Spectral Image Processing Using Python


Vishal Kumar Singh


Certificate Courses

Course Attendees

Still no participant

Course Reviews

Still no reviews

Certificate Course : Spectral Image Processing using Python

Course Credit 0+2+2

Course Description

The course is designed to meet industry trends in terms of image processing technique, students will be able to learn an open-source python-based tool for Hyperspectral Image processing. Spectral Python (SPy) is a pure Python module for processing hyperspectral image data. It has functions for reading, displaying, manipulating, and classifying hyperspectral imagery.

The course has 23 sessions which include practice sessions, project work, and assignments.

Course Objectives

• To study the spectral python tools for processing Hyperspectral images.
• To study the concept of Hyperspectral remote sensing.
• To know the basics, importance, and methods of Spectral remote sensing.
• To study machine learning technology for processing hyperspectral images and multispectral images.

Learning Outcomes

• To understand the structure of spectral data including band associations, shape and size of a hyperspectral images
• To develop software skills in programs used for map production in the modern cartographic workflow.
• To develop skills for deploy machine learning technology for processing multispectral and hyperspectral images.

Course Syllabus

Module 1

1. Downloading multispectral satellite data from USGS/Bhuban etc
2. Installation of Python (Integrated Development and Learning Environment, Colab Notebook, Python 3.5 or above versions)

Module 2

1. Reading multispectral data in python interface.
2. Reading hyperspectral data in pyhton interface.

Module 3

1. installing dependencies library and visualization tools in Python such as Rasterio, shapely, GDIL, Spy, Matplotlib, Fiona, etc.
2. Check the shape and size of the image.

Module 4

1. Importing Training dataset l.e Ground truth image of one band.
2. Display selected/filtred bands of Hyperspectral image.
3. Superimpose Ground truth image on Hyperspectral image.

Module 5

1. Unsupervised classification of Hyperspectral image.

Module 6

1. Supervised Classification of Hyperspectral image.

Module 7

1. PCA for Dimensionality reduction of Hyperspecral image.
2. Minimum noise fraction hyperspectral data filtering.


Spectral Python: http://www.spectralpython.net/

Click here to watch the tutorial Video for downloading Hyperspectral data

Click here to watch the tutorial video for setting up Python software

Sessions Plan

Session 1

Data download from USGS and Bhuban, Hyperspectral data download from Weebly

Session 2

Data preparation, introduction file formats, catalogue, Geodatabase for multispectral and Hyperspectral images. Storage of datasets.

Click here to download the instruction manual of ESRI

Session 3

Python installation in window 10, installation of Python on window/Linux operating system, installation of dependent libraries.

Session 4

Introduction to Google Colab, linking Colab to Google drive, importing files, importing dependencies. Get started with a web-based python engine.


Get Started with Google Colab


Download the Hyperspectral data, import it into Google Colab drive link, install related dependencies.


Mode of Submission: Online, Please upload the assignment into the Google Classroom

Session 5

Introduction to multispectral images, basics of spectral image processing, spectral bands classification. Advantage and limitation of multispectral images.



Session 6

Introduction to Hyperspectral images, basics of Hyperspectral image processing, spectral bands classification. Advantage and limitation of Hyperspectral images.



What is spectral signature? Explain significance of Hyperspectral and Multispectral images. What are the types of Hyperspectral images ? Explain different types of Hyperspectral sensors.


Mode of submission: Online, please submit the assignment in Google classroom

Session 7

Introduction to spectral python open-source tool for processing of Hyperspectral and Multispectra images. Supported file format for Hyperspectral and multispectral images.


Session 8

Reading Hyperspectral images in spectral python, Displaying the shape of an image, displaying metadata.



Session 9

Spectral signatures for the Hyperspectral and multispectral images, reflectance value for different features.



Session 10

Data filtering, identification of spectral zone, and its projections.


Session 11

Training dataset, i.e Ground Truth image, making an overlap to the BGR bands of the images.

Spectral graphics

Session 12

Visualization of multiple bands at one time, Visualization of multiple spectral signatures.


Image data Display

Session 13

Visualization of multiple bands at one time, Visualization of multiple spectral signatures.


Display Mode Spectral Graphics

Internal Test

Will be in online mode, Exam link will be shared.

Session 14

Unsupervised classification of Hyperspectral image using Gaussian model classifier

Session 15

Supervised classification using training dataset (Ground Truth Image)


quizzes link will be shared during the course

Session 16

Error calculation for supervised classification.

Session 17

Dimensionality reduction of the Hyperspectral images using principal component analysis (PCA), linear transformation using eigenvector or percentage of accuracy.


Spectral Algorithms

Session 18

Dimensionality reduction of the Hyperspectral images using principal component analysis (PCA)

Session 19

Supervised classification of the reduced dataset (PCA image with limited band details).

Session 20

Minimum noise fraction algorithm for Hyperspectral data filtering

Practical Test

link will be shared

Session 21

Project: Training dataset for supervised classification of a multispectral image.

Session 22

Project: PCA for dimensionality reduction a hyperspectral image.

Session 23

Project: Feature classification of a Hyperspectral image based on the spectral signature of each band.

Final Examination

Practice Test + Viva

Our Main Teachers

BIM Modelling, City 3D Model, Geospatial Technology