Semantic Constraint Based Target Object Recognition
Semantic Constraint Based Target Object Recognition
复制标题
DOI：
10.1016/j.ijleo.2017.12.033
复制
发表时间：
2018-03
期刊：
影响因子：
3.1
通讯作者：
Hao Wu;R. Bie;Junqi Guo;Xin Meng;Shenling Wang
中科院分区：
文献类型：
--
作者：
Hao Wu;R. Bie;Junqi Guo;Xin Meng;Shenling Wang
随着深度学习的发展，对象识别的研究越来越受到人们的关注，其准确率在过去几年中得到了显著的提高，然而高质量的识别在很大程度上依赖于大量的学习实例。如果学习实例的数量减少，就很难保持现实的识别准确度。此外，传统的方法通常不考虑不同区域之间的语义关系。针对上述问题，提出了一种基于语义约束的目标识别方法。一方面，基于实例的迁移学习模型可以利用其他类别的学习实例来保持真实的识别精度。另一方面，将不同区域之间的语义约束模拟为联合熵，以更准确地识别目标对象。最后，通过大量的图像实验表明，该模型不仅可以减少学习实例的数量，而且可以实现真实感的识别。
With the growth of deep learning, object recognition has received increasing interests and its accuracy has been improved significantly in the past few years, However, high-quality recognition largely depends on a large number of learning instances. If the number of learning instances is reduced, it’s difficult to maintain realistic recognition accuracy. Moreover, traditional methods usually don’t consider the semantic relationship between different regions. Actually, semantic constraint would contribute to improve the recognition accuracy effectively.Aiming at the problems above, we proposed one semantic constraint based object recognition method. On the one hand, instance-based transfer learning model could make use of learning instances of other categories to maintain realistic recognition accuracy. On the other hand, semantic constraint between different regions simulated as joint entropy is used to recognize target object more accurately. At last, adequate experiments using a large number of images show that our model not only could reduce the number of learning instances but also could achieve realistic recognition.