In this study, an internal fingerprint-guided epidermal thickness of fingertip skin is proposed for optical image encryption based on optical coherence tomography (OCT) combined with U-Net architecture of a convolutional neural network (CNN). The epidermal thickness of fingertip skin is calculated by the distance between the upper and lower boundaries of the epidermal layer in cross-sectional optical coherence tomography (OCT) images, which is segmented using CNN, and the internal fingerprint at the epidermis-dermis junction (DEJ) is extracted based on the maximum intensity projection (MIP) algorithm. The experimental results indicate that the internal fingerprint-guided epidermal thickness is insensitive to pressure due to normal correlation coefficients and the encryption process between epidermal thickness maps of fingertip skin under different pressures. In addition, the result of the numerical simulation demonstrates the feasibility and security of the encryption scheme by structural similarity index matrix (SSIM) analysis between the original image and the recovered image with the correct and error keys decryption, respectively. The robustness is analyzed based on the SSIM value in three aspects: different pressures, noise attacks, and data loss. Key randomness is valid by the gray histograms, and the average correlation coefficients of adjacent pixelated values in three directions and the average entropy were calculated. This study suggests that the epidermal thickness of fingertip skin could be seen as important biometric information for information encryption.