Few-Shot Detection of Surface Roughness of Workpieces Processed by Different Machining Techniques

The traditional deep learning method for detecting workpiece surface roughness relies heavily on a large number of training samples. Also, when detecting the surface roughness of workpieces processed by different machining techniques, it requires a large number of samples of that workpiece to rebuild the model. To address these problems, this paper proposes a few-sample visual detection method for the surface roughness of workpieces processed by different techniques. This method first trains a base model using a relatively large amount of samples from one machining technique, then fine-tunes the model using small amounts of samples from workpieces of different techniques. By introducing contrastive proposal encoding into Faster R-CNN, the model's ability to learn surface features from small amounts of workpiece samples is enhanced, thus improving the detection accuracy of surface roughness of workpieces processed by different techniques. Experiments show that this method reduces the model's dependence on training samples and the cost of data preparation. It also demonstrates higher accuracy in surface roughness detection tasks of workpieces processed by different techniques, providing a new approach and insights for few-sample surface roughness detection.