Abstract: Focused on that limitation of single-layer structure on image feature learning ability, a deep architecture based on sparse representation of image blocks was proposed, namely Multi-layer incorporating Locality and non-negativity Laplacian Sparse Coding method (MLLSC). Each image was divided uniformly into blocks and SIFT (Scale-Invariant Feature Transform) feature extraction on each image block was performed. In the sparse coding stage, locality and non-negativity were added in the Laplacian sparse coding optimization function, dictionary learning and sparse coding were conducted at the first and second levels, respectively. To remove redundant features, Principal Component Analysis (PCA) dimensionality reduction was performed before the second layer of sparse coding. And finally, multi-class linear SVM (Support Vector Machine) was adopted for image classification. The experimental results on four standard datasets show that MLLSC has efficient feature expression ability, and it can capture deeper feature information of images. Compared with the single-layer algorithms, the accuracy of the proposed algorithm is improved by 3% to 13%; compared with the multi-layer sparse coding algorithms, the accuracy of the proposed algorithm is improved by 1% to 2.3%. The effects of different parameters were illustrated, which fully demonstrate the effectiveness of the proposed algorithm in image classification.

Key words: multi-layer architecture, hierarchical feature, locality, non-negativity, Laplacian sparse coding, Principal Component Analysis (PCA)

摘要： 针对单层稀疏编码结构对图像特征学习能力的局限性问题，提出了一个基于图像块稀疏表示的深层架构，即多层融合局部性和非负性的Laplacian稀疏编码算法（MLLSC）。对每个图像平均区域划分并进行尺度不变特征变换（SIFT）特征提取，在稀疏编码阶段，在Laplacian稀疏编码的优化函数中添加局部性和非负性，在第一层和第二层分别进行字典学习和稀疏编码，分别得到图像块级、图像级的稀疏表示，为了去除冗余特征，在进行第二层稀疏编码之前进行主成分分析（PCA）降维，最后采用多类线性支持向量机进行分类。在四个标准数据集上进行验证，实验结果表明，MLLSC方法具有高效的特征学习能力，能够捕获图像更深层次的特征信息，相对于单层结构算法准确率提高了3%~13%，相对于多层稀疏编码算法准确率提高了1%~2.3%；并对不同参数进行了对比分析，充分展现了其在图像分类中的有效性。

关键词: 多层架构, 层级特征, 局部性, 非负性, Laplacian稀疏编码, 主成分分析