This paper presents an advanced method for recognizing corn leaf spot disease using an improved version of the YOLOv8 model. Corn leaf spot disease is a significant issue in Northern China, causing substantial economic losses. Traditional methods are prone to subjective interference and cannot accurately identify the disease in complex field environments. The proposed method leverages actual field images of diseased corn leaves to construct a dataset and accurately labels the diseased leaves, enabling rapid and accurate identification. The improved YOLOv8 model incorporates Slim-neck modules and GAM attention modules to enhance its performance. The Slim-neck module reduces computational complexity, while the GAM attention module improves the model's ability to focus on relevant areas, enhancing overall recognition accuracy. The enhanced model achieved a precision of 95.18%, a recall of 89.11%, an average recognition accuracy (mAP50) of 94.65%, and an mAP50-95 of 71.62%, outperforming the original YOLOv8 model by 3.79%, 4.65%, 3.56%, and 7.3%, respectively. The model was also compared with other popular models such as YOLOv3, YOLOv5, YOLOv6, Faster R-CNN, and SSD, demonstrating superior performance in terms of accuracy and computational efficiency. The enhanced method effectively identifies and localizes corn leaf spot disease in complex field environments, offering robust support for agricultural production.This paper presents an advanced method for recognizing corn leaf spot disease using an improved version of the YOLOv8 model. Corn leaf spot disease is a significant issue in Northern China, causing substantial economic losses. Traditional methods are prone to subjective interference and cannot accurately identify the disease in complex field environments. The proposed method leverages actual field images of diseased corn leaves to construct a dataset and accurately labels the diseased leaves, enabling rapid and accurate identification. The improved YOLOv8 model incorporates Slim-neck modules and GAM attention modules to enhance its performance. The Slim-neck module reduces computational complexity, while the GAM attention module improves the model's ability to focus on relevant areas, enhancing overall recognition accuracy. The enhanced model achieved a precision of 95.18%, a recall of 89.11%, an average recognition accuracy (mAP50) of 94.65%, and an mAP50-95 of 71.62%, outperforming the original YOLOv8 model by 3.79%, 4.65%, 3.56%, and 7.3%, respectively. The model was also compared with other popular models such as YOLOv3, YOLOv5, YOLOv6, Faster R-CNN, and SSD, demonstrating superior performance in terms of accuracy and computational efficiency. The enhanced method effectively identifies and localizes corn leaf spot disease in complex field environments, offering robust support for agricultural production.