Multimodal biometric systems have been widely used in various applications due to its ability to deal with a number of limitations of unimodal biometric systems, such as noise, non-univarsality, sensitivity and lack of invariant representations. The multimodal fusion allows to improve the results obtained by a single biometric characteristic and make the system more robust to noise and interference and more resistant to possible attacks. In many areas where personal identification is important, security is of great importance. Biometric or multi-biometric systems, which include the physiological and behavioral features of individuals, are more preferred because traditional methods are insufficient and cannot provide security. In the study, a new approach of multimodal biometric identification is proposed consisting of the Fingerprint and finger knuckle print (FKP). A hybrid feature extraction technique is utilized along with the gray level co-occurrence matrix (GLCM) and wavelet moments. Extracted features are classified by Random Forest classifier to obtain the simulation results in terms of precision, sensitivity, accuracy, specificity and F-Score.