Background: Pulse waveform morphology changes with age, reflecting underlying vascular and haemodynamic alterations. Vascular age is thus a key indicator of cardiovascular health. Detecting premature ageing could serve as an early warning sign for increased disease risk. Aim: We explored whether age-related morphological changes in pulse waves can be captured using image-based representations in a population free from cardiovascular risk factors, where chronological and vascular age are expected to align. Methods: Images were generated from 20-second segments of pulse wave data using a selected subset of the Asklepios dataset (arterial tonometry recordings from 2,524 participants aged 30-59) and the full Vortal dataset [photoplethysmography (PPG) recordings from 56 participants, aged 18-35 and 70+]. The Symmetric Projection Attractor Reconstruction (SPAR) technique was used to transform time-series signals into images that amplify morphology and variability changes. These images were used to train a simple convolutional neural network for binary age classification, distinguishing between individuals aged 35–40 and 50–55; a narrow but clinically relevant range. The model was trained on 80% of the selected Asklepios data, with 10-fold cross-validation to improve robustness. Generalizability was then evaluated using broader age groups from Asklepios and the full Vortal dataset. Results: The model achieved consistent classification performance, with F1 scores exceeding 70% and specificity above 79% across all internal and external test sets. It also demonstrated robust generalizability across PPG and tonometry signals. Conclusion: SPAR provides a visually intuitive method for amplifying pulse morphology differences, supporting age classification in individuals free from cardiovascular risk factors. These results suggest that SPAR images capture discriminative features of vascular ageing, even among healthy adults close in chronological age. This proof-of-concept lays the groundwork for future research into the use of SPAR for early risk detection using smart wearables.