SingTown Technology's AI vision automatically identifies nuts, allowing 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, 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 the raw materials inside the hopper via a camera, automatically identifies the type of food currently loaded, and then calls the corresponding frying programme. The identification targets are primarily nut-based foods with a particle size of 1–5 centimetres, and the installation position is above the equipment, allowing it to capture the contents of the hopper within an adjustable distance. The system must be able to distinguish between different varieties such as peanuts, sunflower seeds, and chestnuts, maintaining stable identification even with minor positional deviations or angle variations. The goal is to enable the robot to automatically identify the type of material, achieve unmanned loading and intelligent frying matching, and enhance the equipment's level of intelligence and user experience.

The manufacturer of stir-frying robots utilises SingTown Technology's OpenMV intelligent camera-based material recognition system, which integrates 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 currently in the bin, output the corresponding identification signal, and automatically match the robot frying programme.

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. Even if there is deviation or stacking of material positions in the hopper, the system can accurately identify them through region segmentation and multi-feature fusion algorithms (colour + texture + contour shape). The recognition results are sent to the main control microcontroller via serial port or bus to achieve automatic parameter switching.

Measured data indicates that the system achieves an identification accuracy rate exceeding 95% for three common roasted snack ingredients (peanuts, sunflower seeds, chestnuts) under standard lighting conditions, with a response time under 0.5 seconds.

SingTown OpenMV intelligent 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, assisting the food automation processing industry in upgrading towards intelligence.