As one of human biometric features, footprint is of great significance in the field of biometric identification. However, the pressure footprint images of different shoe types for the same person have significant differences in the footprint contour features, leading to large intra-class differences. For cross-domain retrieval of pressure footprint images, this paper proposed a cross-domain pressure footprint images retrieval method based on mutual information disentangled representations. Firstly, a multi-domain pressure footprint dataset containing 200 people’ s footprint images was constructed and the characteristics of cross-domain pressure footprint images were analyzed from qualitative and quantitative perspectives. Secondly, two independent encoders were used to construct an image disentanglement module, which disentangles the pressure footprint images into a domain-specific representation and a domain-shared representation, and ensures that the domain-specific representation contains more domain-related information through domain classification. Then, the distance between the domain-specific representation and the domain-shared representation was enlarged by minimizing mutual information loss. At the same time, in order to avoid the loss of information in the disentangled process, the original pressure footprint image was reconstructed based on the domain-specific representation and the domain-shared representation. Finally, the deep convolution features of the domain-shared representation were further extracted by feature extraction module and the cross-domain pressure footprint images retrieval was realized through the metric module which calculates the correlation degree between different features. The results of comparison and ablation experiments show that the disentanglement module of this method is effective and performs well on multi-domain pressure footprint dataset. The retrieval accuracy of the first query result reached 79.83%, and the average accuracy reached 65.48%.

With the development of biometric recognition technology, the research of tactile pressure footprint classification has been more and more frequently used, and the traditional classification method is labor-intensive. For tactile pressure footprint classification, the paper proposed a tactile pressure footprint classification method of fusion distribution graph network. Firstly, the convolutional features of the tactile pressure footprint image was extracted through the embedding module and the sample correlation matrix was obtained with the norm-regularization method. Then the fusion correlation matrix between the samples and the label one-hot vector was formed, and feature information was added through the self-attention module. A new feature distribution graph was obtained through the distribution module, and an association matrix between the labeled sample and the unlabeled sample was constructed. Finally, the convolution feature and feature distribution graph of the tactile pressure footprint image were used as the input of the update module to implement the tactile pressure footprint classification. The experimental results show that, compared with the few-shot classification method, this new method’s classification accuracy of 5-way 1-shot experiments on Mini-Imagenet and Tiered-Imagenet data set reached 71.71% and 74.34%, respectively. Meanwhile, the 5-way 1-shot and 5-way 5-shot experiments on the left and right foot data sets of tactile pressure reached 88.87% and 98.66%, respectively.

When using semantic segmentation methods to automatically segment barefoot footprint images, although manual intervention can be reduced, the issue of blurred toe regions in barefoot footprint image segmentation requires the neural network model to pay more attention to feature extraction from these areas. For barefoot footprint images with uneven lighting, the model can establish contextual relationships between the global and local regions of the footprint, using the feature information from the global region to enhance the feature expression of the uneven lighting areas, thereby improving the accuracy and robustness of image segmentation. To address this, this paper proposed a barefoot footprint segmentation method based on multi-granularity feature-region relationships. By using local region labels, the method enhances feature representation in the toe area, extracts multi-granularity features of footprints, and integrates them with global footprint features to improve segmentation performance in blurred areas. Meanwhile, spatial transformations were applied to both the original image and the footprint feature map, and a matrix multiplication approach was used to establish a barefoot region relationship matrix between them. This relationship matrix was then utilized to spatially modulate the global barefoot features, achieving feature enhancement. Furthermore, this paper constructed an in-the-wild barefoot footprint dataset consisting of 1100 barefoot footprint images from 25 individuals and conducted experiments on four types of barefoot footprint images: blurred, unevenly illuminated, both blurred and unevenly illuminated, and normal. The results show that the intersection over union (IoU) for the barefoot class reaches 93.50% on normal barefoot footprint images. For blurred, uneven lighting, and blurry-uneven lighting images, the IoU are 92.90%, 93.06%, and 91.66%, respectively. Notably, the IoU for blurry-uneven lighting images is improved by 1.15 percentage points compared to U-Net.