Plant leaf classification is a core task in biodiversity monitoring, ecological studies, and smart agriculture. In prac-tice, it often still depends on field identification by botanists, which can be slow, laborious, and limited by the availabil-ity of skilled personnel. To address these issues, we present Leaf-StarNet, a compact convolutional neural network tai-lored for accurate and efficient leaf recognition. The network combines three complementary components: an LS-Conv module for localized and efficient feature extraction, an scSE attention block to refine both spatial and channel infor-mation, and a Frequency-Based Enhancement (FBE) unit to better capture subtle frequency-domain patterns. We evalu-ate the model on the LeafSnap dataset and achieve an accuracy of 96.83%, surpassing lightweight baselines such as MobileNetV2, GhostNetV3, and FasterNet-T1. Ablation experiments confirm the contribution of each module, while Grad-CAM visualizations illustrate how the network’s focus shifts from fine textures in early layers to higher-level se-mantic regions in deeper layers. With its small footprint and low computational demand, Leaf-StarNet is well suited for deployment on mobile or embedded platforms, providing a practical and reliable solution for automated plant leaf clas-sification.