Displays最新文献

{"title":"A high-precision framework for teeth instance segmentation in panoramic radiographs","authors":"Yanning Ma ,&nbsp;Zhiyuan Qu ,&nbsp;Xulin Liu ,&nbsp;Jiaman Lin ,&nbsp;Zuolin Jin","doi":"10.1016/j.displa.2025.103064","DOIUrl":"10.1016/j.displa.2025.103064","url":null,"abstract":"<div><div>Panoramic radiography plays a vital role in dental diagnosis and treatment, characterized by low radiation exposure, cost-effectiveness, and high accessibility, rendering it suitable for initial screening of oral diseases. However, inexperienced dentists may find it challenging to accurately interpret the information presented in panoramic images regarding the teeth, jaw bone, and maxillary sinus, which can result in missed diagnoses or misdiagnoses. This study proposed a deep learning-based framework for segmenting teeth and alveolar bone from panoramic radiographs and also provided examples of its application for disease diagnosis. This study incorporated relevant medical knowledge when designing algorithms, including graphic optimization algorithms and medical optimization algorithms. The experimental results indicated that the proposed segmentation method was very accurate in segmenting teeth and alveolar bone. The proposed method also improved the accuracy of disease diagnosis in panoramic radiographs, further demonstrating the clinical value of the method for segmenting teeth and alveolar bone.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103064"},"PeriodicalIF":3.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Burst image super-resolution based on dual branch fusion and adaptive frame selection","authors":"Lijuan Duan ,&nbsp;Wendi Zuo ,&nbsp;Ke Gu ,&nbsp;Zhi Gong","doi":"10.1016/j.displa.2025.103057","DOIUrl":"10.1016/j.displa.2025.103057","url":null,"abstract":"<div><div>The modern handheld camera is capable of rapidly capturing multiple images and subsequently merging them into a single image. The extant methodologies typically select the first frame as the reference frame, utilising the information from the remaining frames and the information from the reference frame to calculate the high-resolution image. However, for complex scenes and unstable shooting situations, this fixed frame selection is not the optimum solution. In this direction, we propose an adaptive frame selection method which, by calculating the frame channel weight information, selects the best frame image as the reference frame to perform the subsequent computation. Moreover, to enhance the visual quality of high-resolution images, we propose a dual-branch fusion module in the feature fusion phase for the sequence attributes of the input frame images. This allows the network to concentrate on the temporal global features of the input sequence and the spatial local detail features of the frame images. Subsequently, the feature map is obtained through residual computation utilising the adaptive selected frame image and the image features obtained through fusion. The image is then reconstructed through up-sampling to obtain a high-resolution image. The experimental results on the BurstSR and RealBSR datasets demonstrate that our approach not only outperforms existing techniques in terms of evaluation metrics but also exhibits superior visual effects.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103057"},"PeriodicalIF":3.7,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of tunnel lighting on traffic emissions based on VR experiment and car-following method","authors":"Xin Huang ,&nbsp;Yi Rui ,&nbsp;Shiqi Dou ,&nbsp;Guanlin Huang ,&nbsp;Xiaojun Li ,&nbsp;Yuxin Zhang","doi":"10.1016/j.displa.2025.103071","DOIUrl":"10.1016/j.displa.2025.103071","url":null,"abstract":"<div><div>The complex lighting environments within tunnels have been established as significant factors influencing drivers’ visual processing abilities, which in turn affect driving safety and comfort. However, there is a lack of research exploring whether tunnel lighting impacts drivers’ eco-driving behaviors, particularly in terms of vehicle carbon emissions. To address this gap, this study designs a virtual reality (VR) driving experiment, utilizing luminance and correlated color temperature (CCT) as key lighting parameters to quantitatively assess the influence of tunnel lighting environments on traffic carbon emissions. Furthermore, the intelligent driver model (IDM) is employed to simulate and analyze traffic flow within tunnels. Carbon emissions are calculated using the MOVES methodology. The findings reveal that car platoons exhibit the lowest carbon emissions under lighting environments of (1 cd/m², 5000 K) and (3 cd/m², 2000 K), which are optimal for reducing traffic emissions. Compared to the scenario with the highest total carbon emissions, occurring under lighting conditions of (3 cd/m², 8000 K), the total carbon emissions are reduced by 26.8 % when the lighting is set to (3 cd/m², 2000 K). By integrating VR experiments with traffic simulations, this study bridges the existing research gap regarding the effects of tunnel lighting on traffic emissions and provides valuable insights for the low-carbon design of tunnel lighting environments.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103071"},"PeriodicalIF":3.7,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced defense against GAN-based facial manipulation: A multi-domain and multi-dimensional feature fusion approach","authors":"Yunqi Liu ,&nbsp;Xue Ouyang ,&nbsp;Xiaohui Cui","doi":"10.1016/j.displa.2025.103062","DOIUrl":"10.1016/j.displa.2025.103062","url":null,"abstract":"<div><div>Powerful facial image manipulation offered by encoder-based GAN inversion techniques raises concerns about potential misuse in identity fraud and misinformation. This study introduces the Multi-Domain and Multi-Dimensional Feature Fusion (MDFusion) method, a novel approach that counters encoder-based GAN inversion by generating adversarial samples. Firstly, MDFusion transforms the luminance channel of the target image into spatial, frequency, and spatial-frequency hybrid domains. Secondly, we use the specifically adapted Feature Pyramid Network (FPN) to extract and fuse high-dimensional and low-dimensional features that enhance the robustness of adversarial noise generation. Then, we embed adversarial noise into the spatial-frequency hybrid domain to produce effective adversarial samples. Finally, the adversarial samples are guided by our designed hybrid training loss to achieve a balance between imperceptibility and effectiveness. Tests were conducted on five encoder-based GAN inversion models using ASR, LPIPS, and FID metrics. These tests demonstrated the superiority of MDFusion over 13 baseline methods, highlighting its robust defense and generalization abilities. The implementation code is available at <span><span>https://github.com/LuckAlex/MDFusion</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103062"},"PeriodicalIF":3.7,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biomedical text-based detection of colon, lung, and thyroid cancer: A deep learning approach with novel dataset","authors":"Kubilay Muhammed Sünnetci","doi":"10.1016/j.displa.2025.103068","DOIUrl":"10.1016/j.displa.2025.103068","url":null,"abstract":"<div><div>Pre-trained Language Models (PLMs) are widely used nowadays and increasingly popular. These models can be used to solve Natural Language Processing (NLP) challenges, and their focus on specific topics allows the models to provide answers to directly relevant issues. As a sub-branch of this, Biomedical Text Classification (BTC) is a fundamental task that can be used in various applications and is used to aid clinical decisions. Therefore, this study detects colon, lung, and thyroid cancer from biomedical texts. A dataset including 3070 biomedical texts is generated by artificial intelligence and used in the study. In this dataset, there are 1020 texts labeled colon cancer, while the number of samples labeled lung and thyroid cancer is equal to 1020 and 1030, respectively. In the study, 70 % of the data is used in the training set, while the remaining data is split for validation and test sets. After preprocessing all the data used in the study, word encoding is used to prepare the model inputs. Furthermore, these documents in the dataset are converted into sequences of numeric indices. Afterward, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (BiLSTM), LSTM+LSTM, GRU+GRU, BiLSTM+BiLSTM, and LSTM+GRU+BiLSTM architectures are trained with train and validation sets, and these models are tested with the test set. Both validation and test performances of all developed models are determined, and a Graphical User Interface (GUI) software is prepared in which the most successful architecture has been embedded. The results show that LSTM is the most successful model, and the accuracy and specificity values achieved by this model in the validation set are equal to 91.32 % and 95.67 %, respectively. The F1 score value achieved by this model for the validation set is also equal to 91.32 %. The accuracy, specificity, and F1 score values achieved by this model in the test set are equal to 85.87 %, 92.94 %, and 85.90 %, respectively. The sensitivity values achieved by this model for the validation and test set are 91.33 % and 85.88 %, respectively. These developed models both provide comparative results and have shown successful performances. Focusing these models on specific issues can provide more effective results for related problems. Furthermore, the presentation of a user-friendly GUI application developed in the study allows users to use the models effectively.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103068"},"PeriodicalIF":3.7,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A full-reference image quality assessment method based on visual attention and phase consistency","authors":"Fan Zhang ,&nbsp;Xinhong Zhang","doi":"10.1016/j.displa.2025.103060","DOIUrl":"10.1016/j.displa.2025.103060","url":null,"abstract":"<div><div>Human Visual System (HVS) focuses more attention on areas of high salience when perceiving image quality. The human eye attaches great importance to the structural change of the image, and the degree of structural change of the image can be reflected by the phase consistency. This paper proposes a full-reference image quality assessment method PCHSIVS based on multi-feature fusion. The phase consistency similarity, visual significance similarity and chrominance similarity are used to generate image quality scores, and the generated image quality scores are weighted by visual significance maps. The experimental results show that the PCHSIVS method is more consistent with the characteristics of human visual perception.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103060"},"PeriodicalIF":3.7,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Summary report auto-generation based on hierarchical corpus using large language model","authors":"Xinxin Guan,&nbsp;Zekai Ye,&nbsp;Bin Cao,&nbsp;Jing Fan","doi":"10.1016/j.displa.2025.103055","DOIUrl":"10.1016/j.displa.2025.103055","url":null,"abstract":"<div><div>Enterprises are increasingly challenged by the exponential growth of data, making it essential to efficiently extract, organize, and present query-related data in actionable reports for decision-making. Traditional report generation is time-intensive and reliant on manual effort. Large language model (LLM) offers a promising solution by automating this process. However, existing research on automatic report generation has primarily focused on specific domains, such as medical and financial fields. To address this gap, we propose SRAG (Summary Report Auto-Generation), a novel framework that leverages LLM to transform a query into a high-quality summary report through hierarchical corpus retrieval across general fields. SRAG emulates human report writing by structuring the process into five stages: Data Pre-processing, Basic Outline Drafting, Detailed Outline Refinement, Content Writing, and Section Refinement and Integration. The pre-processing stage converts raw data into a hierarchical corpus, enriching retrieval context with hybrid mechanisms. The subsequent stages are meticulously designed to enhance the interaction between the LLM and the Retriever, guided by stage-specific metrics. Each stage builds on the previous one, iteratively expanding a query into a complete and comprehensive summary report. Experimental results with open-source LLMs demonstrate that each stage of SRAG significantly enhances the overall quality of generated reports. SRAG outperforms baseline methods across all custom metrics, particularly excelling in content-based metrics. It achieves overall score improvements of 7.7% compared to the naive RAG-based method on the CCTD dataset and 2.4% on the ARD dataset. The results highlight SRAG’s potential to enhance decision-making by leveraging the capabilities of LLMs.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103055"},"PeriodicalIF":3.7,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143903634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blind DIBR-synthesized view quality assessment by integrating local geometry and global structure analysis","authors":"Yuanhao Cai ,&nbsp;Chongchong Jin ,&nbsp;Yeyao Chen ,&nbsp;Ting Luo ,&nbsp;Zhouyan He ,&nbsp;Gangyi Jiang","doi":"10.1016/j.displa.2025.103061","DOIUrl":"10.1016/j.displa.2025.103061","url":null,"abstract":"<div><div>The realization of free viewpoint videos (FVV) relies heavily on depth-image-based-rendering (DIBR) technology, but the imperfections of DIBR usually lead to local geometric distortions that significantly impact user experience. Therefore, it is crucial to develop a specialized image quality assessment (IQA) model for DIBR-synthesized views. To address this, this paper leverages local geometry and global structure analysis for DIBR-synthesized IQA (LGGS-SIQA). Specifically, in the local geometry-aware feature extraction module, the proposed method introduces an auxiliary task that converts the score learning task into a distortion classification task, aiming to simplify score sample expansion while effectively locating local geometric distortion regions. Based on this, different types of DIBR-synthesized distortions are further detected and weighted to obtain local geometric features. In the global structure-aware feature extraction module, as DIBR-synthesized distortions are mainly concentrated at object edges, the proposed method designs a strategy to extract key structures globally. Statistical analysis of these regions is performed to obtain robust global structural features. Finally, these two types of features are fused and regressed to obtain the final quality score. Experimental results on public benchmark databases show that the proposed LGGS-SIQA method outperforms existing manually extracted-based and deep learning-based IQA methods. Besides, feature ablation experiments validate the effectiveness of the core components of the proposed LGGS-SIQA method.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103061"},"PeriodicalIF":3.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mamba4PASS: Vision Mamba for PAnoramic Semantic Segmentation","authors":"Jiayue Xu,&nbsp;Chao Xu,&nbsp;Jianping Zhao,&nbsp;Cheng Han,&nbsp;Hua Li","doi":"10.1016/j.displa.2025.103058","DOIUrl":"10.1016/j.displa.2025.103058","url":null,"abstract":"<div><div>PAnoramic Semantic Segmentation (PASS) is a significant and challenging task in the field of computer vision, aimed at achieving comprehensive scene understanding through an ultra-wide-angle view. However, the equirectangular projection (ERP) with richer contextual information is susceptible to geometric distortion and spatial discontinuity, which undoubtedly impede the efficacy of PASS. Recently, significant progress has been made in PASS, nevertheless, these methods often face a dilemma between global perception and efficient computation, as well as the effective trade-off between image geometric distortion and spatial discontinuity. To address this, we propose a novel framework for PASS, Mamba4PASS, which is more efficient compared to Transformer-based backbone models. We introduce an Incremental Feature Fusion (IFF) module that gradually integrates semantic features from deeper layers with spatial detail features from shallower layers, effectively alleviating the loss of local details caused by State Space Model (SSM). Additionally, we introduce a Spherical Geometry-Aware Deformable Patch Embedding (SGADPE) module, which leverages spherical geometry properties and employs a novel deformable convolution strategy to adapt to ERPs, effectively addressing spatial discontinuities and stabilizing geometric distortions. To the best of our knowledge, this is the first semantic segmentation model for panoramic images based on the Mamba architecture. We explore the potential of this approach for PASS, providing a new solution to this domain, and validate its effectiveness and advantages. Extensive experiments demonstrate the effectiveness of the proposed method, achieving state-of-the-art results compared to existing approaches.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103058"},"PeriodicalIF":3.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DMCMFuse: A dual-phase model via multi-dimensional cross-scanning state space model for multi-modality medical image fusion","authors":"Hang Zhao ,&nbsp;Zitong Wang ,&nbsp;Chenyang Li ,&nbsp;Rui Zhu ,&nbsp;Feiyang Yang","doi":"10.1016/j.displa.2025.103056","DOIUrl":"10.1016/j.displa.2025.103056","url":null,"abstract":"<div><div>Multi-modality medical image fusion is crucial for improving diagnostic accuracy by combining complementary information from different imaging modalities. However, a key challenge is effectively balancing the abundant modality-specific features (e.g., soft tissue details in MRI and bone structure in CT) with the relatively fewer modality-shared features, often leading to suboptimal fusion outcomes. To address this, we propose DMCMFuse, a dual-phase model for multi-modality medical image fusion that leverages a multi-dimensional cross-scanning state-space model. The model first decomposes multi-modality images into distinct frequency components to maintain spatial and channel coherence. In the fusion phase, we apply Mamba for the first time in medical image fusion and develop a fusion method that integrates spatial scanning, spatial interaction, and channel scanning. This multi-dimensional cross-scanning approach effectively combines features from each modality, ensuring the retention of both global and local information. Comprehensive experimental results demonstrate that DMCMFuse surpasses the state-of-the-art methods, generating fused images of superior quality with enhanced structure consistency and richer feature representation, making it highly effective for medical image analysis and diagnosis.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"89 ","pages":"Article 103056"},"PeriodicalIF":3.7,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}