Academic dishonesty has been a growing concern in e-learning environment due to the fact that e-examination takes place under supervised and unsupervised learning environment despite its huge advantages. The e-examination environment has faced various security breaches such as academic dishonesty (impersonation), identity theft, unauthorised access and illegal assistance as a result of inefficient measures employed. Hence, an efficient framework which will aid the monitoring of the e-examination is needed. This paper reviews the process of mining multimedia data and propose a framework for monitoring the e-examination environment in order to extract images and audio features. The framework has four major phases: data pre-processing, mining, association and post processing. The pre-processing phases carries out the extraction and transformation of multimedia data features, the mining phase does the classification and clustering of these features, the association does pattern matching while the post processing carries out the knowledge interpretation and reporting. The approach presented in this study will allow for efficient and accurate monitoring of e-examination environment which will help provide adequate security and reduce unethical behaviour in e-examination environment.