The State of Health (SOH) of lithium-ion batteries is a crucial aspect of battery management system, playing a significant role in ensuring the reliable operation of the battery. To improve the accuracy of SOH estimation for lithium-ion batteries, a SOH estimation method based on Bayesian Optimization-Support Vector Regression (BO-SVR) is proposed. Firstly, the voltage information during the relaxation phase of each cycle process is transformed into five health indicators to characterize the capacity degradation. Pearson coefficient analysis is then utilized to assess the correlation between these health indicators and battery capacity under various cycling conditions, filtering out the health indicators highly correlated with battery capacity degradation as SOH features. Subsequently, Bayesian optimization is introduced to optimize the hyperparameters of SVR model. Finally, the Bayesian Optimization-eXtreme Gradient Boosting (BO-XGBoost) model is served as a comparison model to validate the accuracy of the proposed model using a public dataset.