Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
The requirement of large amounts of annotated images has become one grand challenge while training deep neural network models for various visual detection and recognition tasks. This paper presents a novel image synthesis technique that aims to generate a large amount of annotated scene text images for training accurate and robust scene text detection and recognition models. The proposed technique consists of three innovative designs. First, it realizes "semantic coherent" synthesis by embedding texts at semantically sensible regions within the background image, where the semantic coherence is achieved by leveraging the semantic annotations of objects and image regions that have been created in the prior semantic segmentation research. Second, it exploits visual saliency to determine the embedding locations within each semantic sensible region, which coincides with the fact that texts are often placed around homogeneous regions for better visibility in scenes. Third, it designs an adaptive text appearance model that determines the color and brightness of embedded texts by learning from the feature of real scene text images adaptively. The proposed technique has been evaluated over five public datasets and the experiments show its superior performance in training accurate and robust scene text detection and recognition models.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationScene Text DetectionSemantic SegmentationText DetectionSimilar Papers 제목 키워드 기반
Analysis by Synthesis: 3D Object Recognition by Object Reconstruction
We introduce a new approach for recognizing and reconstructing 3D objects in images. Our approach is based on an analysis by synthesis strategy. A forward synthesis model constructs possible geometric interpretations of …
3D Object RecognitionObjectObject RecognitionObject ReconstructionScene Text Synthesis for Efficient and Effective Deep Network Training
A large amount of annotated training images is critical for training accurate and robust deep network models but the collection of a large amount of annotated training images is often time-consuming and costly. Image syn…
Image GenerationScene Text DetectionScene Text RecognitionText DetectionTransfer Learning with Convolutional Neural Networks for Rainfall Detection in Single Images
Near real-time rainfall monitoring at local scale is essential for urban flood risk mitigation. Previous research on precipitation visual effects supports the idea of vision-based rain sensors, but tends to be device-spe…
Image ClassificationTransfer LearningExploring 2D Data Augmentation for 3D Monocular Object Detection
Data augmentation is a key component of CNN based image recognition tasks like object detection. However, it is relatively less explored for 3D object detection. Many standard 2D object detection data augmentation techni…
2D Object Detection3D geometry3D Object DetectionData Augmentation+4Thermal to Visible Synthesis of Face Images using Multiple Regions
Synthesis of visible spectrum faces from thermal facial imagery is a promising approach for heterogeneous face recognition; enabling existing face recognition software trained on visible imagery to be leveraged, and allo…
Face RecognitionFacial Landmark DetectionHeterogeneous Face RecognitionImage Registration