Keysers Daniel, Deselaers Thomas, Gollan Christian, Ney Hermann
Germany Research Center for Artificial Intelligence (DFKI GmbH), Image Understanding and Pattern Recognition Group, D-67663 Kaiserslautern, Germany.
IEEE Trans Pattern Anal Mach Intell. 2007 Aug;29(8):1422-35. doi: 10.1109/TPAMI.2007.1153.
We present the application of different nonlinear image deformation models to the task of image recognition. The deformation models are especially suited for local changes as they often occur in the presence of image object variability. We show that, among the discussed models, there is one approach that combines simplicity of implementation, low-computational complexity, and highly competitive performance across various real-world image recognition tasks. We show experimentally that the model performs very well for four different handwritten digit recognition tasks and for the classification of medical images, thus showing high generalization capacity. In particular, an error rate of 0.54 percent on the MNIST benchmark is achieved, as well as the lowest reported error rate, specifically 12.6 percent, in the 2005 international ImageCLEF evaluation of medical image categorization.
我们展示了不同非线性图像变形模型在图像识别任务中的应用。这些变形模型特别适用于局部变化，因为在存在图像对象变异性的情况下经常会出现这种变化。我们表明，在所讨论的模型中，有一种方法结合了实现的简单性、低计算复杂度以及在各种实际图像识别任务中的极具竞争力的性能。我们通过实验表明，该模型在四个不同的手写数字识别任务和医学图像分类中表现非常出色，从而显示出高泛化能力。特别是，在MNIST基准测试中实现了0.54%的错误率，以及在2005年国际ImageCLEF医学图像分类评估中报告的最低错误率，具体为12.6%。
