Deep multi-modal networks for book genre classification based on its cover

원문 초록

Book covers are usually the very first impression to its readers and they often convey important information about the content of the book. Book genre classification based on its cover would be utterly beneficial to many modern retrieval systems, considering that the complete digitization of books is an extremely expensive task. At the same time, it is also an extremely challenging task due to the following reasons: First, there exists a wide variety of book genres, many of which are not concretely defined. Second, book covers, as graphic designs, vary in many different ways such as colors, styles, textual information, etc, even for books of the same genre. Third, book cover designs may vary due to many external factors such as country, culture, target reader populations, etc. With the growing competitiveness in the book industry, the book cover designers and typographers push the cover designs to its limit in the hope of attracting sales. The cover-based book classification systems become a particularly exciting research topic in recent years. In this paper, we propose a multi-modal deep learning framework to solve this problem. The contribution of this paper is four-fold. First, our method adds an extra modality by extracting texts automatically from the book covers. Second, image-based and text-based, state-of-the-art models are evaluated thoroughly for the task of book cover classification. Third, we develop an efficient and salable multi-modal framework based on the images and texts shown on the covers only. Fourth, a thorough analysis of the experimental results is given and future works to improve the performance is suggested. The results show that the multi-modal framework significantly outperforms the current state-of-the-art image-based models. However, more efforts and resources are needed for this classification task in order to reach a satisfactory level.