The presented study aims to estimate blood pressure (BP) using photoplethysmogram (PPG) signals while employing multiple machine learning models. The study proposes a novel algorithm for signal reconstruction, which utilizes the semi-classical signal analysis (SCSA) technique. The proposed algorithm optimises the semi-classical constant and eliminates the trade-off between complexity and accuracy in reconstruction. The reconstructed signals' spectral features are extracted and incorporated with clinically relevant PPG and its second derivative's (SDPPG) morphological features. The developed method was assessed using a publicly available virtual in-silico dataset with more than 4000 subjects, and the Multi-Parameter Intelligent Monitoring in Intensive Care Units dataset. Results showed that the method attained a mean absolute error of 5.37 and 2.96 mmHg for systolic and diastolic BP, respectively, using the CatBoost supervisory algorithm. This approach met the standards set by the Advancement of Medical Instrumentation, and achieved Grade A for all BP categories in the British Hypertension Society protocol. The proposed framework performs well even when applied to a combined database of the MIMIC-III and the Queensland dataset. This study also evaluates the proposed method's performance in a non-clinical setting with noisy and deformed PPG signals, to validate the efficacy of the SCSA method. The noise stress tests showed that the algorithm maintained its key feature detection, signal reconstruction capability, and estimation accuracy up to a 10 dB SNR ratio. It is believed that the proposed cuff-less BP estimation technique has the potential to perform well on resource-constrained settings due to its straightforward implementation approach.