At present, text spotting in natural scenes has become one of the research hotspots. Among them, curvilinear text and long text are the main difficulties of text spotting in natural scenes. To better solve these two types of problems, we propose a novel end-to-end text spotting model. The model includes three parts: shared convolution module, text detector module and text recognizer module. For the problem of long text, we adopt the corner attention mechanism to extract the features of long text more effectively. For the problem of curve text, we feed the rectification feature map into the SA-BiLSTM decoder to recognize the curve text more effectively. More importantly, the joint optimization strategy realizes the mutual promotion function of the text detection task and the text recognition task. Experimental results on TotalText, ICDAR2015, ICDAR2013, CTW1500, COCO-Text and MLT datasets prove that our method achieves excellent performance and robustness in text spotting tasks based on end-to-end natural scenes.
Aiming at the problem that the traditional OCR processing method ignores the inherent connection between the text detection task and the text recognition task, This paper propose a novel end-to-end text spotting framework. The framework includes three parts: shared convolutional feature network, text detector and text recognizer. By sharing convolutional feature network, the text detection network and the text recognition network can be jointly optimized at the same time. On the one hand, it can reduce the computational burden; on the other hand, it can effectively use the inherent connection between text detection and text recognition. This model add the TCM (Text Context Module) on the basis of Mask RCNN, which can effectively solve the negative sample problem in text detection tasks. This paper propose a text recognition model based on the SAM-BiLSTM (spatial attention mechanism with BiLSTM), which can more effectively extract the semantic information between characters. This model significantly surpasses state-of-the-art methods on a number of text detection and text spotting benchmarks, including ICDAR 2015, Total-Text.
The fire recognition model based on deep learning can avoid many defects in the traditional method, but its construction requires a large amount of data to train the network parameters, and it takes a lot of time. In order to improve the accuracy of the model, this paper proposes a fire recognition model TNVGG-19 (Transfer learning + Newly fully connected layer module + VGG-19) with convolutional neural network based on transfer learning. First, we use the strategy of transfer learning to train the feature extraction network. Secondly, based on the VGG-19 model, this paper adds a newly designed fully connected layer module. Considering that flame data belongs to small sample data, we adopted a data augmentation strategy. Experiments show that the TNVGG-19 fire recognition model based on transfer learning proposed in this paper can effectively improve the accuracy of fire prediction and reduce the false alarm rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.