AI Applications: Computer Vision and Speech Recognition

This course is part of Mastering AI: Neural Nets, Vision System, Speech Recognition Specialization

Instructor: Edureka

Access provided by Lok Jagruti University

4 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

4 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Analyze speech waveforms and apply audio signal processing techniques.
Develop and implement computer vision algorithms using OpenCV.
Perform morphological operations on images and videos for data manipulation.
Apply speech recognition techniques for digitizing and analyzing audio signals.

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

12 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Mastering AI: Neural Nets, Vision System, Speech Recognition Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

Welcome to AI Applications: Computer Vision and Speech Recognition, where you will gain hands-on expertise in using cutting-edge technologies to process visual data and interpret human speech. This course equips you with practical skills to address real-world challenges in computer vision and speech analysis.

By the end of this course, you will be able to: - Analyze speech waveforms using advanced audio signal processing techniques. - Develop a strong understanding of computer vision principles and applications. - Perform morphological operations on images and videos within a customized environment. - Implement advanced audio and video processing techniques. - Apply OpenCV functionalities to build robust solutions for image and video analysis. This course is ideal for AI enthusiasts, data scientists, and developers aiming to expand their skills in computer vision and speech recognition. Prior experience with Python programming and a basic understanding of machine learning concepts is recommended for optimal learning. Master the skills required to build intelligent systems in the evolving field of artificial intelligence with this focused course.

This module is designed to help learners understand the history of AI and how its ongoing development has led to the creation of image and video processing tools like OpenCV. Learn to perform various image processing such as morphological operations.

What's included

32 videos5 readings5 assignments2 discussion prompts

32 videos Total 166 minutes

Course Introduction 4 minutes
Industrial Breakthrough in Audio and Speech Recognition 2 minutes
Speech Recognition Technology 5 minutes
Computer Vision Application 5 minutes
Computer Vision Applications: Medical and Plant Disease 6 minutes
AI Responsibility Pyramid 7 minutes
Evolution of Computer Vision and Speech Analysis 5 minutes
Evolution of Speech Analysis 5 minutes
What is OpenCV? 6 minutes
Installing OpenCV on Windows 4 minutes
Installing OpenCV on Windows: Handling Libraries in Jupyter 5 minutes
Installing Integrated Libraries - NumPy, Matplotlib, SciPy, and Pillow 6 minutes
Installing Integrated Libraries - Dlib, Scikit, and Pytorch 5 minutes
Operations on OpenCV 3 minutes
Demonstration: Loading the Image and Encoding Image to RGB 6 minutes
Demonstration: Resizing, Rotating and Flipping the Image 7 minutes
Demonstration: Gaussian Blur 7 minutes
Demonstration: Edge Detection and Conversion 6 minutes
Demonstration: Image Thresholding - Binary Image 5 minutes
Demonstration: Different Methods of Thresholding 6 minutes
Demonstration: Practical Use Cases 3 minutes
What is Adaptive Thresholding 5 minutes
Demonstration of Global Adaptive Threshold 5 minutes
Demonstration: Implementing Adaptive Thresholding Methods 7 minutes
Morphological Operations 5 minutes
Morphological Operations in OpenCV 4 minutes
Demonstration: Opening (Dilation and Erosion) 6 minutes
Demonstration: Closing and Morphological Gradient 6 minutes
Blackhat and Whitehat Transformations 5 minutes
Demonstration: Whitehat/Tophat 4 minutes
Demonstration: Blackhat 6 minutes
Summary of Computer Vision with OpenCV 7 minutes

5 readings Total 40 minutes

Welcome to AI Applications: Computer Vision and Speech Recognition 10 minutes
Exploring Technologies for Computer Vision 10 minutes
Ethical Considerations in Computer Vision 10 minutes
LBPH Algorithm: Local Binary Patterns Histogram 5 minutes
Watershed Algorithm for Image Processing 5 minutes

5 assignments Total 54 minutes

Knowledge Check : Computer Vision with OpenCV 30 minutes
Practice Quiz : Evolution of AI and Computer Vision 6 minutes
Practice Quiz : Setting Up Environment 6 minutes
Practice Quiz : Image Processing 6 minutes
Practice Quiz : Morphological Operations 6 minutes

2 discussion prompts Total 20 minutes

Introduce Yourself 10 minutes
Simplifying OpenCV Environment Setup 10 minutes

In the second module of this course, you'll delve deeper into OpenCV functionalities for video preprocessing. You'll learn how to play videos using OpenCV, extract and combine frames, and demonstrate the use of Haar cascades and their integration with OpenCV.

What's included

28 videos2 readings3 assignments1 discussion prompt

28 videos Total 137 minutes

Video Processing 3 minutes
Demonstration: Implementing Frame by Frame Video Processing 4 minutes
Demonstration: Exiting the Processing Operation 3 minutes
Demonstration: Initializing the Video Frames 6 minutes
Demonstration: Saving the Frames 7 minutes
Demonstration: Loading the Data 5 minutes
Demonstration: Reading and Writing Operations 6 minutes
Demonstration: Histogram Matching 7 minutes
Demonstration: Matching Source and Reference Images 5 minutes
Demonstration: Cumulative Distribution Function 5 minutes
Demonstration: Differences in Images 4 minutes
Haar Cascade 2 minutes
Haar Cascade: Algorithm Overview 6 minutes
Haar Cascade Application and Limitation 2 minutes
Demonstration: Implementation of Haar Cascade Algorithm 7 minutes
Demonstration: Face Detection Code for Static Image 4 minutes
Demonstration: Implementing Boundary Box for Face Detection 6 minutes
Demonstration: Applying Face Detection on Images 6 minutes
Introduction to Face Recognition 6 minutes
Demonstration: Setting Up Pre-requisite Libraries and Loading the Image 2 minutes
Demonstration: Face Recognition and Detection 5 minutes
Demonstration: Facial Landmark Detection with File Loading and Library Setup 5 minutes
Demonstration: Adjusting Video details through OpenCV 6 minutes
Demonstration: Face Recognition 7 minutes
Demonstration: Encoding Facial Landmarks 4 minutes
Demonstration: Implementing Facial Landmarks on Images 4 minutes
Demonstration: Implementing Facial Landmarks on Videos 5 minutes
Summary of Video Processing with OpenCV 6 minutes

2 readings Total 20 minutes

Marker-Based Augmented Reality (AR) 10 minutes
Pros and Cons of OpenCV’s Haar cascade Face Detector 10 minutes

3 assignments Total 42 minutes

Knowledge Check : Video Processing with OpenCV 30 minutes
Practice Quiz : Video Processing Using OpenCV 6 minutes
Practice Quiz : Exploring Various Techniques for Face Detection and Recognition 6 minutes

1 discussion prompt Total 10 minutes

The Future of Face Recognition and Security: Opportunities and Challenges 10 minutes

In the third module of this course, you will learn the fundamental structure of speech and how it is organized. Process speech by analyzing waveforms and applying various techniques to manipulate them effectively.

What's included

27 videos2 readings3 assignments1 discussion prompt

27 videos Total 137 minutes

Introduction to Speech: Audio Data 4 minutes
Introduction to Speech: Human Computer Interaction and Applications 5 minutes
Processing Speech 6 minutes
Speech Production 7 minutes
Difficulties in Analyzing Speech 7 minutes
Working of Sound Waves 5 minutes
ADC and Sample Rate, Bit Rate 3 minutes
Conversion of ADC (Analog to Digital Converter) to DAC (Digital to Analog Converter) 5 minutes
Demonstration: Generating Sound 7 minutes
Demonstration: Spectrogram 6 minutes
Demonstration: Signal Frequencies Over Time 4 minutes
Summary of Audio File Analysis 2 minutes
Demonstration: Converting a Sound File into Waveform 7 minutes
Human Speech 7 minutes
Speech Waveform 5 minutes
Digital Signal Processing 7 minutes
MFCC (Mel Frequency Cepstral Coefficient) 6 minutes
Windowing Formula and Cepstrum 5 minutes
Demonstration: Computing the Spectrogram 4 minutes
Demonstration: Digitizing the Audio Data 5 minutes
Demonstration: Converting Fragmented Parts of Audio File for Speech Recognition 4 minutes
Voice Onset, Voice Offset, Tremor, and Noise Detection 6 minutes
Understanding the Concepts of Voice Onset and Offset 3 minutes
Tremor Detection 2 minutes
Demonstration: ZCR, Pitch Detection, Voice Activity Detection 5 minutes
Demonstration: Tremor Detection 5 minutes
Summary of Speech Recognition and Audio Analysis 5 minutes

2 readings Total 20 minutes

Speech Analysis In Cyber Security 10 minutes
Speech Processing - Interactive Creation and Evaluation (SPICE) Toolkit 10 minutes

3 assignments Total 42 minutes

Knowledge Check : Speech Recognition and Audio Analysis 30 minutes
Practice Quiz : Speech and it's Variation 6 minutes
Practice Quiz : Digitizing and Analyzing Speech 6 minutes

1 discussion prompt Total 10 minutes

The Role of Speech Analysis in Modern AI Applications 10 minutes

This module is designed to assess an individual on the various concepts and teachings covered in this course. Answer a comprehensive quiz which marks you as a learner who is confident in working with Computer Vision and OpenCV.