Skip to main content
QUICK REVIEW

[论文解读] A Parallel Framework for Multilayer Perceptron for Human Face Recognition

Mrinal Kanti Bhowmik, Debotosh Bhattacharjee|arXiv (Cornell University)|Jul 5, 2010
Face and Expression Recognition参考文献 9被引用 5
一句话总结

本文提出了一种用于人脸识别中多层感知机(MLPs)的并行训练框架,比较了两种架构:全类合一网络(ACON)与单类单网络(OCON)。通过同时在独立的网络中训练每个类别,OCON相比传统的顺序ACON训练实现了更快的训练收敛速度,展示了在光照变化和姿态变化等挑战性条件下,对复杂实时模式识别任务的改进效率。

ABSTRACT

Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perceptron (MLP) have been demonstrated. The first architecture is All-Class-in-One-Network (ACON) where all the classes are placed in a single network and the second one is One-Class-in-One-Network (OCON) where an individual single network is responsible for each and every class. Capabilities of these two architectures were compared and verified in solving human face recognition, which is a complex pattern recognition task where several factors affect the recognition performance like pose variations, facial expression changes, occlusions, and most importantly illumination changes. Both the structures were implemented and tested for face recognition purpose and experimental results show that the OCON structure performs better than the generally used ACON ones in term of training convergence speed of the network. Unlike the conventional sequential approach of training the neural networks, the OCON technique may be implemented by training all the classes of the face images simultaneously.

研究动机与目标

  • 解决大规模人脸识别任务中多层感知机(MLPs)训练速度缓慢的问题。
  • 通过利用并行计算提升复杂模式识别的训练效率。
  • 比较两种MLP架构——ACON(所有类别集成于一个网络)与OCON(每个类别对应一个网络)——在人脸识别中的性能表现。
  • 评估并行训练对收敛速度及在真实世界变化(如光照、姿态和表情)下识别鲁棒性的影响。

提出的方法

  • 设计一种并行框架,其中人脸识别中的每个类别均使用专用的MLP网络进行训练(即OCON架构)。
  • 实现所有类别专用网络的同时训练,以加速收敛过程。
  • 在具有受控光照、姿态和表情变化的人脸识别数据集上,对比OCON与ACON架构的性能。
  • 在每个网络内使用标准反向传播算法进行权重更新,并在多个处理器或计算节点上并行执行。
  • 基于不同条件下的训练收敛速度和识别准确率来评估性能表现。
  • 将该框架应用于真实世界的人脸图像数据集,以测试其在具有挑战性视觉变化下的鲁棒性。

实验结果

研究问题

  • RQ1为每个类别单独训练MLP网络(即OCON)是否能实现比为所有类别训练单一网络(即ACON)更快的收敛速度?
  • RQ2对类别专用网络进行并行训练,如何影响在光照和姿态变化下的识别准确率?
  • RQ3与顺序ACON训练相比,OCON架构是否能在显著缩短训练时间的同时保持高识别性能?
  • RQ4OCON与ACON架构在面部表情变化和遮挡情况下的相对鲁棒性如何?

主要发现

  • OCON架构相比传统的ACON方法实现了更快的训练收敛速度。
  • OCON在训练速度方面表现出更优性能,因此更适合用于实时复杂模式识别任务。
  • 两种架构对表情变化和遮挡均具有鲁棒性,但OCON在光照变化下仍能保持更优的收敛性能。
  • OCON的并行实现允许所有类别专用网络同时训练,显著缩短了整体训练时间。
  • 实验结果证实,OCON在收敛速度方面优于ACON,且未牺牲识别准确率。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。