Image Classification Using Hierarchical Feature Learning Method Combined with Image Saliency
-
摘要: 高效的图像特征表示是计算机视觉的基础.基于图像的视觉显著性机制及深度学习模型的思想，提出一种融合图像显著性的层次稀疏特征表示用于图像分类.这种层次特征学习每一层都由3个部分组成：稀疏编码、显著性最大值汇聚(saliency max pooling)和对比度归一化.通过在图像层次稀疏表示中引入图像显著信息，加强了图像特征的语义信息，得到图像显著特征表示.相比于手工指定特征，该模型采用无监督数据驱动的方式直接从图像中学习到有效的图像特征描述.最后采用支持向量机(support vector machine, SVM)分类器进行监督学习，实现对图像进行分类.在2个常用的标准图像数据集(Caltech 101和Caltech 256)上进行的实验结果表明，结合图像显著性信息的层次特征表示，相比于基于局部特征的单层稀疏表示在分类性能上有了显著提升.Abstract: Efficient feature representations for images are essential in many computer vision tasks. In this paper, a hierarchical feature representation combined with image saliency is proposed based on the theory of visual saliency and deep learning, which builds a feature hierarchy layer-by-layer. Each feature learning layer is composed of three parts: sparse coding, saliency max pooling and contrast normalization. To speed up the sparse coding process, we propose batch orthogonal matching pursuit which differs from the traditional method. The salient information is introduced into the image sparse representation, which compresses the feature representation and strengthens the semantic information of the feature representation. Simultaneously, contrast normalization effectively reduces the impact of local variations in illumination and foreground-background contrast, and enhances the robustness of the feature representation. Instead of using hand-crafted descriptors, our model learns an effective image representation directly from images in an unsupervised data-driven manner. The final image classification is implemented with a linear SVM classifier using the learned image representation. We compare our method with many state-of-the-art algorithms including convolutional deep belief networks, SIFT based single layer or multi-layer sparse coding methods, and some kernel based feature learning approaches. The experimental results on two commonly used benchmark datasets Caltech 101 and Caltech 256 show that our method consistently and significantly improves the performance.
-
-
期刊类型引用(7)
1. 刘琳岚，唐家威，朱文俊. 基于特征相似性的机会网络链路预测. 工程科学与技术. 2025(02): 12-21 . 
百度学术
2. 邬剑升，李玉珩. 基于共同邻居惩罚的复杂网络链路预测方法. 计算机测量与控制. 2023(03): 71-75+139 . 百度学术
3. 王子健，薛家玥，杨鹏飞，李艺茹，相洁. 基于对抗生成网络的时序脑功能网络预测方法. 太原理工大学学报. 2023(05): 830-837 . 百度学术
4. 康驻关，金福生，王国仁. 基于Motif聚集系数与时序划分的高阶链接预测方法. 软件学报. 2021(03): 712-725 . 百度学术
5. 高雅娟，王玉峰. 融合多维特征的ISP网络拓扑匹配优化仿真. 计算机仿真. 2021(02): 278-281+286 . 百度学术
6. 顾秋阳，吴宝，池仁勇. 基于高阶路径相似度的复杂网络链路预测方法. 通信学报. 2021(07): 61-69 . 百度学术
7. 王瑾. 动态有向网络中的时序链路预测问题研究. 粘接. 2021(09): 106-109 . 百度学术
其他类型引用(8)
计量
- 文章访问数: 1617
- HTML全文浏览量: 1
- PDF下载量: 1191
- 被引次数: 15
下载:
