In this paper, we used a convolutional neural network to study the classification of marine microalgae by using low-resolution Mueller matrix images. Mueller matrix images of 12 species of algae from 5 families were measured by a Mueller matrix microscopy with an LED light source at 514 nm wavelength. The data sets of seven resolution levels were generated by the bicubic interpolation algorithm. We conducted two groups of classification experiments; one group classified the algae into 12 classes according to species category, and the other group classified the algae into 5 classes according to family category. In each group of classification experiments, we compared the classification results of the Mueller matrix images with those of the first element (M11) images. The classification accuracy of Mueller matrix images declines gently with the decrease of image resolution, while the accuracy of M11 images declines sharply. The classification accuracy of Mueller matrix images is higher than that of M11 images at each resolution level. At the lowest resolution level, the accuracy of 12-class classification and 5-class classification of full Mueller matrix images is 29.89% and 35.83% higher than those of M11 images, respectively. In addition, we also found that the polarization information of different species had different contributions to the classification. These results show that the polarization information can greatly improve the classification accuracy of low-resolution microalgal images.