The persistent cases of corporate accounting scandals which have rocked the Nigerian banking sector in spite of auditor certification of financial statements as free from material error have raised concern not only on the effectiveness of audit committees but also on audit services despite the huge amount charged on their clients. Hence, this study examined the effect of audit committee effectiveness on audit fee of listed deposit money banks in Nigeria. Using an ex-post facto research design, the data sourced through the annual reports of twelve (12) banks for the period between 2012 and 2018 were analysed using random-effect regression analysis. The result of the study revealed that audit committee effectiveness proxy with audit committee audit committee expertise (t-value =3.22 & p-value = 0.000), audit committee diligence (t-value = 3.57, & p-value = 0.000) and audit committee gender diversity (t-value = 3.85 & p-value =0.000) has significant positive effect on audit fee of listed deposit money banks in Nigeria. This implies that an effective audit committee would demand for high audit quality service from the auditor, thereby increasing the audit efforts and time which subsequently result to higher audit fee. The study concluded that an effective audit committee would demand high audit service from the external auditor thereby ensuring that the financial statement published is relevant and of faithful representation.

Face recognition has been an active research area in the pattern recognition and computer vision domains due to its many potential applications in surveillance, credit cards, passport and security. However, the problem of correct method of partitioning the face data into train and test set has always been a challenge to the development of a robust face recognition system. The performance of the System was tested on locally acquired face database when the face database was randomly partitioned and when k-fold Cross Validation partition was used. The face database was captured under the condition of significant variations of rotation, illumination and facial expression. Quantitative evaluation experimental results showed that Random Sampling technique has a higher average recognition rate (96.7%) than Cross Validation partition method (95.3%). However, recognition time in Cross Validation is faster (0.36 secs) than that of Random Sampling (0.38 secs). Keywords: Pattern Recognition, Cross Validation, k-fold, Random Sampling Background to the StudyFace Recognition has being a broad area of research in the recent years. Its applications are continuously gaining demands due its requirements in person authentication, access control and surveillance systems amongst others (Thakur et.al, 2010).Human face cannot be directly used for building automated recognition due to high dimensionality of the face vectors and redundant information contained in the face vectors. The research in face recognition has recently focused on developing a face representation that is capable of capturing the relevant information in a manner which is invariant to facial expression and illumination. If features are inadequately represented, automated face recognition will not be effectively achieved. The classification and subsequent