Music Suggestions from Determining the Atmosphere of Images

Human emotion is affected by visual stimuli from all around the environment. This change in emotion and mood carries over to our tastes in various things, one of them being music. Computer vision and data mining are sub-fields of computer science that deal with the interpretation of visual media and analysis of temporal data to derive an outcome respectively. There has yet to be a method of interpreting visual media and associating it with any sort of music genre. Computer vision can be utilized to recognize the effect of visual elements of the environment on human emotion while data mining can be used to suggest appropriate music genres based on that emotion. This is the approach our paper used to solve the aforementioned problem.In this paper, we have used different models to interpret different attributes from a given image. In our implementation, five attributes were identified and five models were used to detect them. A few surveys were conducted to get a pattern in people’s taste in music according to visual stimuli. The results from the surveys were then used to recommend a music genre from the processed combination of attributes mentioned before. This shall provide a starting point and motivate further research of its kind.