Context-Aware Edge-Cloud Collaborative Scene Text Recognition

Scene text recognition can extract key information in the image to enable the machine to understand the semantics contained in the image, which can also play a vital role in tasks such as video understanding or video clip positioning. There are multiple irregular texts in various scene images. How to identify such irregular texts to better understand the semantics contained in the images is a tough challenge. Most of the existing scene text detection methods adopt a unified model to detect scene text indiscriminately when dealing with scene text of arbitrary shape, which results in the high model complexity and large detection delay. Facing the above problems, a context-aware edge-cloud collaborative scene text recognition method is proposed. First, an edge-cloud collaborative scene text detection architecture is designed to take advantages of the computing resource characteristics of the cloud layer and the edge layer for collaborative scene text detection. Second, a multi-category scene text context awareness method is proposed, and the attention mechanism is introduced to perceive the scene where it is located to realize the rapid classification of multi-category scene text. Furthermore, an adaptive multi-category scene text detection method is devised, and the optimal detection strategy is determined according to the classification results to reduce the computational cost of model detection. Validation results show that our method compared with traditional methods can effectively reduce 19% of the detection delay while ensuring recognition accuracy in comparison with existing methods.