ABSTRACT One of the core challenges in developing a computer system for machine learning is to make the system learn efficiently and effectively like a real human by grasping the domain knowledge exemplified by human experts. In this challenge, we have introduced a hybrid image synthesis model that can simulate one of the human’s learning capabilities in the vision field – the ability to synthesize images of convex objects by identifying solid geometries and textures of specific objects using few photographs. We have incorporated an ontology-based, domain knowledge on solid geometries into our model to synthesize large number of training images with only a minimum number of input images. Our initial experiments have shown that our model has convincing improvements by demonstrating a substantially better FAR/FRR/EER results when it is compared with a smaller set of non-synthetic images.

中文翻译：

---

一种基于本体的凸对象图像合成与识别混合方法

摘要 开发用于机器学习的计算机系统的核心挑战之一是通过掌握以人类专家为例的领域知识，使系统像真人一样高效地学习。在这个挑战中，我们引入了一种混合图像合成模型，该模型可以模拟人类在视觉领域的学习能力之一——通过使用少量照片识别特定物体的立体几何形状和纹理来合成凸面物体图像的能力。我们已将基于本体的实体几何领域知识纳入我们的模型，以仅用最少数量的输入图像合成大量训练图像。