Chinese Herbal Medicine Recognition Method Based on Composite Image Dataset and Deep Learning

OBJECTIVE  To design an automatic composition method for Chinese herbal medicine images and a deep learning model, achieving automatic recognition of Chinese herbal medicine.

METHODS Image processing techniques were employed to segment individual Chinese herbal slice samples and then randomly selected sample images of multiple types were synthesized to generate a training dataset. Contrastive learning was combined with YOLOv5 model to enable the backbone to extract more effective features for variety recognition of Chinese herbal medicine.

RESULTS  Experiment on composite and real images showed that the average recognition rate >95% and the average processing time per image was about 28 ms. The accuracy of bounding boxes and the recognition rate of similar types had been effectively improved.

CONCLUSION  The deep learning model trained on the synthesized image dataset can effectively identify a variety of Chinese herbal medicine and can be extended to broader applications in Chinese herbal medicine recognition.