A method of inpainting moles and acne on the high‐resolution face photos
Abstract With the rapid development of mobile phones, more and more high‐resolution photos are taken. The demand for high‐resolution image inpainting is becoming increasingly urgent. In order to repair high‐resolution face images automatically and quickly, this paper proposes an improved generative...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-02-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12066 |
| _version_ | 1797986123001102336 |
|---|---|
| author | Xuewei Li Xueming Li Xianlin Zhang Yang Liu Jiayi Liang Ziliang Guo Keyu Zhai |
| author_facet | Xuewei Li Xueming Li Xianlin Zhang Yang Liu Jiayi Liang Ziliang Guo Keyu Zhai |
| author_sort | Xuewei Li |
| collection | DOAJ |
| description | Abstract With the rapid development of mobile phones, more and more high‐resolution photos are taken. The demand for high‐resolution image inpainting is becoming increasingly urgent. In order to repair high‐resolution face images automatically and quickly, this paper proposes an improved generative adversarial networks method. Firstly, we made a high‐resolution dataset for training and testing, and abandoned the traditional 256×256 size data. Secondly, since the existing methods can only repair the mask with fixed size and shape on the image, when the global average pooling layer is used in the network, the improved network can repair the moles and acne with arbitrary sizes and shapes on the human face photos. Finally, in order to achieve optimal performance of the network, a mixed loss function is used in training. The experimental results prove that our method has not only achieved good results in qualitative results, but also achieved excellent results in quantitative results. |
| first_indexed | 2024-04-11T07:28:59Z |
| format | Article |
| id | doaj.art-b4ab93a93bc8432eb60cd1058be3e657 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-11T07:28:59Z |
| publishDate | 2021-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-b4ab93a93bc8432eb60cd1058be3e6572022-12-22T04:36:59ZengWileyIET Image Processing1751-96591751-96672021-02-0115383384410.1049/ipr2.12066A method of inpainting moles and acne on the high‐resolution face photosXuewei Li0Xueming Li1Xianlin Zhang2Yang Liu3Jiayi Liang4Ziliang Guo5Keyu Zhai6Beijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaBeijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing ChinaAbstract With the rapid development of mobile phones, more and more high‐resolution photos are taken. The demand for high‐resolution image inpainting is becoming increasingly urgent. In order to repair high‐resolution face images automatically and quickly, this paper proposes an improved generative adversarial networks method. Firstly, we made a high‐resolution dataset for training and testing, and abandoned the traditional 256×256 size data. Secondly, since the existing methods can only repair the mask with fixed size and shape on the image, when the global average pooling layer is used in the network, the improved network can repair the moles and acne with arbitrary sizes and shapes on the human face photos. Finally, in order to achieve optimal performance of the network, a mixed loss function is used in training. The experimental results prove that our method has not only achieved good results in qualitative results, but also achieved excellent results in quantitative results.https://doi.org/10.1049/ipr2.12066Image recognitionComputer vision and image processing techniquesNeural nets |
| spellingShingle | Xuewei Li Xueming Li Xianlin Zhang Yang Liu Jiayi Liang Ziliang Guo Keyu Zhai A method of inpainting moles and acne on the high‐resolution face photos IET Image Processing Image recognition Computer vision and image processing techniques Neural nets |
| title | A method of inpainting moles and acne on the high‐resolution face photos |
| title_full | A method of inpainting moles and acne on the high‐resolution face photos |
| title_fullStr | A method of inpainting moles and acne on the high‐resolution face photos |
| title_full_unstemmed | A method of inpainting moles and acne on the high‐resolution face photos |
| title_short | A method of inpainting moles and acne on the high‐resolution face photos |
| title_sort | method of inpainting moles and acne on the high resolution face photos |
| topic | Image recognition Computer vision and image processing techniques Neural nets |
| url | https://doi.org/10.1049/ipr2.12066 |
| work_keys_str_mv | AT xueweili amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT xuemingli amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT xianlinzhang amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT yangliu amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT jiayiliang amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT ziliangguo amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT keyuzhai amethodofinpaintingmolesandacneonthehighresolutionfacephotos AT xueweili methodofinpaintingmolesandacneonthehighresolutionfacephotos AT xuemingli methodofinpaintingmolesandacneonthehighresolutionfacephotos AT xianlinzhang methodofinpaintingmolesandacneonthehighresolutionfacephotos AT yangliu methodofinpaintingmolesandacneonthehighresolutionfacephotos AT jiayiliang methodofinpaintingmolesandacneonthehighresolutionfacephotos AT ziliangguo methodofinpaintingmolesandacneonthehighresolutionfacephotos AT keyuzhai methodofinpaintingmolesandacneonthehighresolutionfacephotos |