Region-adaptive texture enhancement for detailed person image synthesis

L Yang, P Wang, X Zhang, S Wang… - … on Multimedia and …, 2020 - ieeexplore.ieee.org
The ability to produce convincing textural details is essential for the fidelity of synthesized
person images. Existing methods typically follow a “warping-based” strategy that propagates …

Rapidly and exactly determining postharvest dry soybean seed quality based on machine vision technology

P Lin, L Xiaoli, D Li, S Jiang, Z Zou, Q Lu, Y Chen - Scientific Reports, 2019 - nature.com
The development of machine vision-based technologies to replace human labor for rapid
and exact detection of agricultural product quality has received extensive attention. In this …

Robust line segment matching across views via ranking the line-point graph

D Wei, Y Zhang, X Liu, C Li, Z Li - ISPRS Journal of Photogrammetry and …, 2021 - Elsevier
Line segment matching in two or multiple views is helpful to 3D reconstruction and pattern
recognition. To fully utilize the geometry constraint of different features for line segment …

Label-free regional consistency for image-to-image translation

S Guo, Q Zhou, Y Zhou, Q Gu, J Tang… - … on Multimedia and …, 2021 - ieeexplore.ieee.org
Image-to-Image translation aims to translate images from one domain to another. Existing
approaches mainly stylize the images globally, while the local consistency between regions …

An integrated robust approach for fast face tracking in noisy real-world videos with visual constraints

S Ranganatha, YP Gowramma - … International Conference on …, 2017 - ieeexplore.ieee.org
Face detection and tracking algorithms are used in computer vision applications due to the
fact that they provide reliable and fast results. This paper describes a model for face tracking …

Codebook guided feature-preserving for recognition-oriented image retargeting

B Yan, W Tan, K Li, Q Tian - IEEE Transactions on Image …, 2017 - ieeexplore.ieee.org
Traditional image resizing methods, such as uniform scaling and content-aware image
retargeting, are designed to preserve the visually salient contents of an image while resizing …

Dual-task attention-guided character image generation method

F Zhang, H Wang, L Wang… - Journal of Intelligent & …, 2023 - content.iospress.com
Human body pose transfer is to transform the character image from the source image pose
to the target pose. In recent years, the research has achieved great success in transforming …

Assessing the impact of corneal refraction and iris tissue non-planarity on iris recognition

J Thompson, P Flynn, C Boehnen… - IEEE Transactions …, 2018 - ieeexplore.ieee.org
Assumptions regarding eye morphology are implicit in iris recognition algorithms. The
cornea is assumed to have little to no effect on the view of the iris texture when the eye gaze …

Generating future frames with mask-guided prediction

Q Wu, X Chen, Z Huang, W Wang - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
Current approaches in video prediction tend to hallucinate the future frames directly or learn
global motion transformation from the entire scene. However, it is difficult for these methods …

[HTML][HTML] 基于计算机视觉的钢板测量系统研究

王直, 赵越超 - 江苏科技大学学报: 自然科学版, 2013 - fx361.com
在造船行业中, 船用钢板的弯曲成型是重要的环节. 目前国内外造船厂大都依靠工人采用手工卡
样板的方法对钢板成型情况进行判断, 这种方法耗时耗力, 且精度较低. 针对这一问题 …