Determining the harvesting period can be done visually, physically, computationally, and chemically. Since the harvesting process is crucial, late harvesting will affect post-harvest and production quality. Leafy vegetables have a relatively short ready-to-harvest period. Visual recognition of the harvesting period combined with image processing can recognize harvesting vegetables' visual characteristics. This study aims to build a deep learning-based mobile model to detect real-time vegetable plant objects such as bok choy, spinach, kale, and curly kale to determine whether these vegetables are ready for harvest. Mobile-based architecture is chosen due to latency, privacy, connectivity, and power consumption reason since there is no round-trip communication to the server. In this research, we use MobileNetV3 as the base architecture. To find the best model, we experiment using different image input size. We have obtained a maximum MAP score of 0. 705510 using a 36,000 image dataset. Furthermore, after implementing the model into the Android mobile application, we analyze the best practice in using the application to capture distance. In real-time detection usage, the detection can be done with an ideal distance of 5 cm and 10 cm.