UNSUPERVISED IMAGE CLASSIFICATION USING CELLULAR AUTOMATA WITH BACKTRACKING AND GENETIC ALGORITHM

The main aim of this research is to employ the Cellular Automata technique to implement an unsupervised classification by applying a specified Cellular Automata rules With backtracking mechanism to cover unrecognized area and Gentic Algorithm to compare the results .

1- We Implement a histogram to the image and then we taking the peak of histogram curves and using it as start point of the classification .The classification depend on the all eight neighborhoods (The neighbourhood of each cell will consist of the 8 nearest cells (Moore neighbourhood).

2- We used Satellite Images

3- The Programming language is Matlab .

4- A cellular automaton consists of a grid of cells distributed normally in a matrix form that has the following basic features:

– States: each cell can take an integer value that corresponds to its current state. There is a finite set of states.
– Neighbourhood: a set of cells that interact with the current one.
– Transition function f : takes as input arguments the cell and neighbourhood states, and returns the new state of the current cell.
– Rules: the transition function f uses a set of rules that specify how the states of the cells change.
– iterations: the transition function f is applied to each cell of the grid across several iterations.
When we work with satellite images, we consider each pixel of the image as a cell of the cellular automaton and we normally take the 8 around pixels as neighbourhood (Moore Neighborhood) .

The changes in cells states occur in discrete time form. In each iteration the whole cells are checked and rules are applied through the transition function f to each cell taking into account the around neighbourhood to change its state.

Therefore cellular automata have an evolution process because the cells are always changing their states across the different iterations.

5- after classification if there are uncovered area we used backtracking mechanism to cover unrecognized area .

6. Parent generation and population size, Crossover and Mutation using Genetic Algorithm

7. Influence of crossover and mutation probabilities.

8. Image data, ground truth and error matrices

9.Comparing the result with accuracy.