FionaDong的博客

1. AbstractWe propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.The CTPN detects a text line in a sequence of fine-scale text proposals directly in convolutional feature maps.We develop a ve

1. RNN(Recurrent Neural Networks)Each word based on your understanding of previous words. Your thoughts have persistence.Traditional neural networks can’t do this, and it seems like a major shortcoming.Recurrent neural networks address this issue. They

1. AbstractOCR is still a challenging task due to the various of text appearances and the demand of computational efficiency.In this paper, we propose a practical ultra lightweight OCR system, i.e., PP- OCR.The overall model size of the PP-OCR is only 3

1. AbstractIn this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition.A novel neural net- work architecture, which integrates feature extraction, se- qu

1. AbstractRecently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.However, the post-processing of binarization is essential

1. A Recipe for Training Neural NetworksGoalFollow a certain process to avoid making common errors (or fix them very fast).1.1 Two important observations1.1.1 Neural net training is a leaky abstractionFor standard software, like:>>> r = re