旋转不变二值化联合变换相关识别方法

Method of synthetic discriminant function based rotational invariant binary joint transform correlation recognition

介绍一种基于二值化联合变换相关的综合鉴别函数算法,用等相关峰及Gram-schmidt展开获得的综合鉴别函数对迭代算法进一步优化,获得了适用于二值化联合变换相关的综合鉴别函数。采用这种算法制作的综合鉴别滤波器既有相关峰值高和相关峰尖锐等特点,又能识别旋转图像。计算机模拟结果表明:这种相关器在信噪比、光能效率、相关峰尖锐度和鉴别能力上都有一定程度地提高,实现了较高鉴别率旋转不变光学模式识别。

The synthetic discriminant function （SDF） algorithm based on binary joint transform correlation is introduced. The iterative algorithm was further optimized with SDF obtained by the equally related peaks and the Gram-Schmidt expansion to acquire the SDF suitable for binary joint transform correlator. The synthetic discriminant filter made up of the algorithm has the advantages of high relevant peak value, sharp relevant peak, and can recognize the rotating images. The computer simulation shows that the signal-to-noise ratio, light efficiency, relevant peak sharpness and recognition ability of this correlator are increased, and the rotational invariant optical mode recognition with high recognizability is realized.