paper-with-me

홈 › Papers

Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes

2018-07-09 · ECCV 2018 9 · Fangneng Zhan, Shijian Lu, Chuhui Xue

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.

📄 PDF Abstract BibTeX arXiv:1807.03021

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationScene Text DetectionSemantic SegmentationText Detection

Similar Papers 제목 키워드 기반

Analysis by Synthesis: 3D Object Recognition by Object Reconstruction

2014-06-01 · CVPR 2014 6 · Mohsen Hejrati, Deva Ramanan

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 Reconstruction

Scene Text Synthesis for Efficient and Effective Deep Network Training

2019-01-26 · Changgong Zhang, Fangneng Zhan, Hongyuan Zhu, Shijian Lu

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 Detection

Transfer Learning with Convolutional Neural Networks for Rainfall Detection in Single Images

2021-02-24 · Water 2021 2 · Nicla Maria Notarangelo, Kohin Hirano, Raffaele Albano, Aurelia Sole

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 Learning

Exploring 2D Data Augmentation for 3D Monocular Object Detection

2021-04-21 · Sugirtha T, Sridevi M, Khailash Santhakumar, B Ravi Kiran 외

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+4

Thermal to Visible Synthesis of Face Images using Multiple Regions

2018-03-20 · Benjamin S. Riggan, Nathaniel J. Short, Shuowen Hu

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