arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09193cs.CV
收藏

用于高效且有效深度网络训练的场景文本合成

Scene Text Synthesis for Efficient and Effective Deep Network Training

Changgong Zhang, Fangneng Zhan, Hongyuan Zhu, Shijian Lu

AI总结:

本文提出通过语义一致放置与和谐外观适配合成场景文本训练图像,以降低标注成本,并在检测与识别任务上达到接近或优于真实图像训练的效果。

摘要:

大量带标注的训练图像对于训练准确且鲁棒的深度网络模型至关重要,但收集大量带标注训练图像通常既耗时又昂贵。图像合成通过由机器自动生成带标注训练图像来缓解这一限制,近年来在深度学习研究中吸引了越来越多的关注。我们开发了一种创新的图像合成技术,通过将感兴趣前景对象(OOI)逼真地嵌入背景图像来组合带标注训练图像。所提出的技术包含两个关键组成部分,原则上可提升合成图像在深度网络训练中的实用性。第一是上下文感知的语义一致性,它确保 OOI 被放置在背景图像中语义连贯的区域附近。第二是和谐外观适配,它确保嵌入的 OOI 在几何对齐和外观真实性两方面都与周围背景相协调。所提出的技术已在两个相关但差异很大的计算机视觉挑战上进行评估,即场景文本检测和场景文本识别。在多个公共数据集上的实验证明了我们所提出图像合成技术的有效性——在深度网络训练中使用我们的合成图像,与使用真实图像相比,能够取得相似甚至更好的场景文本检测和场景文本识别性能。

英文摘要:

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 synthesis alleviates this constraint by generating annotated training images automatically by machines which has attracted increasing interest in the recent deep learning research. We develop an innovative image synthesis technique that composes annotated training images by realistically embedding foreground objects of interest (OOI) into background images. The proposed technique consists of two key components that in principle boost the usefulness of the synthesized images in deep network training. The first is context-aware semantic coherence which ensures that the OOI are placed around semantically coherent regions within the background image. The second is harmonious appearance adaptation which ensures that the embedded OOI are agreeable to the surrounding background from both geometry alignment and appearance realism. The proposed technique has been evaluated over two related but very different computer vision challenges, namely, scene text detection and scene text recognition. Experiments over a number of public datasets demonstrate the effectiveness of our proposed image synthesis technique - the use of our synthesized images in deep network training is capable of achieving similar or even better scene text detection and scene text recognition performance as compared with using real images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑