Person re-identification refers to reidentifying individuals across non-overlapping camera views. In the scope of this research, we present a unique integration of Convolutional Neural Networks (CNNs) with Fuzzy Logic (FL) for person re-identification. This approach offers two key advantages: FL enhances change maps, improving information refinement, and the combination of CNN with FL reduces the need for extensive pixel-level data during training. The proposed Convolutional Fuzzy Neural Network (CFNN) framework operates through phases that transform input patterns into abstract, high-level features and assign class labels to probe images. Training CFNN involves distinct actions, utilizing convolutional networks and fine-tuning classifiers, resulting in an accurate and reliable model for person re-identification. This integration promises robust change mapping and streamlined training processes, with applications across various domains, including remote sensing.