confidence.
Video Detection Part-113:12
Implement video inference in a streamlet app by enabling webcam input or video upload, with recording. Configure the video buffer, width, height, fps, and codecs for input and output.
Video Detection Part-215:20
Video Detection Part-39:44

Requirements

Python Programming Experience
OpenCV Background

Description

*Price goes up to $39 on the 1st of April 2022. Price increase is due to newer content added to the course every month.

In this course, we are going to learn how to build from scratch a Computer Vision Web Application using StreamLit in Python and OpenCV. We'll start off by coding the StreamLit User Interface with Python only and then combine it with Googles' Media Pipe Library to perform face landmark detection in real-time. From there we'll create three pages:

The first webapp page will tell us a little about the Web App and the Author,
The second page of the UI one helps us to infer Face-Mesh on a single image, and
The third will allow us to implement Real-Time face landmark detection on a video at 30FPS.

What's really great about this is that unlike native OpenCV apps is that you can actually interact with the app and make adjustments and create neat and professional dashboards with this.

If you don't already know, StreamLit can turn data scripts into shareable web apps in minutes. All in Python. All for free. NO front-end, HTML, JAVA experience required.

This course is a full practical course, no fluff, just straight on practical coding.

Requirements

Please ensure that you have the following:

Basic understanding of Computer Vision
Python Programming Skills
Mid to high range PC/ Laptop
Windows 10/Ubuntu

30 Day Udemy Refund Guarantee

If you are not happy with this course for any reason, you are covered by Udemy's 30 day no questions asked refund guarantee.

Who this course is for:

Students who want to create presentable computer vision web apps
Students who want to learn StreamLit and how to integrate it with Computer Vision