高级检索

基于特征分块与域间融合的跨域足迹图像检索方法

Cross-domain Footprint Image Retrieval Based on Feature Partitioning and Domain Fusion

  • 摘要: 针对现有算法难以提取跨域足迹图像的高区分性域共享特征等问题. 本文提出了一种基于特征分块与域间融合的跨域足迹图像检索方法. 首先, 本文构建了一个包含200人的跨域足迹图像数据集, 并分析了不同域足迹图像的特点; 其次, 引入特征水平分块方法, 以获取更具鉴别性的局部特征; 最后, 采用跨域特征融合方法提取域共享信息, 并给出均衡损失以优化融合特征. 该方法在跨域足迹图像数据集上表现良好, 在光学检索压力及压力检索光学两种模式下Rank-1分别达到91.37%、84.50%.

     

    Abstract: Considering the challenges faced by existing algorithms in extracting highly discriminative domain-shared features from cross-domain footprint images, a cross-domain footprint image retrieval method based on feature partitioning and domain fusion is proposed. Firstly, a cross-domain footprint image dataset containing 200 individuals is constructed, and the characteristics of footprint images in two domains are analyzed. Secondly, a feature-level partitioning method is introduced to obtain more discriminative local features. Lastly, a cross-domain feature fusion method is employed to extract domain-shared information and design an equilibrium loss function to optimize the fused features. The proposed method performs well on the cross-domain footprint image dataset, achieving Rank-1 of 91.37% and 84.50% under optical retrieval pressure and pressure retrieval optical settings, respectively.

     

/

返回文章
返回