Thesis
Smart resizing: a hybrid deep-learning approach to content-aware and selective image retargeting
Master of Science (M.S.), Drexel University
Jun 2023
DOI:
https://doi.org/10.17918/00001699
Abstract
Image resizing is an important image processing task that is widely implemented in the fields of digital and print media. Despite its widespread use, few image resizing algorithms or workflows take advantage of modern developments in deep-learning computer vision models to improve the resizing output while also giving the user directorial control. We present an image retargeting framework which implements a confidence map generated by a segmentation model for content-aware resizing, allowing users to specify which subjects in an image to preserve using natural language prompts much like the role of an art director conversing with their artist. Using computer vision models to detect object positions also provides additional control over the composition of the retargeted image at various points in the image-processing pipeline. This object-based approach to energy map augmentation is incredibly flexible, because only minor adjustments to the processing of the energy maps can provide a significant degree of control over where seams - paths of pixels through the image - are removed, and how seam removal is prioritized in different sections of the image. It also provides additional control with techniques for object and background separation and recomposition. This research explores how several different types of deep-learning models can be integrated into this pipeline in order to easily make these decisions, and provide different retargeting results on the same image based on user input and compositional considerations. Because this is a framework based on existing machine-learning models, this approach will benefit from advancements in the rapidly developing fields of computer vision and large language models and can be extended for further natural language directorial controls over images.
Metrics
43 File views/ downloads
54 Record Views
Details
- Title
- Smart resizing
- Creators
- Elliot Dickman
- Contributors
- Paul J. Diefenbach (Advisor)
- Awarding Institution
- Drexel University
- Degree Awarded
- Master of Science (M.S.)
- Publisher
- Drexel University; Philadelphia, Pennsylvania
- Number of pages
- vii, 64 pages
- Resource Type
- Thesis
- Language
- English
- Academic Unit
- Digital Media; Drexel University; Antoinette Westphal College of Media Arts and Design
- Other Identifier
- 991020879308704721