The quality and safety of medicinal products are related to patients’ lives and health. Therefore, quality inspection takes a key role in the pharmaceutical industry. Most of the previous solutions are based on machine vision, however, their performance is limited by the RGB sensor. The pharmaceutical visual inspection robot combined with hyperspectral imaging technology is becoming a new trend in the high-end medical quality inspection process since the hyperspectral data can provide spectral information with spatial knowledge. Yet, there is no comprehensive review about hyperspectral imaging-based medicinal products inspection. This paper focuses on the pivotal pharmaceutical applications, including counterfeit drugs detection, active component analysis of tables, and quality testing of herbal medicines and other medical materials. We discuss the technology and hardware of Raman spectroscopy and hyperspectral imaging, firstly. Furthermore, we review these technologies in pharmaceutical scenarios. Finally, the development tendency and prospect of hyperspectral imaging technology-based robots in the field of pharmaceutical quality inspection is summarized.

Chinese herbal oral liquid can leach a variety of effective ingredients from herbs and has become a major drug for clinical application. However, it is easy to produce or introduce foreign matters that are very faint in the automatic filling production process. To solve the challenge of low accuracy of faint foreign matter detection, in this paper, we proposed a salient-based anomaly detection method which is fuses visual saliency with dual-spectral saliency (VDS) for the hyperspectral herbal oral liquid. Specifically, we first select the most discriminative bands via the band selection method to generate the pseudo-color map. Subsequently, the histogram-based contrast method is introduced to select the saliency feature map with the largest variance of color features, while fusing the multi-scale gradient features to obtain the preliminary vision-based anomaly detection map. After that, the spectral angles and spectral Euclidean distances are calculated separately based on the oral liquid hyperspectral images to fused into dual-spectral saliency maps. Finally, the dual-spectral saliency map is employed to suppress the background information of the preliminary anomaly detection map. The experimental results show that our proposed method outperforms the state-of-the-art anomaly detection methods, which accurately and quickly achieve the detection of faint foreign matter in the hyperspectral herbal oral liquid. It will accelerate the process of automated filling production lines for oral liquid in the pharmaceutical industry.

No abstract

Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.