Search

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature globally computed from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative power and poorer robustness. In this paper, we present a new system for scene text detection by proposing a novel text-attentional convolutional neural network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components. We develop a new learning mechanism to train the Text-CNN with multi-level and rich supervised information, including text region mask, character label, and binary text/non-text information. The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components. The training process is formulated as a multi-task learning problem, where low-level supervised information greatly facilitates the main task of text/non-text classification. In addition, a powerful low-level detector called contrast-enhancement maximally stable extremal regions (MSERs) is developed, which extends the widely used MSERs by enhancing intensity contrast between text patterns and background. This allows it to detect highly challenging text patterns, resulting in a higher recall. Our approach achieved promising results on the ICDAR 2013 data set, with an F-measure of 0.82, substantially improving the state-of-the-art results. [ABSTRACT FROM AUTHOR]

This paper investigates the generation of large field-of-view (FOV) and high-resolution (HR) panorama images for smartphones. Existing techniques like image stitching struggle to produce satisfactory results due to geometry misalignment and inconsistent appearance. To circumvent the inherent challenges of image stitching methods and generate high-quality panoramas, we treat the image stitching problem as a multiple-reference-based super-resolution problem. Specifically, one large-FOV low-resolution (LR) image and several overlapped small-FOV HR images are taken as inputs, where the LR image acts as a base and multi-view references provide rich HR information. Building on this foundation, a novel multi-view references image super-resolution framework (MVRefSR) is proposed. Within this framework, to address the residual geometric misalignment between the LR-Ref image pairs after coarse alignment, a flow-based RefSR network (FlowSRNet) is proposed, which super-resolves LR patches with corresponding HR references. To facilitate adaptive feature fusion and minimize distortion in structured regions, a fusion weight estimation module and a gradient branch are introduced in FlowSRNet. Finally, the large-FOV HR image is generated by combining these SR patches together. Furthermore, the lack of real-world RefSR datasets for smartphones is addressed by designing an innovative dataset construction pipeline. Extensive experiments demonstrate the superior performance of FlowSRNet and MVRefSR over the compared SR methods and image stitching software, which proves the effectiveness of generating panoramas from a new perspective. • A novel multi-view references image super-resolution framework (MVRefSR) is proposed to generate the large field-of-view and high-resolution panoramas from a new perspective. • Two modules, a fusion weight estimation module and a gradient branch, are adopted to enhance the performance of our reference-based super-resolution (RefSR) methods within our MVRefSR framework. • A new RefSR dataset generation pipeline and a real-world RefSR dataset are presented to address the lack of datasets and facilitate the study of real-world RefSR. • Experimental results demonstrate the superiority of our RefSR network and our framework MVRefSR, which proves the effectiveness of generating panoramas from a new perspective. [ABSTRACT FROM AUTHOR]