图像细粒度识别的显著性特征学习算法研究

项目名称： 图像细粒度识别的显著性特征学习算法研究

项目编号： No.61472313

项目类型： 面上项目

立项/批准年度： 2015

项目学科： 计算机科学学科

项目作者： 孙剑

作者单位： 西安交通大学

项目金额： 82万元

中文摘要： 细粒度图像识别主要关注对图像的细粒度类别信息或者属性信息进行识别，例如对鸟类的不同子类或人的不同属性进行识别。与传统图像识别问题不同，该问题需要在大量相似属性中发现不同细粒度类别或属性的显著性特征。本课题主要关注解决上述问题的机器学习基础算法。主要研究思路为：首先，建模和学习物体的中层姿态和部件模板，并进行姿态和部件对准；然后，研究物体的精细特征学习方法,挖掘描述细粒度类别或者属性信息的显著性特征；最后，面向大规模细粒度图像数据集，研究高效的并行和随机优化算法。针对上述研究思路，该课题将结合深度学习和稀疏性建模思想，学习和选择具有高判别能力的物体部件和显著性图像特征。细粒度图像识别问题研究为解决图像深层语义理解提供基础，为机器学习领域的特征学习研究提供新的方法和平台，并在安全监控、生物物种识别、人工智能等领域具有广泛应用。

中文关键词： 细粒度图像识别；特征学习；稀疏性；深度学习；属性学习

英文摘要： Fine-grained image recognition mainly focuses on the recognition of fine-grained sub-categories or attributes, e.g., the recognition of sub-categories of birds or human attributes. Contrary to the traditional image recognition problem, fine-grained recognition requires to investigate the salient or discriminative features from a large set of similar features to discriminate / describe the sub-categories or attributes. This project aims to develope novel machine learning algorithms to learn the salient features for fine-grained recognition. First, we will model and learn the mid-level templates of object poses and parts, and align the objects based on these templates. Then,we will learn a large set of fine features and select discriminative features for sub-categories or attributes. Finally, we will propose efficient parallel or stochastic optimization algorithms for the optimization of feature learning models over big image database. To achieve this, we will develop novel models based on the sparsity and deep learning approaches. Fine-grained image recognition is the basis for high-level image understanding, and also provides a research platform for feature learning methods in machine learning. It can be widely applied to video surveillance,species identification, artifical intelligence, etc.

英文关键词： Fine-grained image recognition;Feature learning;Sparsity;Deep learning;Attributes learning