The number of films is numerous and complex. A viewer wants to choose a favorite movie is time consuming. This study aims to develop an automatic film classification system. Firstly, a film is sampled frame by frame. The color space in terms of hue, saturation, and brightness value (HSV) in each frame is analyzed. Hence the mean and deviation of the HSV are computed and utilized as classification features for each film. These features are fed into deep learning neural networks. Twenty-five trailers are employed to train the model parameters of neural networks. In the classification phase, twenty-five trailers are classified into five categories, including science fiction, literature-love, action, comedy films, and horror and thrillers. Experimental results show that the proposed method can effectively classify the film types, where the precision rate can reach 93.3%.
Film classification Video recognition HSV analysis Neural networks Deep learning