Movie Posters’ Classification into Multiple Genres

Our project intends to classify movies into the three most probable genres that they belong to, from a predefined set of 25 genres, based on only one image i.e movie poster. We have made use Convolutional Neural Networks (CNN) realize this as we believe it would be help extract features and visual information image. Instead multi-class classification problem in which input is classified any class, more correctly described multilabel belongs than genre. In see comparative study different architectures tune them yield best result metric accuracy. applied various techniques such data augmentation L2 regularization comparatively deduce model performs all tested models.