Multi-loss Function in Robust Convolutional Autoencoder for Reconstruction Low-quality Fingerprint Image
Our research is fingerprint reconstruction based on a convolutional autoencoder. We combine the perceptual measurement as a multi-loss function to give satisfactory weight correction, such as the structural similarity index measure (SSIM), Mean Absolute Error (MAE), and peak signal-to-noise rat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Other |
| Language: | English |
| Published: |
Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/284285/1/169.Multi-loss_Function_in_Robust_Convolutional_Autoencoder_for_Reconstruction_Low-quality_Fingerprint_Image.pdf |
| _version_ | 1826050776531730432 |
|---|---|
| author | Raswa, Farchan Hakim Halberd, Franki Harjoko, Agus Wahyono, Wahyono Lee, Chung-Ting Wang, Jia Ching |
| author_facet | Raswa, Farchan Hakim Halberd, Franki Harjoko, Agus Wahyono, Wahyono Lee, Chung-Ting Wang, Jia Ching |
| author_sort | Raswa, Farchan Hakim |
| collection | UGM |
| description | Our research is fingerprint reconstruction based on
a convolutional autoencoder. We combine the perceptual
measurement as a multi-loss function to give satisfactory weight
correction, such as the structural similarity index measure
(SSIM), Mean Absolute Error (MAE), and peak signal-to-noise
ratio (PSNR). We observed and investigated the result using
multi-loss functions and other loss functions. Eventually, our
experiment obtained the highest image quality metric scores from
the experimental result summarized as a loss function (SSIM +
PSNR) with optimizer Root Mean Squared Propagation
(RMSprop). We evaluated the image reconstruction using a
dataset from FVC2004. Eventually, our proposed method gets
impressive results, increasing the image's average quality by
PSNR of 20.58%, SSIM of 4.07%, and MSE of 38.92%,
respectively. |
| first_indexed | 2024-03-14T00:09:54Z |
| format | Other |
| id | oai:generic.eprints.org:284285 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:09:54Z |
| publishDate | 2022 |
| publisher | Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2842852023-12-06T08:30:15Z https://repository.ugm.ac.id/284285/ Multi-loss Function in Robust Convolutional Autoencoder for Reconstruction Low-quality Fingerprint Image Raswa, Farchan Hakim Halberd, Franki Harjoko, Agus Wahyono, Wahyono Lee, Chung-Ting Wang, Jia Ching Information and Computing Sciences Our research is fingerprint reconstruction based on a convolutional autoencoder. We combine the perceptual measurement as a multi-loss function to give satisfactory weight correction, such as the structural similarity index measure (SSIM), Mean Absolute Error (MAE), and peak signal-to-noise ratio (PSNR). We observed and investigated the result using multi-loss functions and other loss functions. Eventually, our experiment obtained the highest image quality metric scores from the experimental result summarized as a loss function (SSIM + PSNR) with optimizer Root Mean Squared Propagation (RMSprop). We evaluated the image reconstruction using a dataset from FVC2004. Eventually, our proposed method gets impressive results, increasing the image's average quality by PSNR of 20.58%, SSIM of 4.07%, and MSE of 38.92%, respectively. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 2022 Other NonPeerReviewed application/pdf en https://repository.ugm.ac.id/284285/1/169.Multi-loss_Function_in_Robust_Convolutional_Autoencoder_for_Reconstruction_Low-quality_Fingerprint_Image.pdf Raswa, Farchan Hakim and Halberd, Franki and Harjoko, Agus and Wahyono, Wahyono and Lee, Chung-Ting and Wang, Jia Ching (2022) Multi-loss Function in Robust Convolutional Autoencoder for Reconstruction Low-quality Fingerprint Image. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9980345 10.23919/APSIPAASC55919.2022.9980345 |
| spellingShingle | Information and Computing Sciences Raswa, Farchan Hakim Halberd, Franki Harjoko, Agus Wahyono, Wahyono Lee, Chung-Ting Wang, Jia Ching Multi-loss Function in Robust Convolutional Autoencoder for Reconstruction Low-quality Fingerprint Image |
| title | Multi-loss Function in Robust Convolutional
Autoencoder for Reconstruction Low-quality
Fingerprint Image |
| title_full | Multi-loss Function in Robust Convolutional
Autoencoder for Reconstruction Low-quality
Fingerprint Image |
| title_fullStr | Multi-loss Function in Robust Convolutional
Autoencoder for Reconstruction Low-quality
Fingerprint Image |
| title_full_unstemmed | Multi-loss Function in Robust Convolutional
Autoencoder for Reconstruction Low-quality
Fingerprint Image |
| title_short | Multi-loss Function in Robust Convolutional
Autoencoder for Reconstruction Low-quality
Fingerprint Image |
| title_sort | multi loss function in robust convolutional autoencoder for reconstruction low quality fingerprint image |
| topic | Information and Computing Sciences |
| url | https://repository.ugm.ac.id/284285/1/169.Multi-loss_Function_in_Robust_Convolutional_Autoencoder_for_Reconstruction_Low-quality_Fingerprint_Image.pdf |
| work_keys_str_mv | AT raswafarchanhakim multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage AT halberdfranki multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage AT harjokoagus multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage AT wahyonowahyono multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage AT leechungting multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage AT wangjiaching multilossfunctioninrobustconvolutionalautoencoderforreconstructionlowqualityfingerprintimage |