Indoor Outdoor Scene Classification using Deep Learning Neural Networks

Scene recognition is one of the most successful applications of image analysis and it has gained much attention in recent years. A scene recognition system is automatically identifying places by using place databases. Scene classification is act as an image retrieval task which consists of determining a match between the current scene and a previously visited location. Traditional neural networks such as probabilistic neural networks take a maximum time to classification task and performance is not as best. In order to improve the performance and classification speed ,the neural networks are used for scene classification. In recent times, Convolutional neural networks have been shown to achieve brand new performance on various classification tasks. In this project, indoor and outdoor scene classification technique based on Convolutional neural networks is presented. The two databases: places 205 and places 365 is used for scene classification in this proposed method.