Image Features Research Articles

A multimodal educational robots driven via dynamic attention

IntroductionWith the development of artificial intelligence and robotics technology, the application of educational robots in teaching is becoming increasingly popular. However, effectively evaluating and optimizing multimodal educational robots remains a challenge.MethodsThis study introduces Res-ALBEF, a multimodal educational robot framework driven by dynamic attention. Res-ALBEF enhances the ALBEF (Align Before Fuse) method by incorporating residual connections to align visual and textual data more effectively before fusion. In addition, the model integrates a VGG19-based convolutional network for image feature extraction and utilizes a dynamic attention mechanism to dynamically focus on relevant parts of multimodal inputs. Our model was trained using a diverse dataset consisting of 50,000 multimodal educational instances, covering a variety of subjects and instructional content.Results and discussionThe evaluation on an independent validation set of 10,000 samples demonstrated significant performance improvements: the model achieved an overall accuracy of 97.38% in educational content recognition. These results highlight the model's ability to improve alignment and fusion of multimodal information, making it a robust solution for multimodal educational robots.

Enhancing Biometric Security with Bimodal Deep Learning and Feature-level Fusion of Facial and Voice Data

Recent research in biometric technologies underscores the benefits of multimodal systems that use multiple traits to enhance security by complicating the replication of samples from genuine users. To address this, we present a bimodal deep learning network (BDLN or BNet) that integrates facial and voice modalities. Voice features are extracted using the SincNet architecture, and facial image features are obtained from convolutional layers. Proposed network fuses these feature vectors using either averaging or concatenation methods. A dense connected layer then processes the combined vector to produce a dual-modal vector that encapsulates distinctive user features. This dual-modal vector, processed through a softmax activation function and another dense connected layer, is used for identification. The presented system achieved an identification accuracy of 99% and a low equal error rate (EER) of 0.13% for verification. These results, derived from the VidTimit and BIOMEX-DB datasets, highlight the effectiveness of the proposed bimodal approach in improving biometric security.

Coefficient-Shuffled Variable Block Compressed Sensing for Medical Image Compression in Telemedicine Systems

Medical professionals primarily utilize medical images to detect anomalies within the interior structures and essential organs concealed by the skeletal and dermal layers. The primary purpose of medical imaging is to extract image features for the diagnosis of medical conditions. The processing of these images is indispensable for evaluating a patient’s health. However, when monitoring patients over extended periods using specific medical imaging technologies, a substantial volume of data accumulates daily. Consequently, there arises a necessity to compress these data in order to remove duplicates and speed up the process of acquiring data, making it appropriate for effective analysis and transmission. Compressed Sensing (CS) has recently gained widespread acceptance for rapidly compressing images with a reduced number of samples. Ensuring high-quality image reconstruction using conventional CS and block-based CS (BCS) poses a significant challenge since they rely on randomly selected samples. This challenge can be surmounted by adopting a variable BCS approach that selectively samples from diverse regions within an image. In this context, this paper introduces a novel CS method that uses an energy matrix, namely coefficient shuffling variable BCS (CSEM-VBCS), tailored for compressing a variety of medical images with balanced sparsity, thereby achieving a substantial compression ratio and good reconstruction quality. The results of experimental evaluations underscore a remarkable enhancement in the performance metrics of the proposed method when compared to contemporary state-of-the-art techniques. Unlike other approaches, CSEM-VBCS uses coefficient shuffling to prioritize regions of interest, allowing for more effective compression without compromising image quality. This strategy is especially useful in telemedicine, where bandwidth constraints often limit the transmission of high-resolution medical images. By ensuring faster data acquisition and reduced redundancy, CSEM-VBCS significantly enhances the efficiency of remote patient monitoring and diagnosis.

Evaluating neonatal pain via fusing vision transformer and concept-cognitive computing

In clinical nursing, neonatal pain assessment is a challenging task for preventing and controlling the impact of pain on neonatal development. To reduce the adverse effects of repetitive painful treatments during hospitalization on newborns, we propose a novel method (namely pain concept-cognitive computing model, PainC3M) for evaluating facial pain in newborns. In the fusion system, we first improve the attention mechanism of vision transformer by revising the node encoding way, considering the spatial structure, edge and centrality of nodes, and then use its corresponding encoder as a feature extractor to comprehensively extract image features. Second, we introduce a concept-cognitive computing model as a classifier to evaluate the level of pain. Finally, we evaluate our PainC3M on various open pain data sets and a real clinical pain data stream, and the experimental results demonstrate that our PainC3M is very effective for dynamic classification and superior to other comparative models. It also provides a good approach for pain assessment of individuals with aphasia (or dementia).

Global Path Optimal Planning Method for Autonomous Vehicles Based on Image Feature Extraction

In order to solve the problem of autonomous vehicles driving safely on the road while searching for optimal paths to avoid traffic congestion and obstruction, this paper establishes an optimal path planning model based on image feature extraction. The model consists of four parts: the selection of key turning points, interpolation between turning points, definition of the evaluation function, and global optimal path search. First, based on the map information provided by the network, an image feature detection algorithm was proposed, and the key turning points of the map route were selected and stored in an open table. Then, based on mechanical analysis theory, the cubic interpolation between two key turning points of the optimal path was defined. This allows the car to drive along a continuous curve with a certain arc radius, enabling it to drive smoothly, effectively avoid obstacles, and ensure safety. Then, an evaluation function is defined as needed, and different evaluation functions are specified for different road sections to avoid excessive local deviations in planning and to reduce the impact of known obstacles on the path. Finally, the cost of the search path is calculated based on the evaluation function. According to the principle of minimum cost, a globally optimal heuristic search algorithm is proposed to find the globally optimal path. Experimental results show that the proposed global optimal path planning algorithm has excellent performance, with an average accuracy of 96.71% and a search speed of 2.78 ms. The model not only provides accurate path planning and fast path selection capabilities but also has strong robustness against interference.

Педагогическата компетентност на родителя – литературни прочити на лирически произведения за деца от Българското възраждане до 1944 г.

Abstract: The focus of this article is the pedagogical competence of the parent as reflected in children's literature, particularly in children's lyrics from the Bulgarian Renaissance to the end of World War II in 1944. The aim is to delineate at an intertextual level the image of the parent as a bearer and translator of values, pat¬terns of thinking and behaviour that are universal regardless of their contextual ex¬istence. The hypothesis is that transformations in the image, which are the result of cultural changes, give rise to modifications in the structure of parental peda¬gogical competence, while preserving basic elements in it, reflecting archetypal characteristics in the universal image of the parent. The analysis is made after a selection of lyrical texts by Bulgarian poets, in which they write on the themes of parenthood, the family world, motherhood, the family, the upbringing of children, patriarchal values, and traditions. The features of the artistic images, including that of the mother and the father, are highlighted, the linguistic and stylistic pecu¬liarities in the lyrical works are established. Quotations and examples are given from lyrical texts of children’s literature in Bulgaria, which serve an illustrative and evidential function. Keywords: parenting, pedagogical competence, children's literature, lyrical works.

Image tampering detection based on RDS-YOLOv5 feature enhancement transformation

Malicious image tampering has gradually become another way to threaten social stability and personal safety. Timely detection and precise positioning can help reduce the occurrence of risks and improve the overall safety of society. Due to the limitations of highly targeted dataset training and low-level feature extraction efficiency, the generalization and actual performance of the recent tampered detection technology have not yet reached expectations. In this study, we propose a tampered image detection method based on RDS-YOLOv5 feature enhancement transformation. Firstly, a multi-channel feature enhancement fusion algorithm is proposed to enhance the tampering traces in tampered images. Then, an improved deep learning model named RDS-YOLOv5 is proposed for the recognition of tampered images, and a nonlinear loss metric of aspect ratio was introduced into the original SIOU loss function to better optimize the training process of the model. Finally, RDS-YOLOv5 is trained by combining the features of the original image and the enhancement image to improve the robustness of the detection model. A total of 6187 images containing three forms of tampering: splice, remove, and copy-move were used to comprehensively evaluate the proposed algorithm. In ablation test, compared with the original YOLOv5 model, RDS-YOLOv5 achieved a performance improvement of 6.46%, 5.13%, and 3.15% on F1-Score, mAP50 and mAP95, respectively. In comparative experiments, using SRIOU as the loss function significantly improved the model’s ability to search for the real tampered regions by 2.54%. And the RDS-YOLOv5 model trained by the fusion dataset further improved the comprehensive detection performance by about 1%.

Multi‐scale feature extraction for energy‐efficient object detection in remote sensing images

AbstractObject detection in remote sensing images aims to interpret images to obtain information on the category and location of potential targets, which is of great importance in traffic detection, marine supervision, and space reconnaissance. However, the complex backgrounds and large scale variations in remote sensing images present significant challenges. Traditional methods relied mainly on image filtering or feature descriptor methods to extract features, resulting in underperformance. Deep learning methods, especially one‐stage detectors, for example, the Real‐Time Object Detector (RTMDet) offers advanced solutions with efficient network architectures. Nevertheless, difficulty in feature extraction from complex backgrounds and target localisation in scale variations images limits detection accuracy. In this paper, an improved detector based on RTMDet, called the Multi‐Scale Feature Extraction‐assist RTMDet (MRTMDet), is proposed which address limitations through enhancement feature extraction and fusion networks. At the core of MRTMDet is a new backbone network MobileViT++ and a feature fusion network SFC‐FPN, which enhances the model's ability to capture global and multi‐scale features by carefully designing a hybrid feature processing unit of CNN and a transformer based on vision transformer (ViT) and poly‐scale convolution (PSConv), respectively. The experiment in DIOR‐R demonstrated that MRTMDet achieves competitive performance of 62.2% mAP, balancing precision with a lightweight design.

Differentiation and characterization of non-thymomatous ocular myasthenia gravis children with CT.

To compare thymic features using unenhanced computed tomography (CT) images between children with non-thymomatous ocular myasthenia gravis (OMG) and healthy children and determine the image feature cut-off values to allow differentiation of the two populations. We conducted a retrospective study involving 66 children who underwent chest CT, with 33 having non-thymomatous OMG and 33 healthy children without any abnormality. We recorded CT features of the thymus in each child, including the mean CT attenuation value, thymus area, area ratio, anteroposterior (AP) length, width (W), thickness (T), and transverse diameter (TD). These characteristics were analyzed to distinguish OMG from healthy controls. The receiver operating characteristic (ROC) analysis was used to clarify the best assessment, and the optimal cut-off values were determined. The mean CT attenuation value, the thymus area, area ratio, and TD were significantly different (P < 0.05) between the two groups. The mean CT attenuation value was the most significant characteristic in differentiating OMG and healthy controls (area under the curve [AUC] = 0.70). Using 50.41 as the cut-off value for mean CT attenuation, a specificity of 0.70 and sensitivity of 0.82 was observed for distinguishing the two groups (P = 0.003). Optimal differentiation was achieved by combining more than one characteristic including CT attenuation, thymus area, and TD with an optional area ratio (AUC = 0.72). Non-enhanced CT of the thymus complemented the clinical workup of children with non-thymomatous OMG. The cut-off values of the CT features may allow robust differentiation of OMG children.

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

BackgroundCutaneous melanoma is the most aggressive form of skin cancer, responsible for most skin cancer-related deaths. Recent advances in artificial intelligence, jointly with the availability of public dermoscopy image datasets, have allowed to assist dermatologists in melanoma identification. While image feature extraction holds potential for melanoma detection, it often leads to high-dimensional data. Furthermore, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented.MethodsIn this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, whereas for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations.ResultsThe combination of ensemble FS, CTGAN, and linear models achieved the best predictive results, achieving AUCROC values of 87% (with support vector machine and IR=0.9) and 76% (with LASSO and IR=1.0) for the PH2 and Derm7pt, respectively. We also identified that melanoma lesions were mainly characterized by features related to color, while not-melanoma lesions were characterized by texture features.ConclusionsOur results demonstrate the effectiveness of ensemble FS and synthetic data in the development of models that accurately identify melanoma. This research advances skin lesion analysis, contributing to both melanoma detection and the interpretation of main features for its identification.

Lightweight concrete crack detection based on spiking neural networks

PurposeMost existing methods for concrete crack detection are based on deep learning techniques such as convolutional neural networks. However, these models, due to their large memory footprint, high power consumption and insufficient feature extraction capabilities, face challenges in mobile applications. To address these issues, this paper proposes a lightweight spiking neural network detection model.Design/methodology/approachThis model achieves fast and accurate crack detection. Firstly, the Gabor-Spiking (GS) module preprocesses input images, extracting texture features and edge features of crack images through Gabor filter convolution modules and spiking convolution modules, respectively. Next, the multiscale residual (MR) module is designed, composed of convolutional layers and residual modules of various scales, to process the fused features and perform crack detection.FindingsExperimental results demonstrate that the model’s size can be reduced to 4.6 MB, achieving accuracy improvements to 87.3 and 96.4% on the SDNET and OCD datasets, respectively.Originality/valueThis paper proposes a lightweight spiking neural network detection model based on the GS module for edge texture feature fusion and the MR module for crack detection.

Identification of mild cognitive impairment using multimodal 3D imaging data and graph convolutional networks

Abstract Objective. Mild cognitive impairment (MCI) is a precursor stage of dementia characterized by mild cognitive decline in one or more cognitive domains, without meeting the criteria for dementia. MCI is considered a prodromal form of Alzheimer's disease (AD). Early identification of MCI is crucial for both intervention and prevention of AD. To accurately identify MCI, a novel multimodal 3D imaging data integration graph convolutional network model is designed in this paper. Approach. The proposed model utilizes 3D-VGGNet to extract three-dimensional features from multimodal imaging data (such as sMRI and FDG-PET), which are then fused into feature vectors as the node features of a population graph. Non-imaging features of participants are combined with the multimodal imaging data to construct a population sparse graph. Additionally, in order to optimize the connectivity of the graph, we employed the Pairwise Attribute Estimation (PAE) method to compute the edge weights based on non-imaging data, thereby enhancing the effectiveness of the graph structure. Subsequently, a population-based graph convolutional network (GCN) integrates the structural and functional features of different modal images into the features of each participant for MCI classification. Main results. Experiments on the ADNI demonstrated accuracies of 98.57%, 96.03%, and 96.83% for the NC-EMCI, NC-LMCI, and EMCI-LMCI classification tasks, respectively. The AUC, specificity, sensitivity, and F1-score are also superior to state-of-the-art models, demonstrating the effectiveness of the proposed model. Furthermore, the proposed model is applied to the ABIDE dataset for autism diagnosis, achieving an accuracy of 91.43% and outperforming the state-of-the-art models, indicating excellent generalization capabilities of the proposed model. Significance. This study demonstrate the proposed model’s ability to integrate multimodal imaging data and its excellent ability to recognize MCI. This will help achieve early warning for AD and intelligent diagnosis of other brain neurodegenerative diseases.

A novel spatial pyramid-enhanced indoor visual positioning method

As a key application of Internet of Things (IoT) technology, visual localization plays an important role in everyday life. However, pedestrians in images can obstruct environmental features, negatively impacting the performance of visual localization systems. To address this issue, we propose a Spatial Pyramid-Enhanced MixVPR visual localization method (SPE-VL) that aims to enhance image feature descriptions through multi-scale spatial information, thereby mitigating the effects of pedestrian occlusion on localization accuracy. The SPE-VL method is divided into two main phases: sensor-based matching range constraint and image feature extraction and matching. In the matching range constraint phase, we propose a direction decision method based on a machine learning classifier that utilizes smartphone sensor data to restrict the direction of image matching, reducing the likelihood of mismatches. In the feature extraction and matching phase, we propose a Transformer-based feature cross-enhancement method that leverages local features and spatial contextual information to enhance features, improving both image retrieval accuracy and localization precision. Experimental results indicate that the SPE-VL method demonstrates higher localization accuracy and robustness compared to existing state-of-the-art methods, providing new insights and solutions for the application of visual localization in complex environments.

An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images.

Determining the status of breast cancer susceptibility genes (BRCA) is crucial for guiding breast cancer treatment. Nevertheless, the need for BRCA genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect BRCA status from hematoxylin and eosin (H&E) pathological images. A total of 319 histopathological slides from 254 breast cancer patients were included, comprising two dependent cohorts. Following image pre-processing, 633,484 tumor tiles from the training dataset were employed to train the self-developed deep-learning model. The performance of the network was evaluated in the internal and external test sets. BiAMIL achieved AUC values of 0.819 (95% CI [0.673-0.965]) in the internal test set, and 0.817 (95% CI [0.712-0.923]) in the external test set. To explore the relationship between BRCA status and interpretable morphological features in pathological images, we utilized Class Activation Mapping (CAM) technique and cluster analysis to investigate the connections between BRCA gene mutation status and tissue and cell features. Significantly, we observed that tumor-infiltrating lymphocytes and the morphological characteristics of tumor cells appeared to be potential features associated with BRCA status. An interpretable deep neural network model based on the attention mechanism was developed to predict the BRCA status in breast cancer. Keywords: Breast cancer, BRCA, deep learning, self-attention, interpretability.

Hierarchical Fusion of Infrared and Visible Images Based on Channel Attention Mechanism and Generative Adversarial Networks

In order to solve the problem that existing visible and infrared image fusion methods rely only on the original local or global information representation, which has the problem of edge blurring and non-protrusion of salient targets, this paper proposes a layered fusion method based on channel attention mechanism and improved Generative Adversarial Network (HFCA_GAN). Firstly, the infrared image and visible image are decomposed into a base layer and fine layer, respectively, by a guiding filter. Secondly, the visible light base layer is fused with the infrared image base layer by histogram mapping enhancement to improve the contour effect. Thirdly, the improved GAN algorithm is used to fuse the infrared and visible image refinement layer, and the depth transferable module and guided fusion network are added to enrich the detailed information of the fused image. Finally, the multilayer convolutional fusion network with channel attention mechanism is used to correlate the local information of the layered fusion image, and the final fusion image containing contour gradient information and useful details is obtained. TNO and RoadSence datasets are selected for training and testing. The results show that the proposed algorithm retains the global structure features of multilayer images and has obvious advantages in fusion performance, model generalization and computational efficiency.

Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites

Nanosatellites increasingly produce more data than can be downlinked within a reasonable time due to their limited bandwidth and power. Therefore, an on-board system is required to prioritize scientifically significant data for downlinking, as described by scientists. This paper determines whether natural language processing can be used to prioritize remote sensing images on CubeSats with more flexibility compared to existing methods. Two approaches implementing the same conceptual prioritization pipeline are compared. The first uses YOLOv8 and Llama2 to extract image features and compare them with text descriptions via cosine similarity. The second approach employs CLIP, fine-tuned on remote sensing data, to achieve the same. Both approaches are evaluated on real nanosatellite hardware, the VERTECS Camera Control Board. The CLIP approach, particularly the ResNet50-based model, shows the best performance in prioritizing and sequencing remote sensing images. This paper demonstrates that on-orbit prioritization using natural language descriptions is viable and allows for more flexibility than existing methods.

MSMTRIU-Net: Deep Learning-Based Method for Identifying Rice Cultivation Areas Using Multi-Source and Multi-Temporal Remote Sensing Images

Identifying rice cultivation areas in a timely and accurate manner holds great significance in comprehending the overall distribution pattern of rice and formulating agricultural policies. The remote sensing observation technique provides a convenient means to monitor the distribution of rice cultivation areas on a large scale. Single-source or single-temporal remote sensing images are often used in many studies, which makes the information of rice in different types of images and different growth stages hard to be utilized, leading to unsatisfactory identification results. This paper presents a rice cultivation area identification method based on a deep learning model using multi-source and multi-temporal remote sensing images. Specifically, a U-Net based model is employed to identify the rice planting areas using both the Landsat-8 optical dataset and Sentinel-1 Polarimetric Synthetic Aperture Radar (PolSAR) dataset; to take full into account of the spectral reflectance traits and polarimetric scattering traits of rice in different periods, multiple image features from multi-temporal Landsat-8 and Sentinel-1 images are fed into the network to train the model. The experimental results on China’s Sanjiang Plain demonstrate the high classification precisions of the proposed Multi-Source and Multi-Temporal Rice Identification U-Net (MSMTRIU-NET) and that inputting more information from multi-source and multi-temporal images into the network can indeed improve the classification performance; further, the classification map exhibits greater continuity, and the demarcations between rice cultivation regions and surrounding environments reflect reality more accurately.

Research on automatic segmentation and recognition of single characters in original rubbings based on intelligent recognition of oracle bone inscriptions

This paper proposes an effective segmentation and recognition method using YOLOv8 to solve the problem of segmentation and recognition of Oracle rubbings images. Draw sub-pixel edge contours through spot detection, corner detection, and edge detection (such as Canny and Sobel), and combine grayscale, opening operations, binarization, and Gaussian filtering to remove noise and repair contours, extract image features, and establish preprocessing Model. Use this model to preprocess the original oracle rubbing image and train it based on YOLOv8. The results show that this method can effectively segment and identify oracle bones characters.

Enhancing Multimodal Emotional Information Extraction in Film and Television through Adaptive Feature Fusion with DenseNe, Transformer, and 3D CNN Models

ABSTRACT The extraction of multimodal emotional information enables a more nuanced representation of the emotional subtleties embedded in film and television works. However, conventional approaches that independently extract features from images and text fail to capture the rich semantic interplay between these modalities, impeding the feature learning process within each modality. To address this, this paper presents an innovative model for extracting emotional information from multimodal film and television content. The model utilizes DenseNe for image feature extraction, enhancing network depth via the MSC module. Text feature extraction is achieved through a Transformer encoder, while video feature extraction employs a 3D CNN model. Refinements are made to the number and placement of convolutional layers, planar convolution size, and 3D convolution depth. Moreover, a multi-head scaled dot-product attention mechanism is incorporated into the interaction module to compute the similarity between each image block within the sequence and every word in the text sequence. Experimental evaluations on the CMU-MOSEI and CMU-MOSI datasets showcase superior performance compared to the baseline model, achieving accuracy and F1 scores of 0.708 and 0.698, respectively. Noteworthy is the proposed adaptive feature fusion module, which enriches the expressiveness of pivotal emotional features while eliminating redundant data.

WiTUnet: A U-shaped architecture integrating CNN and Transformer for improved feature alignment and local information fusion

Low-dose computed tomography (LDCT) has emerged as the preferred technology for diagnostic medical imaging due to the potential health risks associated with X-ray radiation and conventional computed tomography (CT) techniques. While LDCT utilizes a lower radiation dose compared to standard CT, it results in increased image noise, which can impair the accuracy of diagnoses. To mitigate this issue, advanced deep learning-based LDCT denoising algorithms have been developed. These primarily utilize Convolutional Neural Networks (CNNs) or Transformer Networks and often employ the Unet architecture, which enhances image detail by integrating feature maps from the encoder and decoder via skip connections. However, existing methods focus excessively on the optimization of the encoder and decoder structures while overlooking potential enhancements to the Unet architecture itself. This oversight can be problematic due to significant differences in feature map characteristics between the encoder and decoder, where simple fusion strategies may hinder effective image reconstruction. In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathway in place of traditional skip connections to improve feature integration. Additionally, to address the high computational demands of conventional Transformers on large images, WiTUnet incorporates a windowed Transformer structure that processes images in smaller, non-overlapping segments, significantly reducing computational load. Moreover, our approach includes a Local Image Perception Enhancement (LiPe) module within both the encoder and decoder to replace the standard multi-layer perceptron (MLP) in Transformers, thereby improving the capture and representation of local image features. Through extensive experimental comparisons, WiTUnet has demonstrated superior performance over existing methods in critical metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Root Mean Square Error (RMSE), significantly enhancing noise removal and image quality. The code is available on github https://github.com/woldier/WiTUNet.