Estimation of Geo-Location of an Image Using Affective Image Classification

Abstract

Images have always been affecting viewers on an emotional level by portraying so much in a single frame. These emotions have been involved in human decision making. Machines can also be made emotionally intelligent using ‘Affective Computing’, giving them the ability of decision making by involving emotions. Emotional aspect of machine learning has been used in many areas like E-Health and E-learning etc. In this paper, the emotional aspect of machines have been used to detect Geo-location of an image. The proposed solution concentrates on a hybrid approach towards Affective Image Classification where the Elements-of-Art based emotional features (EAEF) and Principles-of-Art based emotional features (PAEF) are combined. Firstly, the generic features also known as Low-Level features or Element-of-Art features are extracted. Then, the Principle-of-Art features or Mid-Level features are extracted. These features are easily understandable by humans. Experiments are then performed on these two sets of features individually. These two sets are then combined together to obtain resultant Hybrid features and same experiments are performed on them. On comparison of results, it is indicated that the hybrid approach gives better accuracy then the individual approach. Images in this research work are downloaded from Yahoo Flickr Creative Commons 100 Million (YFCC100M) dataset which contains the co-ordinates of millions of images and are free to use.