Scene Categorization Using Invariant Moments and Neural Networks

Thousands of images are generated every day, which implies the necessity to classify, organize and access them using an easy, faster and efficient way. Scene classification, the classification of images into semantic categories (e.g., coast, mountains, highways and streets) is a challenging and important problem nowadays. Many different approaches concerning scene classification have been proposed in the last few years. This paper presents a different approach using invariant geometric moments and artificial neural networks to scene classification. Feed forward neural networks with backpropagation algorithm are used for ANN. The results are proving the efficiency of this work with 83.5% classification rate. This complete work is carried out using real world data set.