摘要
提出一种基于光学小波联合变换相关器的图像识别系统。该系统对光学图像具有较高的识别力,并可实现图像的尺度和旋转不变识别。首先应用对数极坐标-梅林变换对参考图像和待测图像进行预处理,然后同时置于光学联合变换相关器的输入面上,在空间频谱面上通过小波滤波实现图像的光学小波变换,最后在输出面上得到二者的互相关峰。Matlab仿真结果表明,该系统同时排除了因图像尺度变化和旋转造成的干扰,并得到很好的峰噪比和识别力.
An image recognition system based on optical wavelet joint-transform correlatorwas presented to recognize the scale and rotation of the optical image with a high discernment. The referenceand target ima- ges were preprocessed by using Logpolar-Mellin Transform before being placed on the input plane of joint- transform correlator at the same time. The optical wavelet transform of the image was realized by the wave- let filter on the spatial frequency spectrum plane. Finally the systemreaehedits cross-correlation peak on the output plane. Matlab simulation results showed that the system can eliminate the interference caused by the scaling and rotation of the target image simultaneously,providing good effectiveness for PNR and ACR.
出处
《南昌大学学报(理科版)》
CAS
北大核心
2016年第5期431-435,共5页
Journal of Nanchang University(Natural Science)
基金
福建省自然科学基金资助项目(2012J01280)