We use nonlinear composite filters in object recognition, even when they have rotation, scale, noise, and illumination distortions. We generated 936 images of the letters E, F, H, P, and B. The images consisted of these letters scaled from 70% to 130% and rotated 360 deg. The maximum number of images supported by these filters was determined by a numerical experiment. Considering a system confidence level of at least 80%, the maximum number of images is around 216. We found a "rotation problem" when the filter contained the letter rotated 360 deg, since circles were artificially introduced, and this creates complications when working with images that also have circles in their spectrum. Due to this, we propose a segmented filter that breaks the circular symmetry. Experiments where carried out in order to find the noise tolerance of each filter, and the use of Spearman's rank correlation (in conjunction with the nonlinear method, SNM) is proposed in order to increase that tolerance. We also made an assessment of the impact that illumination changes had in the correlation output, in the problem image, and we propose the use of SNM to obtain illumination invariance. We tested these filters with two real-life problems; nonlinear composite filters can recognize the target in the presence of distortions.