As an important export, cleanliness control on edible bird’s nest (EBN) is paramount. Automatic impurities detection is in urgent need to replace manual practices. However, effective impurities detection algorithm is yet to be developed due to the unresolved inhomogeneous optical properties of EBN. The objective of this work is to develop a novel U-net based algorithm for accurate impurities detection. The algorithm leveraged the convolution mechanisms of U-net for precise and localized features extraction. Output probability tensors were then generated from the deconvolution layers for impurities detection and positioning. The U-net based algorithm outperformed previous image processing-based methods with a higher impurities detection rate of 96.69% and a lower misclassification rate of 10.08%. The applicability of the algorithm was further confirmed with a reasonably high dice coefficient of more than 0.8. In conclusion, the developed U-net based algorithm successfully mitigated intensity inhomogeneity in EBN and improved the impurities detection rate.
There is a dire need for vision automation for edible bird's nest (EBN) hygiene inspection. To date, an effective impurities detection method for EBNs has yet to be realized owing to the inhomogeneous optical properties, various types and sizes of impurities, and limited sample size. The impurities inspection was formulated as an anomaly detection task, and a hybrid autoencoder model that contains an autoencoder and a single layer convolutional network is proposed. The model was trained to reconstruct only nonimpurity regions of the EBN for impurities segmentation and detection as anomalies. The results showed that with only 50 EBN sample images, the hybrid model achieved a recall of 0.9282, a precision of 0.7718, and a 5.63% undetected rate for impurities. Furthermore, a misclassification rate of 21.53% was recorded due to artifacts mostly with sizes <0.20 mm that were detected as false positive. Nonetheless, the applicability of the proposed autoencoder model was confirmed, with >92% of successful impurities detected. Therefore, the hybrid autoencoder model is further explored for improvement and practical application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.