SingTown Technology's AI vision automatically identifies nuts, allowing roasting machines to perfectly control the heat.

In intelligent roasting equipment, different materials (such as peanuts, melon seeds, chestnuts, etc.) require matching with distinct heating curves and stirring strategies. Manual setup is not only time-consuming but also prone to errors. To achieve automation and precise control of the roasting process, the roasting robot manufacturer plans to adopt SingTown Technology's OpenMV intelligent camera to build a machine vision-based material recognition system.

The system captures images of raw materials inside the hopper via a camera, automatically identifies the type of food currently placed, and then calls the corresponding frying program. The identification targets are mainly nut-based foods with particle sizes of 1–5 cm, installed above the equipment, capable of capturing hopper contents within an adjustable distance. The system must distinguish between different varieties such as peanuts, sunflower seeds, and chestnuts, maintaining stable recognition even with minor positional deviations or angle variations. The goal is to enable the robot to automatically identify material types, achieve unmanned feeding and intelligent frying matching, and enhance the equipment's intelligence level and user experience.

The manufacturer of stir-frying robots utilizes SingTown Technology's OpenMV intelligent camera-based material recognition system, integrating AI image recognition, color texture analysis, and machine learning classification algorithms to automatically identify material types in real-time.

The system captures images of the material bin using high-resolution cameras and analyzes and classifies the color, texture, and shape characteristics of raw materials such as peanuts, sunflower seeds, and chestnuts through color space conversion (RGB-HSV) and morphological feature extraction algorithms. By training sample models, the system can quickly determine the type of material in the current bin, output corresponding identification signals, and automatically match the robot frying program.

During the detection process, the OpenMV embedded vision module can automatically adjust exposure and white balance according to different lighting conditions to maintain stable and accurate recognition work. Even if there is deviation or stacking of material positions in the material bin, the system can accurately identify them through region segmentation and multi-feature fusion algorithms (color + texture + contour shape). The recognition results are sent to the main control microcontroller via serial port or bus to achieve automatic parameter switching.

Actual test data shows that the system achieves an identification accuracy rate of over 95% for three common roasted snack ingredients (peanuts, melon seeds, chestnuts) under standard lighting conditions, with a response time below 0.5 seconds.

SingTown Technology's OpenMV smart camera features low cost, easy deployment, and strong anti-interference capability. It is suitable for edge deployment in various equipment such as roasting machines, nut packaging machines, and food sorting systems, supporting the intelligent upgrade of the food automation processing industry.