Reinforcement learning cropping method based on comprehensive feature and aesthetics assessment

Zhang, YaQing; Li, Xueming

doi:10.1049/ipr2.12420

Cited by 4 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies have solved irregular boundary selection by directly using smaller rectangular boxes to crop images [11,12]. However, such methods may result in the loss of a large amount of information, which contradicts the original purpose of image stitching, which aims to expand the field of view [13,14].…”

Section: Introductionmentioning

confidence: 99%

Rectification for Stitched Images with Deformable Meshes and Residual Networks

Fan,

Mao,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Image stitching is an important method for digital image processing, which is often prone to the problem of the irregularity of stitched images after stitching. And the traditional image cropping or complementation methods usually lead to a large number of information loss. Therefore, this paper proposes an image rectification method based on deformable mesh and residual network. The method aims to minimize the information loss at the edges of the spliced image and the information loss inside the image. Specifically, the method can select the most suitable mesh shape for residual network regression according to different images. Its loss function includes global loss and local loss, aiming to minimize the loss of image information within the grid and global target. The method in this paper not only greatly reduces the information loss caused by irregular shapes after image stitching, but also adapts to different images with various rigid structures. Meanwhile, its validation on the DIR-D dataset shows that the method outperforms the state-of-the-art methods in image rectification.

show abstract

Section: Introductionmentioning

confidence: 99%

Rectification for Stitched Images with Deformable Meshes and Residual Networks

Fan,

Mao,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

View adjustment: helping users improve photographic composition

Sheng,

Ke,

Yang

et al. 2024

Multimedia Systems

View full text Add to dashboard Cite

A survey on deep reinforcement learning architectures, applications and emerging trends

et al. 2022

View full text Add to dashboard Cite

From a future perspective and with the current advancements in technology, deep reinforcement learning (DRL) is set to play an important role in several areas like transportation, automation, finance, medical and in many more fields with less human interaction. With the popularity of its fast‐learning algorithms there is an exponential increase in the opportunities for handling dynamic environments without any explicit programming. Additionally, DRL sophisticatedly handles real‐world complex problems in different environments. It has grasped great attention in the areas of natural language processing (NLP), speech recognition, computer vision and image classification which has led to a drastic increase in solving complex problems like planning, decision‐making and perception. This survey provides a comprehensive analysis of DRL and different types of neural network, DRL architectures, and their real‐world applications. Recent and upcoming trends in the field of artificial intelligence (AI) and its categories have been emphasized and potential challenges have been discussed.

show abstract

Reinforcement learning cropping method based on comprehensive feature and aesthetics assessment

Cited by 4 publications

References 36 publications

Rectification for Stitched Images with Deformable Meshes and Residual Networks

Rectification for Stitched Images with Deformable Meshes and Residual Networks

View adjustment: helping users improve photographic composition

A survey on deep reinforcement learning architectures, applications and emerging trends

Contact Info

Product

Resources

About