A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps
In recent years, Generative Adversarial Networks (GANs)-based illumination processing of facial images has made favorable achievements. However, some GANs-based illumination-processing methods only pay attention to the image quality and neglect the recognition accuracy, whereas others only crop part...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4869 |
| _version_ | 1797555233437515776 |
|---|---|
| author | Shenggui Ling Ye Lin Keren Fu Di You Peng Cheng |
| author_facet | Shenggui Ling Ye Lin Keren Fu Di You Peng Cheng |
| author_sort | Shenggui Ling |
| collection | DOAJ |
| description | In recent years, Generative Adversarial Networks (GANs)-based illumination processing of facial images has made favorable achievements. However, some GANs-based illumination-processing methods only pay attention to the image quality and neglect the recognition accuracy, whereas others only crop partial face area and ignore the challenges to synthesize photographic face, background and hair when the original face image is under extreme illumination (Image under extreme illumination (extreme illumination conditions) means that we cannot see the texture and structure information clearly and most pixel values tend to 0 or 255.). Moreover, the recognition accuracy is low when the faces are under extreme illumination conditions. For these reasons, we present an elaborately designed architecture based on convolutional neural network and GANs for processing the illumination of facial image. We use ResBlock at the down-sampling stage in our encoder and adopt skip connections in our generator. This special design together with our loss can enhance the ability to preserve identity and generate high-quality images. Moreover, we use different convolutional layers of a pre-trained feature network to extract varisized feature maps, and then use these feature maps to compute loss, which is named multi-stage feature maps (MSFM) loss. For the sake of fairly evaluating our method against state-of-the-art models, we use four metrics to estimate the performance of illumination-processing algorithms. A variety of experimental data indicate that our method is superior to the previous models under various illumination challenges in illumination processing. We conduct qualitative and quantitative experiments on two datasets, and the experimental data indicate that our scheme obviously surpasses the state-of-the-art algorithms in image quality and identification accuracy. |
| first_indexed | 2024-03-10T16:44:31Z |
| format | Article |
| id | doaj.art-0c686418ed164ece8db6152898ab95e9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:44:31Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0c686418ed164ece8db6152898ab95e92023-11-20T11:42:17ZengMDPI AGSensors1424-82202020-08-012017486910.3390/s20174869A High-Performance Face Illumination Processing Method via Multi-Stage Feature MapsShenggui Ling0Ye Lin1Keren Fu2Di You3Peng Cheng4National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaCollege of Computer Science, Sichuan University, Chengdu 610065, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaIn recent years, Generative Adversarial Networks (GANs)-based illumination processing of facial images has made favorable achievements. However, some GANs-based illumination-processing methods only pay attention to the image quality and neglect the recognition accuracy, whereas others only crop partial face area and ignore the challenges to synthesize photographic face, background and hair when the original face image is under extreme illumination (Image under extreme illumination (extreme illumination conditions) means that we cannot see the texture and structure information clearly and most pixel values tend to 0 or 255.). Moreover, the recognition accuracy is low when the faces are under extreme illumination conditions. For these reasons, we present an elaborately designed architecture based on convolutional neural network and GANs for processing the illumination of facial image. We use ResBlock at the down-sampling stage in our encoder and adopt skip connections in our generator. This special design together with our loss can enhance the ability to preserve identity and generate high-quality images. Moreover, we use different convolutional layers of a pre-trained feature network to extract varisized feature maps, and then use these feature maps to compute loss, which is named multi-stage feature maps (MSFM) loss. For the sake of fairly evaluating our method against state-of-the-art models, we use four metrics to estimate the performance of illumination-processing algorithms. A variety of experimental data indicate that our method is superior to the previous models under various illumination challenges in illumination processing. We conduct qualitative and quantitative experiments on two datasets, and the experimental data indicate that our scheme obviously surpasses the state-of-the-art algorithms in image quality and identification accuracy.https://www.mdpi.com/1424-8220/20/17/4869face illuminationface preprocessingillumination processingshadow removaldeep learning |
| spellingShingle | Shenggui Ling Ye Lin Keren Fu Di You Peng Cheng A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps Sensors face illumination face preprocessing illumination processing shadow removal deep learning |
| title | A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps |
| title_full | A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps |
| title_fullStr | A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps |
| title_full_unstemmed | A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps |
| title_short | A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps |
| title_sort | high performance face illumination processing method via multi stage feature maps |
| topic | face illumination face preprocessing illumination processing shadow removal deep learning |
| url | https://www.mdpi.com/1424-8220/20/17/4869 |
| work_keys_str_mv | AT shengguiling ahighperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT yelin ahighperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT kerenfu ahighperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT diyou ahighperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT pengcheng ahighperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT shengguiling highperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT yelin highperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT kerenfu highperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT diyou highperformancefaceilluminationprocessingmethodviamultistagefeaturemaps AT pengcheng highperformancefaceilluminationprocessingmethodviamultistagefeaturemaps |