Neural network classifier

Image classification using neural network classifier


Updated 16 Nov 2014

View License

This code is written for image classification using Matlab newff function. You can refer Crab classification which is given in Matlab help. This is a supervised classification technique. Appropriate training areas are selected for each class. Training should be given to the neural network using training areas. Here .CSV (comma seprated value) file is used to store training areas (download "5_class_test.csv") and the corresponding class. Once the neural network is trained the entire image can be converted to .CSV file for exmaple if the size of the RGB image is 5 rows and 5 columns then the csv file will have 3 columns and 25 rows (download "all_class.csv").. Each row will be one pixel of the image and each column will be one band. First column will be red band 2nd will be green and 3rd will be blue band.Once the CSV file for the entire image is ready it is given to the trained neural network. Since the image used here is big the code takes more time to classify. The required CSV files are also uploaded along with this code. The input image is not given as it comes under copy right. Here the input data is in a float format

Cite As

Dr.Varsha Turkar (2023). Neural network classifier (, MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2012b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes