There is a growing interest in scene text detection for arbitrary shapes. The effectiveness of text detection has also evolved from horizontal text detection to the ability to perform text detection in multiple directions and arbitrary shapes. However, scene text detection is still a challenging task due to significant differences in size and aspect ratio and diversity in shape, as well as orientation, coarse annotations, and other factors. Regression-based methods are inspired by object detection and have limitations in fitting the edges of arbitrarily shaped text due to the characteristics of their methods. Segmentation-based methods, on the other hand, perform prediction at the pixel level and thus can fit arbitrarily shaped text better. However, the inaccuracy of image text annotations and the distribution characteristics of text pixels, which contain a large number of background pixels and misclassified pixels, degrades the performance of segmentation-based text detection methods to some extent. Usually, considering whether a pixel belongs to a text region is highly dependent on the strength of the semantic information it has and the position of the pixel in the text area. Based on the above two points, we propose an innovative and robust method for scene text detection combining position and semantic information. First, we add position information to the images using a position encoding module (PosEM) to help the model learn the implicit feature relationships associated with the position. Second, we use the semantic enhancement module (SEM) to enhance the model’s focus on the semantic information in the image during feature extraction. Then, to minimize the effect of noise due to inaccurate image text annotations and the distribution characteristics of text pixels, we convert the detection results into a probability map that can more reasonably represent the text distribution. Finally, we reconstruct and filter the text instances using a post-processing algorithm to reduce false positives. The experimental results show that our model improves significantly on the Total-Text, MSRA-TD500, and CTW1500 datasets, outperforming most previous advanced algorithms.

The segmentation-based scene text detection algorithm has advantages in scene text detection scenarios with arbitrary shape and extreme aspect ratio, depending on its pixel-level description and fine post-processing. However, the insufficient use of semantic and spatial information in the network limits the classification and positioning capabilities of the network. Existing scene text detection methods have the problem of losing important feature information in the process of extracting features from each network layer. To solve this problem, the Attention-based Dual Feature Fusion Model (ADFM) is proposed. The Bi-directional Feature Fusion Pyramid Module (BFM) first adds stronger semantic information to the higher-resolution feature maps through a top-down process and then reduces the aliasing effects generated by the previous process through a bottom-up process to enhance the representation of multi-scale text semantic information. Meanwhile, a position-sensitive Spatial Attention Module (SAM) is introduced in the intermediate process of two-stage feature fusion. It focuses on the one feature map with the highest resolution and strongest semantic features generated in the top-down process and weighs the spatial position weight by the relevance of text features, thus improving the sensitivity of the text detection network to text regions. The effectiveness of each module of ADFM was verified by ablation experiments and the model was compared with recent scene text detection methods on several publicly available datasets.