Lampinen J, Oja E
Dept. of Inf. Technol., Lappeenranta Univ. of Technol.
IEEE Trans Neural Netw. 1995;6(3):539-47. doi: 10.1109/72.377961.
A generic, modular, neural network-based feature extraction and pattern classification system is proposed for finding essentially two-dimensional objects or object parts from digital images in a distortion tolerant manner, The distortion tolerance is built up gradually by successive blocks in a pipeline architecture. The system consists of only feedforward neural networks, allowing efficient parallel implementation. The most time and data-consuming stage, learning the relevant features, is wholly unsupervised and can be made off-line. The consequent supervised stage where the object classes are learned is simple and fast. The feature extraction is based on distortion tolerant Gabor transformations, followed by minimum distortion clustering by multilayer self-organizing maps. Due to the unsupervised learning strategy, there is no need for preclassified training samples or other explicit selection for training patterns during the training, which allows a large amount of training material to be used at the early stages, A supervised, one-layer subspace network classifier on top of the feature extractor is used for object labeling. The system has been trained with natural images giving the relevant features, and human faces and their parts have been used as the object classes for testing. The current experiments indicate that the feature space has sufficient resolution power for a moderate number of classes with rather strong distortions.
提出了一种通用的、模块化的、基于神经网络的特征提取和模式分类系统，用于以容错方式从数字图像中找到本质上的二维物体或物体部分。容错能力通过流水线架构中的连续模块逐步建立。该系统仅由前馈神经网络组成，允许高效并行实现。最耗时和耗数据的阶段，即学习相关特征，完全是无监督的，并且可以离线进行。随后学习对象类别的监督阶段简单且快速。特征提取基于容错Gabor变换，然后通过多层自组织映射进行最小失真聚类。由于采用无监督学习策略，训练期间无需预分类的训练样本或对训练模式进行其他明确选择，这使得在早期阶段可以使用大量训练材料。在特征提取器之上使用有监督的单层子空间网络分类器进行对象标记。该系统已使用给出相关特征的自然图像进行训练，并使用人脸及其部分作为测试的对象类别。当前实验表明，对于中等数量的具有相当大失真的类别，特征空间具有足够的分辨率能力。
