Three-Dimensional Image Quality Evaluation and Optimization Based on Convolutional Neural Network

Luo, Xiang-Qian

doi:10.18280/ts.380414

Cited by 3 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image quality assessment models are also widely used in the fields of image coding, super-resolution reconstruction, image quality enhancement, and other related fields [3]. Image quality assessment mainly includes full-reference image quality assessment, half-reference image quality assessment, and no-reference image quality assessment [4]. Full-reference image quality assessment and half-reference image quality assessment refer to the full availability and partial availability of reference information for predicting image quality, respectively, while no-reference image quality assessment refers to the unavailability of reference information for predicting image quality.…”

Section: Introductionmentioning

confidence: 99%

Online Simulation Quality Assessment of Illustration Patterns Based on Digital Art Design in Neural Network Perspective

Yang

2022

Mobile Information Systems

View full text Add to dashboard Cite

Digital art illustration as new media is a major advancement in the history of illustration. It has broadened the application of graphic arts and the way of communication. At present, digital illustrators are constantly exploring new artistic expressions for digital illustration in order to pursue new digital effects. A wide range of integrated materials and experimental design concepts are gradually emerging, making digital illustration evolve in the competition. The artistic style of digital illustration has also shown the development trend of “diversification.” With the trend of commercialization of digital illustration, the quality of illustration patterns is gradually neglected. The traditional illustration pattern assessment relies on manual subjective judgment, with backward evaluation means and poor accuracy. This study proposes an illustration pattern evaluation method based on a deep neural network. In particular, this study proposes a reference-free image evaluation model with multiple feature fusion; specifically, we use CNN and information entropy-based methods for feature extraction and regularization methods for information fusion to solve the problem of missing reference images in applications. The chunking process is performed on the basis of considering the influence of information entropy on image quality, and the information entropy of multiple chunked features is calculated as importance weights, representing the degree of their influence on distorted image quality. The experimental results on the digital illustration pattern database show that the method in this study has strong robustness and can output a reasonable and reliable quality assessment score for distorted patterns.

show abstract

Section: Introductionmentioning

confidence: 99%

Online Simulation Quality Assessment of Illustration Patterns Based on Digital Art Design in Neural Network Perspective

Yang

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…The model's performance is scrutinized by varying the depth of the Swin-Transformer blocks and the number of multi-head self-attention heads, while also considering the impact of the distorted image ratio within the dataset. The data presented in the table reveal comparable performances across different parameter sets, with the configuration consisting of deeper Swin-Transformer blocks ( [4,4,4,4]) exhibiting a slight advantage over the [2,4,4,2] combination at distorted image ratios of 50% and 70%. This outcome suggests that increasing the depth of the Swin-Transformer module can marginally enhance the model's performance within the tested parameter range.…”

Section: Experimental Results and Analysismentioning

confidence: 94%

“…In today's rapidly evolving digital imaging landscape, IQA has emerged as a pivotal discipline at the intersection of technology and visual fidelity. Propelled by the swift advances in image acquisition and transmission technologies, coupled with an escalating demand for high-quality visual experiences, the evolution of IQA methods has gained considerable momentum [1][2][3][4]. Historically, IQA approaches have been rooted in emulating human visual perception, a strategy that has served well up to a point.…”

Section: Introductionmentioning

confidence: 99%

Innovative Approaches in Image Quality Assessment: A Deep Learning-Enabled Multi-Level and Multi-Scale Perspective

Sun

2023

View full text Add to dashboard Cite

In the dynamic field of digital image technology, the imperative role of Image Quality Assessment (IQA) is increasingly recognized. Traditional methodologies, designed to echo human visual processing, frequently encounter challenges in diverse application landscapes, primarily due to their singular focus on limited scale and level analysis. This shortcoming curtails their efficacy in practical scenarios. The incorporation of deep learning paradigms into IQA has notably enhanced evaluation capabilities. Yet, there remains a scope for refinement, especially in areas like integrating multi-scale data, fusing features at multiple levels, and optimizing computational resources. Addressing these gaps, this study proposes an advanced multi-level and multi-scale IQA strategy, harnessing the power of deep learning. A unique end-to-end multi-scale IQA module has been crafted, tailored to aggregate image quality data across a spectrum of scales comprehensively. Additionally, this research introduces an IQA model built upon the foundation of multi-level feature fusion. This innovative model stands out in its capacity to efficiently assess image quality, by adeptly extracting and amalgamating features from various levels. Beyond enhancing accuracy in quality scoring, this approach significantly bolsters the model's interpretability and operational efficiency, marking a stride forward in digital image processing research and applications.

show abstract

“…For the above stated reasons, as opposed to user evaluation, metric/model based methods; machine learning based approaches focus on visual complexity evaluation rely on machine learning models` understanding. Although, previously deep learning models for other type of general image visual complexity problems [9][10][11] and even for the quality assessment problem for 3D images [12] produced promising results, deep learning models for visual complexity of mobile UIs has not been studied thoroughly. The absence of latent factors that can be utilized in addition to existing metrics without directly involving human in the visual complexity analysis process encouraged us to explore pre-trained models that are known to be effective for computer vision tasks.…”

Section: Introductionmentioning

confidence: 99%

A Deep Transfer Learning Based Visual Complexity Evaluation Approach to Mobile User Interfaces

Akça¹,

Tanrıöver²

2022

View full text Add to dashboard Cite

Visual complexity is an important factor affecting the efficiency and functionality of user interfaces. Its impact on the user's impression and the usability is significant, especially for mobile applications with constraints such as layout size, on screen keys and small input fields. Conventional approaches for visual complexity evaluation of user interfaces are either based on user evaluations with surveys or based on pre-specified formal metrics or on heuristics. Alternatively, in this study, we have explored the effectiveness of deep learning models for visual complexity evaluation, specifically, of mobile user interfaces. We have experimented with five state of the art pre-trained deep learning models known to be effective for computer vision tasks, namely, VGG16, DenseNet121, MobileNetv2, GoogleNet and ResNet152 were trained with 3635 different mobile user interface images as login, menu, search and settings. Furthermore, in order to validate the effectiveness of this approach, a new validation dataset and survey application was developed and an evaluation study was conducted with 98 participants where 7309 comparison result were obtained from the study. It was found that the agreement rate between the results of deep learning models and the user evaluations was up to 78% and 74% on the average. The high to moderate agreement rate between the results of deep learning models and the user evaluations reveals that this approach can be useful for designers in visual complexity evaluation of mobile user interfaces.

show abstract

Three-Dimensional Image Quality Evaluation and Optimization Based on Convolutional Neural Network

Cited by 3 publications

References 22 publications

Online Simulation Quality Assessment of Illustration Patterns Based on Digital Art Design in Neural Network Perspective

Online Simulation Quality Assessment of Illustration Patterns Based on Digital Art Design in Neural Network Perspective

Innovative Approaches in Image Quality Assessment: A Deep Learning-Enabled Multi-Level and Multi-Scale Perspective

A Deep Transfer Learning Based Visual Complexity Evaluation Approach to Mobile User Interfaces

Contact Info

Product

Resources

About