This dataset contains raw images of sugar cane stems and leaves captured directly from the camera, as part of the doctoral project 'Study of the Feasibility of Using Computer Vision for the Identification of Sugarcane Varieties.' The dataset is organized into three compressed files, each representing a specific variety and age of cutting. Inside these files are JPEG images, approximately 18 megapixels in size, portraying individual samples. It's important to note that these images are unprocessed, directly sourced from the camera. Further elaboration on the experimental conditions is provided in an attached document (.pdf).