Abstract: Algae cell detection is of great significance for ecosystem monitoring, and currently algal cell detection still relies on manual identification, which is not only time-consuming and labor-intensive, but also incurs substantial costs. In this study, computer-aided detection is combined with a Transformer-based target detection model for microalgae cell detection task. To address the issue of blurred features in microalgae cell, we design a feature-enhanced convolutional module that combines Receptive Field Attention (RFA) and Coordinate Attention (CA). Experiments are conducted using three different backbones, namely, ResNet50, ResNet34, and ResNet18. The results show that the improved model obtains the highest accuracy of 87.6%, 73.3%, 85.7%, 95.2%, 97.7% and 99.0% for six microalgae: Platymonas, Chlorella, Dunaliella, Effrenium, Porphyridium, and Haematococcus in Kaggle’s publicly available microalgae image dataset, respectively. These results demonstrate the feasibility and scientific validity of the Transformer model in the field of microalgae target detection, providing new ideas and methods for the application of artificial intelligence in ecological research and microalgae detection.