This paper presents a novel approach to enhancing image comparison through the integration of Siamese Neural Networks (SNN) and the Interplanetary File System (IPFS) for decentralized data sharing. The proposed method addresses the challenges of image comparison in scenarios where data privacy, security, and accessibility are paramount concerns. We begin by preprocessing the dataset with techniques like histogram stretching and resizing for consistency. Subsequently, a Siamese Neural Network architecture is employed to compare images efficiently, capturing their inherent similarities and differences. Crucially, after completing all preprocessing, training, and evaluation steps, we upload the dataset to IPFS. This approach guarantees data integrity and enables decentralized access for researchers worldwide. By leveraging IPFS post-processing, we ensure secure, censorship-resistant data sharing without compromising privacy. Experimental results demonstrate the effectiveness and robustness of the proposed approach, achieving high accuracy in image comparison tasks across diverse datasets. Overall, this research contributes to advancing the field of image comparison by combining state-of-the-art neural network techniques with decentralized data sharing mechanisms, opening avenues for secure and collaborative research in image analysis and beyond.