Scribd
Upload
4 views

Image Processing & Deep Learning

The document outlines a two-week course on Computer Vision and Deep Learning using Python, covering topics such as Python basics, image processing with OpenCV, and data analysis with Numpy and Pandas. It introduces deep learning concepts, including neural networks, CNNs, and LSTMs, along with model performance metrics. Various projects are included, such as object tracking, face detection, and predictive modeling using machine learning techniques.

Uploaded by

Sweety Jachak
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

Image Processing & Deep Learning

The document outlines a two-week course on Computer Vision and Deep Learning using Python, covering topics such as Python basics, image processing with OpenCV, and data analysis with Numpy and Pandas. It introduces deep learning concepts, including neural networks, CNNs, and LSTMs, along with model performance metrics. Various projects are included, such as object tracking, face detection, and predictive modeling using machine learning techniques.

Uploaded by

Sweety Jachak
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Week 1 - Computer Vision & Image Processing Using Python

❖ Python
o Knowing python
o Installing the environment
o Getting familiar to python ide

❖ Expressions & operators


o Python syntax
o Including comments, indentation
o Python variables
o Operators & python keywords

❖ Python data types


o Data: numeric - int, float, long, complex
o Strings properties, methods, indexing, sequencing slicing, finding string in strings, finding string
in string with numbers . . .
o Lists, tuples, dictionary

❖ Python for data analysis-Numpy


o Introduction to numpy
o Numpy arrays
o Quick note on array indexing
o Numpy array indexing and operations

❖ Pandas
o Introduction to pandas
o Pandas operations

❖ Introduction to OpenCV
o What is opencv
o Installing opencv-python

❖ Getting started with images


o Image databases
o Reading an image with different modes
o Displaying an image
o Writing an image to different path
❖ Images & numbers
o Understanding images as matrices and numbers
o Image shape & dimension
o Size of image

❖ Getting started with webcam & videos


o Using webcam
o Webcam resolution
o Capture image using webcam
o Capture video from camera
o Playing video from file
o Saving a video

❖ Drawing functions in opencv


o Creating an image
o Drawing line
o Drawing rectangle
o Drawing circle
o Drawing ellipse
o Drawing polygons
o Adding text to images

❖ Matplotlib and colormaps


o Image plotting using matplotlib
o Understanding different color maps
o Understanding different color spaces
o Plotting multiple images through matplotlib

❖ Basic operations on images


o Accessing and modifying pixel values
o Accessing image properties
o Image ROI
o Splitting and merging image channels
o Changing image background
o Blurring | image smoothening
o Image transition
o Image sharpening
❖ Introduction to face/ eyes/ smile detection
o Accessing and modifying pixel values
o Haarcascade concept
o Detection of eyes / face / smile from any image
o Detection of eyes / face / smile from live webcam

❖ Projects
o Object tracking by color
o Face/smile/eyes detection from image/webcam
o Car detection
o Image transition
o Applying different filters on image
o Image sharpening and smoothing
o Edge detection
o Image blurring
o Facial recognition system

Week 2 - Deep Learning Using Python

❖ Data Science
o Introduction to data science
o Flow of data science and its applications
o Machine learning and its types
o Deep learning vs machine learning

❖ Introduction to deep learning


o Deep learning: introduction
o Deep learning techniques
o Artificial neural networks concept
o Activation functions
o Feed forward neural networks
o Back propagation
o Cost functions
❖ Introduction to convolutional neural network (CNN)
o Introduction to CNN
o Working of CNN
o Convolutional layer
o Pooling
o Flatten
o Image recognition techniques and feature extraction fundamentals

❖ Introduction RNN (recurrent neural network)


o Introduction to RNN
o Working of RNN architecture
o Disadvantages of RNN

❖ Introduction to LSTM (long short-term memory)


o Introduction to LSTM
o Working of LSTM architecture
o LSTM vs RNN

❖ Model performance metrics


o Confusion matrix
o Precision score | Recall score | F1 – score
o Use cases
o Overfitting and underfitting
o Learning rate | batch size
o Feature scaling
o Outliers
Projects –
1. Data manipulation using numpy and pandas
2. Data visualization on different graphs
3. Breast cancer prediction using ANN
4. Diabetes prediction using ANN
5. Cat and dog classification using CNN
6. Spam email classification
7. Google stock price prediction

You might also like