Computer Vision: Python OCR and Object Detection Quick Starter

Course Cover
compare button icon

Course Features

icon

Duration

4.41 hours

icon

Delivery Method

Online

icon

Available on

Limited Access

icon

Accessibility

Desktop, Laptop

icon

Language

English

icon

Subtitles

English

icon

Level

Intermediate

icon

Teaching Type

Self Paced

icon

Video Content

4.41 hours

Course Description

Learn about optical character recognition, object detection and object recognition with Python

About This Video

  • Learn about the optical character recognition technology (OCR).
  • Discover convolutional neural network models pre-trained for image recognition
  • For object detection, use pre-trained Mask R-CNN models and MobileNet–SSD.

This course is designed to be a quick start for anyone who wants an overview of optical character recognition (OCR), object detection, image recognition, and object recognition using Python.

As you progress, you will use convolutional neural network (CNNs), Keras library, pre-trained models like VGGNet 16 or VGGNet 19 to perform image recognition using sample images. The course then focuses upon object recognition. It teaches you how to use MobileNet–SSD and Mask R–CNN pre-trained models for detecting and labeling objects in real-time video from the computer's internetcam, as well as in saved video. You'll also learn how the YOLO and Tiny YOLO models can speed up the process of detecting an item from a single image.

You will have a solid understanding and confidence in OCR and the methods by the end of this course.

Course Overview

projects-img

International Faculty

projects-img

Post Course Interactions

projects-img

Instructor-Moderated Discussions

Skills You Will Gain

What You Will Learn

Explore convolutional neural networks pre-trained models for image recognition

Understand the optical character recognition (OCR) technology

Use Mask R-CNN pre-trained models and MobileNet-SSD for object detection

Course Cover