Retinal recognition by using compression-based joint transform correlator (JTC) is proposed. Recognition performance is quantitatively measured by taking into account effect of imbalanced illuminations and noise presence. The simulation results show that the compression-based JTC has reliable recognition performance for high-contrast retina target. Besides acceleration of image transfer time, the compression of the noise-corrupted retina target images can improve the correlator robustness to noise.
A novel method for retinal blood vessel detection by using a wavelet-matched filter is proposed to improve the detection performance. Vessel references are generated by using dual Gaussian functions with different widths, separations, and orientations, while a Mexican hat wavelet is used for feature enhancements. The results show that the proposed method has advantages over the conventional matched filter in that the vessels can be easily distinguished from the fluctuating background without the need of a thresholding process, and vessel images can be precisely reconstructed.
Retina recognition by using joint transform correlator (JTC) with JPEG-compressed target and reference images is proposed. Recognition performance is studied by using retina images with different contrasts employed as test scenes. The simulation results show that regardless of the reference contrast, the compression-based JTC offers better recognition performance for a high-contrast target. The compression of target images has advantages in that recognition degradation caused by noise can be reduced and image transfer time delay can be accelerated.
A real-time implementation of a joint transform correlator by using JPEG-compressed reference images is proposed in order to solve storage problems and improve the time response of automatic target recognition systems. The correlation performance is studied quantitatively by using two types of images with different spatial-frequency contents. The simulation results show that in comparison with the compressed high-spatial-frequency images, the joint transform correlator using the compressed low-spatial-frequency reference image offers better recognition performance in that it is robust to noise and contrast difference for a wide range of compression levels.