A system for invariant face recognition is presented. A combined classifier uses the generalization capabilities of learning vector quantization (LVQ) neural networks to build a representative model of a face from a variety of training patterns with different poses, details, and facial expressions. The combined generalization error of the classifier is found to be lower than that of each individual classifier. The system is tested on an in-house built database and is capable of recognizing a face in about 1 second. The system performance compares favorably with the state-of-the-art systems. While the recognition rates of the individual classifiers ranged from 94% to 96%, a correct recognition rate of 100% is achieved by the combined classifier at 0% rejection.