arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1601.07883cs.CV
收藏

一种端到端的图像和视频自动识别系统的设计

Towards the Design of an End-to-End Automated System for Image and Video-based Recognition

University of Maryland, College Park(马里兰大学帕克分校);Rutgers University(罗格斯大学)

Rama Chellappa, Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan, Amit Kumar, Vishal M. Patel, Carlos D. Castillo

摘要:

几十年来,从事对象识别的研究人员一直渴望一种端到端的自动化系统,该系统将简单地接受2D或3D图像或视频作为输入,并在输入数据中输出对象的标签。使用基于几何、辐射和神经考虑以及统计和结构匹配器导出的表示的计算机视觉方法以及基于人工神经网络的方法(其中多层网络学习从输入到类别标签的映射)已经为图像识别问题提供了竞争方法。在过去的四年中,基于深度卷积神经网络(DCNN)的方法在目标检测/识别挑战问题上表现出令人印象深刻的性能改进。这是由于大量注释数据的可用性,对图像和类别标签之间的非线性映射的更好理解以及GPU的可负担性。在本文中,我们提出了一个简短的历史,在计算机视觉和人工神经网络在过去的四十年的发展,基于图像的识别问题。然后,我们提出了一个用于端到端无约束人脸验证/识别的深度学习系统的设计细节。然后讨论了关于DCNN用于对象识别问题的一些公开问题。我们提醒读者,本文所表达的观点仅来自作者和作者!

英文摘要:

Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output the labels of objects in the input data. Computer vision methods that use representations derived based on geometric, radiometric and neural considerations and statistical and structural matchers and artificial neural network-based methods where a multi-layer network learns the mapping from inputs to class labels have provided competing approaches for image recognition problems. Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements on object detection/recognition challenge problems. This has been made possible due to the availability of large annotated data, a better understanding of the non-linear mapping between image and class labels as well as the affordability of GPUs. In this paper, we present a brief history of developments in computer vision and artificial neural networks over the last forty years for the problem of image-based recognition. We then present the design details of a deep learning system for end-to-end unconstrained face verification/recognition. Some open issues regarding DCNNs for object recognition problems are then discussed. We caution the readers that the views expressed in this paper are from the authors and authors only!

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。

↑