The performance of handwritten numeral string recognition integrating segmentation and classification relies on the classification accuracy and the resistance to non-characters of the underlying classifier. The classifier can be trained at either character level (with character and non-character samples) or string level (with string samples). We show that both character-level and string-level training yield superior string recognition performance. String-level training improves segmentation but deteriorates classification. By combining the character-level trained classifier and the string-level trained classifier, we have achieved higher string recognition performance. We show the experimental results of three classifier structures on the numeral strings of NIST Special Database 19.