Sketch face recognition refers to matching photos with sketches, which has effectively been used in various applications ranging from law enforcement agencies to digital entertainment. However, due to the large modality gap between photos and sketches, sketch face recognition remains a challenging task at present. To reduce the domain gap between the sketches and photos, this paper proposes a cascaded transformation generation network for cross-modality image generation and sketch face recognition simultaneously. The proposed cascaded transformation generation network is composed of a generation module, a cascaded feature transformation module, and a classifier module. The generation module aims to generate a high quality cross-modality image, the cascaded feature transformation module extracts high-level semantic features for generation and recognition simultaneously, the classifier module is used to complete sketch face recognition. The proposed transformation generation network is trained in an end-to-end manner, it strengthens the recognition accuracy by the generated images. The recognition performance is verified on the UoM-SGFSv2, e-PRIP, and CUFSF datasets; experimental results show that the proposed method is better than other state-of-the-art methods.
Lin CAO
Beijing Information Science and Technology University
Xibao HUO
Beijing Information Science and Technology University
Yanan GUO
Beijing Information Science and Technology University
Kangning DU
Beijing Information Science and Technology University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Lin CAO, Xibao HUO, Yanan GUO, Kangning DU, "Sketch Face Recognition via Cascaded Transformation Generation Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 10, pp. 1403-1415, October 2021, doi: 10.1587/transfun.2021EAP1005.
Abstract: Sketch face recognition refers to matching photos with sketches, which has effectively been used in various applications ranging from law enforcement agencies to digital entertainment. However, due to the large modality gap between photos and sketches, sketch face recognition remains a challenging task at present. To reduce the domain gap between the sketches and photos, this paper proposes a cascaded transformation generation network for cross-modality image generation and sketch face recognition simultaneously. The proposed cascaded transformation generation network is composed of a generation module, a cascaded feature transformation module, and a classifier module. The generation module aims to generate a high quality cross-modality image, the cascaded feature transformation module extracts high-level semantic features for generation and recognition simultaneously, the classifier module is used to complete sketch face recognition. The proposed transformation generation network is trained in an end-to-end manner, it strengthens the recognition accuracy by the generated images. The recognition performance is verified on the UoM-SGFSv2, e-PRIP, and CUFSF datasets; experimental results show that the proposed method is better than other state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAP1005/_p
Copy
@ARTICLE{e104-a_10_1403,
author={Lin CAO, Xibao HUO, Yanan GUO, Kangning DU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Sketch Face Recognition via Cascaded Transformation Generation Network},
year={2021},
volume={E104-A},
number={10},
pages={1403-1415},
abstract={Sketch face recognition refers to matching photos with sketches, which has effectively been used in various applications ranging from law enforcement agencies to digital entertainment. However, due to the large modality gap between photos and sketches, sketch face recognition remains a challenging task at present. To reduce the domain gap between the sketches and photos, this paper proposes a cascaded transformation generation network for cross-modality image generation and sketch face recognition simultaneously. The proposed cascaded transformation generation network is composed of a generation module, a cascaded feature transformation module, and a classifier module. The generation module aims to generate a high quality cross-modality image, the cascaded feature transformation module extracts high-level semantic features for generation and recognition simultaneously, the classifier module is used to complete sketch face recognition. The proposed transformation generation network is trained in an end-to-end manner, it strengthens the recognition accuracy by the generated images. The recognition performance is verified on the UoM-SGFSv2, e-PRIP, and CUFSF datasets; experimental results show that the proposed method is better than other state-of-the-art methods.},
keywords={},
doi={10.1587/transfun.2021EAP1005},
ISSN={1745-1337},
month={October},}
Copy
TY - JOUR
TI - Sketch Face Recognition via Cascaded Transformation Generation Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1403
EP - 1415
AU - Lin CAO
AU - Xibao HUO
AU - Yanan GUO
AU - Kangning DU
PY - 2021
DO - 10.1587/transfun.2021EAP1005
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 2021
AB - Sketch face recognition refers to matching photos with sketches, which has effectively been used in various applications ranging from law enforcement agencies to digital entertainment. However, due to the large modality gap between photos and sketches, sketch face recognition remains a challenging task at present. To reduce the domain gap between the sketches and photos, this paper proposes a cascaded transformation generation network for cross-modality image generation and sketch face recognition simultaneously. The proposed cascaded transformation generation network is composed of a generation module, a cascaded feature transformation module, and a classifier module. The generation module aims to generate a high quality cross-modality image, the cascaded feature transformation module extracts high-level semantic features for generation and recognition simultaneously, the classifier module is used to complete sketch face recognition. The proposed transformation generation network is trained in an end-to-end manner, it strengthens the recognition accuracy by the generated images. The recognition performance is verified on the UoM-SGFSv2, e-PRIP, and CUFSF datasets; experimental results show that the proposed method is better than other state-of-the-art methods.
ER -