We present a new technique for Chinese seal recognition using constrained energy minimization joint transform correlator (CEMJTC). Either optical or digital correlation is one of the most powerful operations for detecting the presence/absence of the seal image. The CEMJTC is proposed to improve the discrimination capability for shift-invariance and rotational-invariant seal recognition. By minimizing the average correlation energy with respect to all training seal images, while constraining the correlation peak value to a constant, a filter function is constructed. The main emphasis is to design a filter for good discriminate ability. Numerical results are presented to demonstrate the improvements. Furthermore, experimental results show the sharp correlation output profile when the seal image is correct, otherwise the correlation peak will be obviously reduced. The new technique for seal recognition shows a significant increase in high speed and detection ability.