Wood defects classification using GLCM based features and PSO trained neural network

Machine vision based inspection system are in great focus nowadays for quality control applications. The paper presents a novel approach for classification of wood knot defects for an automated inspection. The proposed technique utilizes gray level co-occurrence matrix based features and a particle swarm optimization trained feedforward neural network. It takes contrast, correlation, energy, homogeneity as input parameters to a feedforward neural network to predict wood defects. PSO is used as a learning algorithm. The MSE for training data is found to be 0.3483 and 78.26% accuracy is achieved for testing data. The proposed technique shows promising results to classify wood defects using a PSO trained neural network.