Deep Learning Applications in Thermal IR Image Processing
Lecture Notes in Networks and Systems, ISSN: 2367-3389, Vol: 786, Page: 115-123
2024
- 1Captures
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Metrics Details
- Captures1
- Readers1
Conference Paper Description
IR image recognition has been a promising field for the past few years. However, it is difficult to identify facial emotions when it is dark, the lighting is poor, or there are other elements present. Thermal pictures are therefore recommended as a fix for these issues and for a number of additional advantages. Additionally, focusing on important areas of a face rather than the complete face is sufficient to reduce processing while also enhancing accuracy. This study provides brand-new infrared thermal image-based methods for identifying the images. The face’s whole image is first divided into four parts. Then, to create training and testing datasets, we only allowed four active regions (ARs). An approach to machine learning is called active neural network (ANN). We also used a parallelism strategy to speed up processing of training and testing datasets. We have observed a 46% reduction in processing time as a result. Finally, to increase the recognition accomplishes a recognition accuracy of 92.38%. The achieved accuracy validates the stability of our suggested strategy.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85181983905&origin=inward; http://dx.doi.org/10.1007/978-981-99-6547-2_10; https://link.springer.com/10.1007/978-981-99-6547-2_10; https://dx.doi.org/10.1007/978-981-99-6547-2_10; https://link.springer.com/chapter/10.1007/978-981-99-6547-2_10
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know