SingTown Technology's AI vision automatically identifies nuts, enabling roasting machines to precisely control the temperature.

In intelligent roasting equipment, different materials (such as peanuts, sunflower seeds, chestnuts, etc.) require matching with distinct heating curves and stirring strategies. Manual configuration is not only time-consuming but also prone to errors. To achieve automation and precise control of the roasting process, roasting robot manufacturers plan 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 primary recognition targets are nut-based foods with particle sizes ranging from 1 to 5 centimeters. Installed above the equipment, the camera can capture the contents of the hopper within an adjustable distance. The system must be capable of distinguishing 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 loading and intelligent frying matching, thereby enhancing the equipment's intelligence level and user experience.

The manufacturer of stir-frying robots utilises SingTown Technology's OpenMV intelligent camera-based material recognition system, integrating AI image recognition, colour 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 employs colour space conversion (RGB-HSV) and morphological feature extraction algorithms to analyse and classify the colour, texture, and shape characteristics of raw materials such as peanuts, sunflower seeds, and chestnuts. By training sample models, the system can swiftly determine the type of material in the current bin, output corresponding identification signals, and automatically match the robotic frying programme.

During the detection process, the OpenMV embedded vision module automatically adjusts exposure and white balance according to varying lighting conditions to maintain stable and accurate recognition performance. Even if the material position in the hopper deviates or materials are stacked, the system can accurately identify them through region segmentation and multi-feature fusion algorithms (colour + texture + contour shape). The recognition results are transmitted to the main control microcontroller via serial port or bus, enabling automatic parameter switching.

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

SingTown 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.