Research Article
A Water-Area Recognition Approach Based on “Tuned” Texture Mask and Cuckoo Search Algorithm
Pseudocode 1
Pseudocode of learning “Tuned” mask based on CS algorithm.
| Begin | | Input training sample texture images | | Set the parameters of CS algorithm and generate initial populations | | Generate “Tuned” mask by using Equation (3), and make convolution with training images and “Tuned” mask | | While (The current iteration does not reach the maximum iteration) | | Compute the fitness value of each bird by Equation (4) | | Lévy flight by using Equation (2) | | Update new position of each bird by using Equation (1) | | If (The fitness value of current position is better) | | Replace the object by the new position | | End if | | End while | | Output the optimal “Tuned” mask according to Equation (3) | | End |
|