Real-world images often encompass embedded texts that adhere to disparate disciplines like business, education, and amusement, to name a few. Such images are graphically rich in terms of font attributes, color distribution, foreground-background similarity, and component organization. This aggravates the difficulty of recognizing texts from these images. Such characteristics are very prominent in the case of movie posters. One of the first pieces of information on movie posters is the title. Automatic recognition of movie titles from images can aid in efficient indexing as well as information conveyance. However, it is accompanied by other texts like the names of actors, producers, taglines, dates, etc. Though the organization of components is somewhat similar across different film industries like Tollywood (West Bengal), Bollywood (Mumbai), and Hollywood (Los Angeles), the graffiti patterns differ in multifarious instances. To address the problem of movie title understanding, we propose a dataset named MOvie POsters-Hollywood Bollywood Tollywood (MOPO-HBT) that encompasses movie posters from the aforementioned industries. The entire dataset is publicly available (link ) for research purposes. The baseline results of text identification and recognition were obtained with a CNN-based (Convolutional neural network) approach, wherein the titles were extracted using the M-EAST (Modified-Efficient and Accurate Scene Text detector) model.
The MOPO-HBT dataset contains 5 directories namely, Tollywood_Bangla, Tollywood_Roman, Bollywood_Devanagari, Bollywood_Roman, and Hollywood_Roman.
The Tollywood_Bangla and Tollywood_Roman represent Tollywood posters having Bangla and Roman titles, respectively,
since the titles in these poster images can be written in Bangla or in Roman.
Similarly, there are titles written in Devanagari or Roman for Bollywood posters.
Several posters from the original film, featuring various themes but identical typography,
were also included in MOPO-HBT.
The ground truth files correspond to the same names as the directory names (e.g., Tollywood_Bangla ground truth).
The ground truth file is presented as the image name, the number of words in a movie title, the angle of inclination
of each word of the title, the script of the title, and the actual text corresponding to the title. Contact the Author for the Password.