Angelopoulou Anastassia, Garcia Rodriguez Jose, Orts-Escolano Sergio, Gupta Gaurav, Psarrou Alexandra
1Faculty of Science and Technology, University of Westminster, 115 New Cavendish Street, Middlesex, W1W 6UW UK.
2Department of Computing Technology, University of Alicante, PO Box 99, 03080 Alicante, Spain.
Neural Comput Appl. 2018;29(10):903-919. doi: 10.1007/s00521-016-2579-y. Epub 2016 Sep 22.
This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.
这项工作展示了一个利用自组织网络对视觉对象进行建模的实时系统的设计。该系统的架构可处理多种计算机视觉任务，如图像分割、最优参数估计和对象表示。我们首先利用自组织映射的增长机制开发了一个构建非刚性形状的框架，然后基于从信息论考虑中获得的知识，定义了一个最优的节点数量，以避免网络出现过拟合或欠拟合的情况。我们展示了针对手部和面部的实验结果，并定量评估了所提方法与地形积的匹配能力。所提方法易于扩展到三维对象，因为它为高效的网格重建提供了类似的特征。
