TRPN: A Text Region Proposal Network in the Wild under the Constraint of Low Memory GPU

Text region proposal is one of the fundamental tasks required for text detection and recognition in the natural images. This paper proposes a Convolutional Neural Network (CNN) based Text Region Proposal Network (TRPN) for generating word level region proposal. The proposed architecture is capable of getting trained on the low memory GPU and achieves a good recall with a limited number of region proposals to reduce the overhead on the detection and recognition task. The number of parameters of the proposed architecture is reduced to make it trainable on the low memory GPU by first decreasing the number of kernels and increasing them afterward. The in-network fusion is used to maintain localization accuracy which was reduced due to max-pooling operation. This fuses the feature map of different levels to obtain an efficient localization of text with different aspect ratio and size. The proposed architecture achieves a competitive recall with few tens of region proposals which are less compared to the state-of-the-art region proposal methods for text. The results are validated on test-set of ICDAR 2013 and SVT datasets.