Video 54: Face Recognition using Wavelet Features and PCA (With MATLAB Code)

Hello viewers, In this video, a face recognition scheme is implemented using Wavelet Features and Principal Component Analysis (PCA). Here wavelets are used to extract facial features and PCA is used to reduce the size of wavelet feature vectors. The proposed scheme is very robust and capable to recognize the faces even some changes occur in faces such growing beard and mustache or putting goggles etc.

This video covers followings contents,

• Face image database (Faces94).
• Face image database preparation for training and testing.
• Finding wavelet features.
• PCA for dimension reduction.
• Training and testing procedures.
• MATLAB Code for Training.
• MATLAB Code for Testing (Discrete and Bulk).

-------------------------------------------------------------------------------------------------------------------------

Links of previous videos:

1. Principal Component Analysis (PCA) for Images and Signals: Click Here

2. Face Recognition using PCA in MATLAB: Click Here

Links for Face Image Database:

1. https://cmp.felk.cvut.cz/~spacelib/faces/ (All Faces)

2. https://cmp.felk.cvut.cz/~spacelib/faces/faces94.html (Face94 database)

3. https://www.exptech.co.in/p/resource-download.html (Database used in video)

Download Resources:

1. All Image Database: Download

2. Test Images for Robustness: Download

Read More

Video 53: ECG based Heart Disease Diagnosis using Wavelet Features and Deep CNN (Arrhythmia detection)

Hello viewers. This is recorded video of an invited guest lecture delivered by me in an international conference held in July 2021.

This video is about heart disease diagnosis using wavelet features and deep CNN mainly focusing on Arrhythmia detection and heart rate estimation.

This video includes following contents.

• Introduction (Problem Statement).
• Basics of ECG signals and QRS Complex. 
• ECG Database on PhysioNet.
• Proposed wavelet based algorithm for Heart Rate estimation and Arrhythmia detection.
• Deep CNN based approach of Arrhythmia detection.
• Conclusions.

This lecture is based on my previously published YouTube videos, which you can find on following links.

1. ECG signals Classification using CWT and Deep Neural Network in MATLAB: Click Here
2. ECG's QRS Peak Detection and Heart Rate Estimation using Discrete Wavelet Transform (DWT) in MATLAB: Click Here

Other Links:

1. PhysioNet: https://physionet.org/

2. PhysioNet Databases: https://physionet.org/about/database/

3. PhysioNet Bank ATM: https://archive.physionet.org/cgi-bin/atm/ATM

4. ECG signal database GitHub repository:

     https://github.com/mathworks/physionet_ECG_data/

Read More

Video 52: LTI System Analysis using Python (With Python Code)

 

Hello Viewers, In this video, the introduction to LTI systems is described. Also various time domain and frequency domain analysis of LTI systems are implemented using Python. The Python program can plot various time response curves such as Impulse response, Step response and Ramp response. It can also give various stability plots such as Root locus, Nyquist plot, Bode plot, Log magnitude vs Phase plot (Nichols Plot) and Pole-zero plot.

The Python implementation is done using Spyder IDE in Anaconda environment. The Python Control System Library (v0.9.0) is used to write Python program.

This video includes following contents:

• Introduction to LTI systems.
• Various (Time domain/ Freq. domain) analysis of LTI systems.
• Anaconda and Spyder for Python implementation.
• Python Control System Library (v0.9.0).
• Python code for LTI System Analysis.

Link for previous video,

1. LTI System Analyzer using MATLAB GUI: Click Here

Other Links:

1. Anaconda Download: https://www.anaconda.com/distribution/

2. Spyder IDE: https://www.spyder-ide.org/

3. Python Control System Library (0.9.0): https://python-control.readthedocs.io/en/0.9.0/index.html

Read More

Video 51: Solution of State Equations (Homogeneous & Nonhomogeneous) with MATLAB Simulation

 

Hello Viewers, in this video, the theory of solution of state equations is explained. Both the cases of homogeneous and non-homogeneous equations are considered. To clear the concept, some numerical examples are also solved. Also a MATLAB code is developed which is very efficient and capable to solve any state equations for any types of inputs. With this MATLAB program, students can solve questions of their text books and can verify their theoretical outcomes.

This video includes following contents:

• State Space model of systems.
• Solution of homogeneous state equation.
• State Transition Matrix (STM) and its properties.
• Example of solution of homogeneous state equation.
• Solution of non-homogeneous state equation.
• Examples of solution of non-homogeneous state equation.
• MATLAB code for solution of state equations.

Link for previous videos,

1. Introduction to State Space Analysis: Click Here

Read More

Video 50: Introduction to State Space Analysis (Physical Systems Modelling) (With MATLAB Code)

 

Hello Viewers, in this video, the theory of state space modelling is explained. the modern approach based on state space is compared with classical approach of system modelling which is based on transfer functions highlighting advantages of state space method.

Also various physical systems such as Electrical and Mechanical systems are considered for state space modelling. 

The relationship between TF and SS for an LTI system is also established. Also a MATLAB code is explained to model a system in SS and to do various analysis of it.

This video includes following contents:

• Why State Space? (Classical and Modern approach of system modelling).
• Introduction to State space system modelling.
• Basic Definitions: State variables, State, State vector and State space.
• State space modelling of physical systems (Mechanical/ Electrical).
• State space to transfer function conversion and vice-versa. 
• MATLAB code for State space modelling.

Link for previous videos,

1. LTI System Analyzer using MATLAB GUI: Click Here

Read More

Video 49: LTI System Analyzer using MATLAB GUI (With Code)

 

Hello Viewers, in this video, a graphical user interface (GUI) is created to analyze any LTI system. This GUI can plot various time response curves such as Impulse response, Step response, Ramp response. It can also give various stability plots such as Root locus, Nyquist plot, Bode plot, Log magnitude vs phase plot and Pole-zero plot.

This tutorial also covers basics of LTI systems. 

This video includes following contents:

• Introduction to LTI systems.
• Various (Time domain/ Freq. domain) analysis of LTI systems.
• Creating MATLAB GUI for LTI system analyzer using GUIDE.
• MATLAB code of Call Back functions for various GUI components.
• Program Simulation.

Link for previous videos,

1. Device Control using DTMF signals and MATLAB App designer: Click Here

2. Producing Colors with RGB LEDs using Arduino and MATLAB: Click Here

Read More

Video 48: Denoising of Signals and Images using Wavelet Packet Transform

 

Hello Viewers, in this video, denoising of signals and images using Wavelet Packet Transform (WPT) is explained.

This tutorial explains the basic theoretical background of WPT based denoising scheme, noise variance estimation and universal threshold calculation. The denoising is implemented in MATLAB to do experiments with different noisy 1D and 2D signals. The concept of full tree and best tree based decomposition is also included.

This video includes following contents:

• Introduction to Wavelet Packet Transform (WPT).
• Objective and Noise Model.
• WPT based Denoising scheme.
• Noise variance estimation and finding universal threshold.
• Thresholding methods.
• MATLAB functions for WPT and WPT based denoising.
• MATLAB code for denoising 1D signals (Audio).
• MATLAB code for denoising 2D signals (Images).

Link for previous videos,

1. Introduction to wavelet theory and Its applications: Click Here

2. Wavelet Packet Transform of Signals and Images: Click here

3. Wavelet based denoising of audio signals using MATLAB & Simulink: Click Here

4. Wavelet based denoising of images using MATLAB: Click Here

Download Resources: 

1. Test Images: Download 

2. Test Audio Clips: Download

Read More

Video 47: Wavelet Packet Transform (WPT) of signals and Images

Hello Viewers, in this video, the Wavelet Packet Transform (WPT) of signals and images is explained.

The wavelet packet transform is generalization of wavelet transform. In WPT, the detailed coefficients are also split into approximation and detailed coefficients, while in WT, only approximation coefficients are split in further levels.

Also WPT shows superior performance in spectral analysis of signals. It finds suitability in various applications such as denoising, compression, feature extraction and image classification.

This tutorial explains the basic theoretical background of WPT including construction of WPs, WP tree and optimal selection of WP tree.

This video includes following contents:

• Introduction to Wavelet Packets (WP).
• Construction of Wavelet Packets.
• Atoms of Wavelet Packets.
• Organization of Wavelet Packets (WP Tree).
• Selecting Optimal Wavelet Packets Tree .
• Comparing Wavelets and Wavelet Packets decomposition.
• Wavelet Packets decomposition of Images.

Links for previous videos,

1. Introduction to wavelet theory and Its applications: Click Here

2. CWT of 1D signals using MATLAB and Python: Click Here

Read More

Video 46: Object Classification using HOG features and ECOC Multi-Class SVM (With Matlab Code)

Hello Viewers, in this video, a multi-class object classification problem using HOG features is explained. To demonstrate the implementation, simple geometrical shapes (Circle, Square, Star and Triangle) are taken for classification. As a classifier, ECOC (Error Correcting Output Codes) based multi-class SVM is used. The shapes image database is obtained from Kaggle. 

The HOG feature is very popular and widely used for object detection in images. To understand the HOG feature computation, viewers are requested to watch my previous video of HOG feature computation.

This video includes following contents:

• Introduction.
• Proposed scheme for object Classification.
• Image Database Preparation.
• ECOC based Multi-Class SVM.
• Appropriate Cell Size selection for HOG feature.
• MATLAB Code for Shapes Classification (Multi-Class).
• MATLAB Code for Discrete Testing.

1. Link for previous video on HOG feature computation: Click Here

2. Link for Kaggle Dataset: https://www.kaggle.com/smeschke/four-shapes

3. Link to download original paper of N. Dalal and Bill Triggs:

https://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf

Download Resources: 

1. Image Dataset (Modified): Download (Source: Kaggle)

2. Distorted Test Images: Download

Read More

Video 45: HOG (Histogram of Oriented Gradients) Features (Theory and Implementation using MATLAB and Python)

Hello Viewers, in this video, Histogram of Oriented Gradients (HOG) is explained. This video tutorial includes, its theory and its implementation using both MATLAB and Python.

The HOG feature is very popular and widely used for object detection in images. This tutorial is based on the work proposed by Navneet Dalal and Bill Triggs.

This video includes following contents:

• Introduction.
• Finding Image Gradient.
• Getting Cell Orientation Histogram (Getting Bins).
• Making Blocks and Block Normalization.
• Getting HOG feature Vector.
• MATLAB Code for finding HOG feature vector.
• Python Code for finding HOG feature vector.

Link to download original paper of N. Dalal and Bill Triggs:

https://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf

Download Resources: 

1. All Test Images used: Download

Read More

Video 44: Walsh-Hadamard Transform (Signal Filtering and Image Compression)

Hello Viewers, in this video, Walsh-Hadamard Transform (WHT) is explained. This video tutorial includes, its theory, applications and implementation of signal filtering and Image compression using WHT in MATLAB.

The Walsh-Hadamard Transform is non-sinusoidal, orthogonal transform that is widely used in the areas of signals and image processing.

This video has following contents:

• Introduction and Applications.
• Forward and Inverse Walsh-Hadamard Transform (1-D).
• Hadamard Matrix and Walsh Matrix (Sequency and Dyadic Ordering).
• WHT for Images.
• Example: Computing WHT of 1-D signals.
• Example:  Computing WHT of 2-D signals.
• Fast WHT algorithm.
• MATLAB Code for filtering of Noisy ECG signal using WHT.
• MATLAB Code for Image Compression using WHT.

Download Resources: 

1. ECG Signal: Download

2. Lena Image: Download

3. Pepper Image: Download

Read More

Video 43: Symmetrical Components Analysis of Unbalanced Three-Phase Vector (Theory and MATLAB Code)

Hello Viewers, in this video, Symmetrical Components Analysis of three-phase unbalanced voltage or current vectors is presented.

These symmetrical components are useful in solving unsymmetrical faults in power system. In this video, method of obtaining symmetrical components is explained and also a MATLAB program is implemented to do the same.

This video has following contents:

• Introduction (Symmetrical and Asymmetrical 3-phase vectors) .
• Positive Sequence, Negative Sequence and Zero Sequence Vectors.
• Operator ‘a’.
• Method of getting PS, NS and ZS components.
• Example Analysis.
• MATLAB Code to get symmetrical components.

Read More

Video 42: Animated 2D and 3D Plots using MATLAB

Hello Viewers, in this video, It is explained that how one can create animated 2D and 3D plots using MATLAB.

This video tutorial shows the implementation of slow motion 2D, 3D curve plotting, Slow motion movement of data cursor with values, Recording animated plots as videos and 3D surface plots in slow motion.

This video has following contents:

• Why animated plots?
• 2D animated plots: Slow motion Plots (Basic approach).
• 2D animated plots: Slow motion Plots (With inbuilt functions).
• Slow moving Marker with values.
• Making video of animated plots.
• 3D animated plots (Basic approach).
• 3D animated plots (With inbuilt functions).

Read More

Video 41: Detecting STOP Traffic Sign using Deep RCNN (Real time and Offline mode)

Hello Viewers, in this video, It is explained that how one can implement a deep RCNN for detecting 'STOP' traffic signs from image and videos in both offline and real time mode.

Also, it is shown that how one can use MATLAB's Labeler app to create database for training.

Here, transfer learning is used and for fine tuning, a pre trained RCNN is re trained on our own image dataset which is created with help of Image Labeler app.

This video has following contents:

• Introduction.
• What is Deep R-CNN?
• Proposed Scheme using Deep R-CNN.
• Understanding MATLAB’s Image Labeler for image database creation.
• MATLAB Code for training.
• MATLAB Code for testing.
• Code execution and result analysis.

Links of previous videos:

1. How to create a Deep CNN: Click Here

2. ECG signals classification using wavelet features and deep CNN: Click Here​

3. Implementing deep CNN in Python using TF and Keras (Face Mask detection): Click Here

Download Resources: 

1. Test Video: Download (Source: Mathworks.com)

2. Traffic Sign Image Database: Download

Read More

Video 40: How to Choose a Right Wavelet and Wavelet Transform? (Understanding Wavelet Properties)

Hello Viewers, in this video, It is explained that how one can choose appropriate wavelet transform and a right wavelet for a particular application.

To choose a right wavelet, it is important to understand few basic properties of the wavelets such as, Vanishing moments, Support width, Regularity, Symmetry and Orthogonality. 

These properties actually help us in selection of right wavelet.

This video has following contents:

• Introduction.
• What to choose CWT or DWT?
• Understanding wavelets properties.
• Wavelets for Feature Extraction.
• Wavelets for Denoising.
• Wavelets for Compression.
• Wavelets for detection of change or discontinuity.
• Wavelets for other applications (Analysis of Variance, Watermarking, Edge detection, ECG signals, OCR).

Link of previous videos:

1. Introduction to wavelet theory and its applications: Click Here​

2. Continuous Wavelet Transform (CWT) of 1D signals using Python and MATLAB: Click Here

Read More

Video 39: Implementing Deep CNN in Python using TensorFlow and Keras (Face Mask Detection Problem)

Hello Viewers, in this video, it is shown that how a deep Convolutional Neural Network (CNN) can be implemented in Python using TensorFlow (TF) and Keras (K).

To understand its working, an interesting example is taken for implementation, where we can classify face images 'With Mask' and 'Without Mask'.

This video has following contents:

• Objective: Recognize a face with Mask or without Mask.
• Proposed Deep CNN based scheme.
• Introduction  to TensorFlow, Keras and Python.
• Image Dataset used.
• Python Code to implement deep CNN using TF and K.
• Simulation result analysis.

Links of previous videos:

1. How to create a Deep Neural Network in MATLAB: Click Here

2. Introduction to Deep Learning: Click Here

3. Anaconda Download: https://www.anaconda.com/products/individual#Downloads

4. Image Dataset: https://www.kaggle.com/ashishjangra27/face-mask-12k-images-dataset

Read More

Video 38: Wavelet Based Robust Spread Spectrum Watermarking of Color Images (With Code)

Hello Viewers, in this video, Watermarking of color images using Discrete Wavelet Transform (DWT) is presented. The proposed watermarking scheme is based on spread spectrum watermarking, which is robust against several attacks.

This video has following contents:

• Color Space Selection.
• Proposed DWT based spread-spectrum watermarking for color images.
• Watermark embedding and watermark extraction algorithms.
• Performance evaluation parameters.
• MATLAB Code to implement watermarking (Embedding/ Extraction).
• Result analysis.

Link of previous video:

Wavelet based Robust Spread Spectrum Watermarking of Grayscale Images: Click Here

Download Resources : 

1. Test Images and Watermarks: Download

2. I. J. Cox Paper: Download

Read More

Video 37: Hand Gesture Recognition using Basic Image Processing and Device Control in Real Time

Hello Viewers, in this video, a real time Hand Gesture Recognition (HGR) using simple image processing steps, is presented. This HGR is able to count number of fingers when a hand is shown to the camera. The proposed scheme uses few morphological operations to recognize number of fingers and it generates DTMF tone equivalent to fingers count. With this DTMF signal, we can control devices (ON/ OFF) with help of DTMF decoder and relay driver circuit.

This video has following contents:

• What is Hand Gesture Recognition (HGR)?
• Hand Gesture Recognition (HGR) scheme using basic image processing.
• Various steps of achieving HGR.
• DTMF generation and device control.
• MATLAB Code to implement HGR and Device control.

Previous Videos:

1) Device Control using DTMF signals and MATLAB's App Designer: Click Here

2) Webcam and IP cam interface with MATLAB: Click Here

Read More

Video 36: Wavelet Based Robust Spread Spectrum Watermarking of Grayscale Images

Hello Viewers, in this video, Watermarking of grayscale images using Discrete Wavelet Transform (DWT) is presented. The proposed watermarking scheme is based on spread spectrum watermarking, which is known to be robust against several attacks.

This video has following contents:

• What is image watermarking?
• Types of watermarking and challenges in image watermarking 
• DWT based spread-spectrum watermarking for grayscale images.
• Watermark embedding and watermark extraction algorithms.
• Performance evaluation parameters.
• MATLAB Code to implement watermarking (Embedding/ Extraction).
• Result analysis.

Important links:

Research paper of I. J. Cox:

1. https://link.springer.com/chapter/10.1007/3-540-61996-8_41

2. https://drive.google.com/file/d/1M9iV3t8sMESBuuEfrgNaUrt6tCFG5eMD/view?usp=sharing

Download Resources: 

1. Test Images and Watermark: Download

2. I. J. Cox Paper: Download

Read More

Video 35: Fourier Series implementation using Symbolic Math's Toolbox of MATLAB

Hello Viewers, in this video, Fourier series is implemented and simulated using Symbolic Math's Toolbox of MATLAB.

Both the forms of Fourier series i.e. Trigonometric and Exponential are implemented.

The proposed programs are versatile and have capability to receive any function of t. The program gives plots of harmonics, original function and approximated function, Magnitude spectrum and Phase spectrum.

With these programs, students can solve any Fourier series problem of their text books. 

This video has following contents:

• What is Fourier Series? 
• Trigonometric Fourier Series.
• Exponential Fourier Series.
• MATLAB Code to implement Trigonometric Fourier Series.
• MATLAB Code to implement Exponential Fourier Series.

Read More

Video 34: Device Control using DTMF signals and MATLAB's App Designer

Hello Viewers, in this video, a device control method is presented using DTMF signals. These DTMF signals are generated by a GUI app which is built by MATLAB App Designer. Also related hardware such as DTMF decoder, Relay driver etc. are also explained.

The content provides a good platform to learn and helps the students to build a project on the suggested framework. It can be used to control up to 16 different electrical equipment. 

This video has following contents:

• Device Control Strategy. 
• Understanding DTMF generation.
• DTMF Recognition and Relay Driver Hardware.
• MATLAB Code to generate DTMF tones.
• Building Application using App Designer.
• MATLAB code for DTMF App.

Read More

Video 33: Content Based Image Retrieval (CBIR) using Wavelet Features, CLD and EHD of MPEG-7

Hello Viewers, in this video, a Content Based Image Retrieval (CBIR) system is implemented. This CBIR utilizes Color Layout Descriptor (CLD) for color feature extraction and Wavelets and Edge Histogram Descriptor (EHD) for extraction of texture features.

This CBIR uses a feature vector of just length of 181 and it also shows enough robustness against distorted input images.

The implementation is done in MATLAB.

This video has following contents:

• What is Content Based Image Retrieval (CBIR)? 
• CLD and EHD as feature vectors.
• Use of Wavelets for features extraction.
• Image Databases used for image retrieval.
• Training Procedure and Testing Procedure.
• Performance Parameters for a CBIR system.
• MATLAB code of complete CBIR system.

Link of previous videos:

1. Color Layout Descriptor (CLD) of Mpeg-7 for Image Retrieval: Click Here

2. Edge Histogram Descriptor (EHD) of Mpeg-7 for Image Retrieval: Click Here

Link of Image Databases:

1. Wang Image Database: http://wang.ist.psu.edu/docs/related/​

2. Microsoft Image Database: https://www.microsoft.com/en-us/download/details.aspx?id=52644

Download Resources: 

1. Test Images: Download

2. Wang Database: Download

3. Microsoft Research Database (Reduced): Download

Read More

Video 32: Edge Histogram Descriptor (EHD) of Mpeg-7 for Image Retrieval

Hello Viewers, in this video, Edge Histogram Descriptor (EHD) of MPEG-7 family is explained. It is shown that EHD is one of the effective visual descriptor which focuses on the spatial edge distribution in an image. EHD mainly captures five types of edge orientations such as Vertical, Horizontal, Diagonal 45, Diagonal 135 and isotropic.

This EHD is compact in size and is just length of 80 points. If global bin is also attached then it becomes of size 85. Due to small size, it is suitable for fast image search. In this video, Theory of EHD, its implementation in MATLAB and its effectiveness in image retrieval is shown.

This video has following contents:

• What is Content Based Image Retrieval (CBIR)? 
• MPEG-7 Visual Descriptors.
• Edge Histogram Descriptor (EHD).
• Steps to compute EHD.
• MATLAB Code for implementing EHD.
• Applying EHD on images and interpreting the outcome.
• Using EHD for image retrieval.

Link of previous video:

Color Layout Descriptor (CLD) of Mpeg-7 for Image Retrieval: Click Here

Download Resources: 

1. All Images: Download

2. Wang Database: Download

Read More

Video 31: Color Layout Descriptor (CLD) of MPEG-7 for Image Retrieval (With MATLAB Code)

Hello Viewers, in this video, Color Layout Descriptor (CLD) of MPEG-7 family is explained. It is shown that CLD is one of the effective visual descriptor which focuses on the color distribution in an image.

This CLD is compact in size and obtained using fast computation, therefore, it is suitable for fast image search. CLD also shows scale invariance property. In this video, Theory of CLD, its implementation in MATLAB and its effectiveness in image retrieval is shown.

This video has following contents:

• What is Content Based Image Retrieval (CBIR)? 
• MPEG-7 Visual Descriptors.
• Color Layout Descriptor (CLD).
• Steps to compute CLD.
• MATLAB Code for implementing CLD.
• Applying CLD on two images and getting their closeness.
• Showing effectiveness of CLD in image retrieval.

Link of previous video:

Discrete Cosine Transform (DCT) of Images and Image Compression: Click Here

Download Resources: 

1. All Images: Download

2. Flower Image Database: Download

Read More

Video 30: Producing Colors with RGB LEDs using Arduino and MATLAB (With GUI and MATLAB Code)

Hello Viewers, in this video, A scheme is presented to produce any color using RGB LEDs controlled by Arduino Uno board. The Arduino Uno board is interfaced with MATLAB.

By viewing this video, one can learn how to interface Arduino Uno with MATLAB and also will get idea that how different colors are produced from three primary colors Red, Green and Blue.

A Graphical User Interface (GUI) is also created using MATLAB guide to produce colors.

This video has following contents:

• What is Arduino Board? 
• How to produce 16.7 million colors?
• Hardware schematics (Arduino with RGB LED).
• Adding Hardware Support Package for Arduino in MATLAB.
• Designing GUI using MATLAB’s GUIDE.
• MATLAB code for color production.

Read More