Review of Retargeting Methods and Assessment of Retargeted Image Objective Quality
The image retargeting technique enhances compatibility across various display devices by adjusting the size and aspect ratio of the generated image. Though current image retargeting methods have achieved significant research advancements, they are still not applicable to all types of display devices...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2025-02-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2404047.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The image retargeting technique enhances compatibility across various display devices by adjusting the size and aspect ratio of the generated image. Though current image retargeting methods have achieved significant research advancements, they are still not applicable to all types of display devices. Artificial distortions may arise in image retargeting, reducing the users visual experience and necessitating diverse quality evaluation methods to precisely assess the quality of the resulting retargeted image under various distortion types. This paper comprehensively summarizes the current research progress in image retargeting methods and objective quality evaluation techniques. Firstly, this paper provides an overview of retargeting methods, categorizes them into content-aware image retargeting methods and those based on deep learning techniques, and analyzes the advantages and disadvantages of the two types of methods. Subsequently, this paper delineates the attributes of objective quality evaluation methods for image retargeting, which is essential for the optimization and development of image retargeting methods, encompassing approaches grounded in underlying features and those reliant on multi-level features. This paper then delves into detailing the existing three datasets and conducts a comparative analysis of diverse methodologies for the objective quality evaluation of image retargeting. Finally, this paper proposes potential avenues for future research by addressing the current challenges in the image retargeting field. |
|---|---|
| ISSN: | 1673-9418 |