FaSTExt: Fast and Small Text Extractor
Autor: | Ivan Zagaynov, Konstantin Gudkov, Alexander Filonenko, Aleksei Lebedev, Nikita Orlov |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
I.2.10 Relation (database) Scale (ratio) Computer science business.industry Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition Convolutional neural network Convolution Component (UML) Artificial intelligence business Word (computer architecture) |
Zdroj: | CBDAR@ICDAR |
Popis: | Text detection in natural images is a challenging but necessary task for many applications. Existing approaches utilize large deep convolutional neural networks making it difficult to use them in real-world tasks. We propose a small yet relatively precise text extraction method. The basic component of it is a convolutional neural network which works in a fully-convolutional manner and produces results at multiple scales. Each scale output predicts whether a pixel is a part of some word, its geometry, and its relation to neighbors at the same scale and between scales. The key factor of reducing the complexity of the model was the utilization of depthwise separable convolution, linear bottlenecks, and inverted residuals. Experiments on public datasets show that the proposed network can effectively detect text while keeping the number of parameters in the range of 1.58 to 10.59 million in different configurations. 6 pages, 8th International Workshop on Camera-Based Document Analysis & Recognition |
Databáze: | OpenAIRE |
Externí odkaz: |