A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies

Liu, Gaokai; Yang, Ning; Guo, Shiping; Chen, Zhi

doi:10.3390/s20071829

Cited by 16 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the lipsticks were checked for marks (representing scratches or dents on the surface), heterogeneity (color or texture differences), pollutants (dust or other undesirable particles), and distortion (irregular line, deformation, etc.). The surface of the product should be completely devoid of crystal formation with no signs of contamination from the molds and fungi [32,33].…”

Section: Surface Anomaliesmentioning

confidence: 99%

In vitro characterization of self-emulsifying drug delivery system-based lipsticks loaded with ketoconazole

2023

View full text Add to dashboard Cite

Background Self-emulsifying system-based lipstick may prove to have the potential of enhancing moisturizing characteristics and delivering hydrophobic drug antifungal drugs for the management of lip fungal infection, especially candidiasis. In this study, the self-emulsifying drug delivery system (SEDDs) of ketoconazole was obtained using IPM (Oil), Tween 80 (surfactant), and PEG 400 (co-surfactant). The medicinal lipstick was developed from the SEDDs, and the concentration of waxes (beeswax and carnauba wax) and cow ghee (penetration enhancer) was optimized using a Box–Behnken design. The lipstick formulations were assessed based on physicochemical features, such as pH, spreadability, softening point, breaking point, content uniformity, and in vitro drug permeation. Furthermore, the optimal lipstick formulation was tested for stability and antifungal activity. Results The optimized formulation showed exceptional results in physicochemical analysis and ~ 87% release of the drug in 12 h. The formulations displayed adequate stability for 4 weeks at various temperature conditions such as room temperature, 40 °C, and 45 °C. The zone of inhibition produced by lipstick formulation was significantly higher as compared to the reference standard (ketoconazole in ethanol) which shows high antifungal activity. Conclusion It was concluded from the outcomes that SEDDs-based lipstick formulation showed a lot of promise as a topical antifungal treatment option for Candidiasis. Graphical abstract

show abstract

Section: Surface Anomaliesmentioning

confidence: 99%

In vitro characterization of self-emulsifying drug delivery system-based lipsticks loaded with ketoconazole

2023

View full text Add to dashboard Cite

show abstract

“…A surface anomalies inspection is important for product quality control and to meet the customers' expectations [122]. The visual inspection method was used to assess all anomalies which can occur on the surface of lipstick [14,29,51,86,123].…”

Section: Surface Anomaliesmentioning

confidence: 99%

Lipsticks History, Formulations, and Production: A Narrative Review

et al. 2022

View full text Add to dashboard Cite

A considerable amount of literature has been published on several aspects of lipsticks production. To date, there is no collation of studies related to lipsticks production that has been published. This review was conducted to examine information about the history of lipsticks; ingredients used in the preparation of lipsticks, focusing on the natural and chemical ingredients; methods of preparation for the lipsticks; and the characterization of the lipsticks. A literature search for English language articles was conducted by searching electronic databases including Web of Science, Scopus, PubMed, and Google Scholar. Overall, the evidence indicates that lipsticks have been used since ancient times and are among the highest demand cosmetics. The findings of this review summarize those of earlier studies that explained the use of different types of ingredients in the manufacturing processes of lipsticks. It highlights the importance of using green technology and ingredients to fabricate lipsticks to avoid potential side effects such as skin irritation and allergy reaction.

show abstract

“…Also on industrially relevant visual inspection data, DL models based on convolutional neural networks has shown close to zero false positives and false negatives. [3][4][5][6] However, supervisedly trained models typically require large quantities of correctly annotated data, for all classes if should discern; and they are known to be often overconfident in their results when subjected to data far from the training data distribution, OOD data. See for example 7 for an illustrative example of this for the application of industrial X-ray-based image data analysis within NDE.…”

Section: Introductionmentioning

confidence: 99%

Deep-learning-based out-of-distribution data detection in visual inspection images

Lindgren

Zach

2023

NDE 4.0, Predictive Maintenance, Communication, and Energy Systems: The Digital Transformation of NDE

View full text Add to dashboard Cite

Within quality critical industries, e.g. aerospace, quality control with non-destructive evaluation (NDE) is essential. The surface quality is often important and e.g. visual inspection is often applied. Part of the inspection is the data interpretation, not easily made automatic for critical products. Recent studies on the automatization have indicated promising results utilizing deep-learning-based artificial intelligence. However, many such algorithms are known to be overconfident when subjected to unexpected input (e.g. new/rare material defects) far from the training dataset, so-called out-of-distribution (OOD) data. We claim that safe computer-based interpretation of NDE data within quality critical applications, must respond sensible also to OOD data. A sensible response could be that the algorithms identify such OOD data and forward it to a human for further analysis. Such an OOD detector could facilitate a human-machine collaboration in a NDE 4.0 vision. In this work we have explored if a recently proposed (for industrial x-ray images) auto-encoder-based approach can be utilized as OOD detector (one-class classifier) for visual inspection data. The model is trained in an unsupervised manner on accepted input to reconstruct it at high precision. Simultaneously it is trained to remove synthetically added defect indications to generate a clean image patch, similar to denoising-auto-enoders. The difference between the input and reconstructed input is analyzed for OOD detection. We train and test the algorithm on a publicly available visual inspection dataset with surface defects. We achieve true positive rates at 0.90 with true negative rates at 0.99 and demonstrate detection of OOD data.

show abstract

A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies

Cited by 16 publications

References 25 publications

In vitro characterization of self-emulsifying drug delivery system-based lipsticks loaded with ketoconazole

In vitro characterization of self-emulsifying drug delivery system-based lipsticks loaded with ketoconazole

Lipsticks History, Formulations, and Production: A Narrative Review

Deep-learning-based out-of-distribution data detection in visual inspection images

Contact Info

Product

Resources

About