Bianchini M, Maggini M, Sarti L, Scarselli F
Dipartimento di Ingegneria dell'Informazione Università degli Studi di Siena Via Roma, 56 53100--Siena (Italy).
Neural Netw. 2005 Oct;18(8):1040-50. doi: 10.1016/j.neunet.2005.07.003. Epub 2005 Sep 21.
In this paper, we introduce a new recursive neural network model able to process directed acyclic graphs with labelled edges. The model uses a state transition function which considers the edge labels and is independent both from the number and the order of the children of each node. The computational capabilities of the new recursive architecture are assessed. Moreover, in order to test the proposed architecture on a practical challenging application, the problem of object detection in images is also addressed. In fact, the localization of target objects is a preliminary step in any recognition system. The proposed technique is general and can be applied in different detection systems, since it does not exploit any a priori knowledge on the particular problem. Some experiments on face detection, carried out on scenes acquired by an indoor camera, are reported, showing very promising results.
在本文中，我们介绍了一种新的递归神经网络模型，它能够处理带有标记边的有向无环图。该模型使用一个状态转移函数，该函数考虑边的标签，并且独立于每个节点的子节点数量和顺序。我们评估了这种新递归架构的计算能力。此外，为了在一个实际具有挑战性的应用中测试所提出的架构，我们还探讨了图像中的目标检测问题。事实上，目标物体的定位是任何识别系统的初步步骤。所提出的技术具有通用性，可应用于不同的检测系统，因为它不利用关于特定问题的任何先验知识。我们报告了一些在室内相机采集的场景上进行的人脸检测实验，结果显示非常有前景。
