Holistic Features Research Articles

Lithology identification using electrical imaging logging image: A case study in Jiyang Depression, China

Lithology identification plays a significant role in stratigraphic evaluation and geological analysis. Traditional lithology identification method is by modeling the relationship between well logging and lithology. However, well logging are not always sufficient to identify lithology since sometimes the curves are similar for different lithologies. Recently, electrical imaging logging image (EILI) with high resolution plays an increasingly important role in logging interpretation since EILI can intuitively reflect the characteristics of lithology. Unlike traditional lithology identification method by using well logging, in this paper, we propose a novel multi-dimensional automatic lithology identification method by applying deep learning to EILI. First, Filtersim algorithm is employed to fill the blank strip of the EILI. Then, an integrated convolutional neural networks (CNNs) model is designed to extract the resistivity feature, texture feature, and holistic feature of the EILI, respectively. Specifically, the integrated CNNs model can realize automatic recognition for different geological structures (massive, bedded, lamellar) and lithology (mudstone, sand-mudstone, lime-mudstone). Finally, lithology identification can be achieved by combining with multi-dimensional features. The efficacy of proposed integrated model is validated experimentally on the EILI of shale oil reservoir in the Jiyang Depression of China. Experimental results show the effectiveness and superiority of the integrated CNNs method for lithology identification.

Granular correlation-based label-specific feature augmentation for multi-label classification

Multi-label classification is an extension of single-label classification with generations of multi-output for unseen instances. Label correlation is an essential component in constructing multi-label classifiers. How to optimize the representation of label correlation while preserving the semantics of label-specific remains an uncertain issue. Instead of estimating label correlation by a holistic feature representation, we present an augmented label correlation model by generating multi-granularity label-specific features. Firstly, we devise a mixture distance measure to characterize the closeness of an instance by weighing the Pearson correlation coefficient with cosine similarity. Secondly, we explore the local label-specific relative discrimination by leveraging from both the instance-level and class-level correlation distribution within k nearest neighborhood. Finally, we conduct an information fusion strategy to comprehensively integrate the positive and the negative tendencies at the neighborhood level. Instances with salient positive tendency and compact neighborhood structure receive larger values while receiving smaller values with salient negative tendency and sparse neighborhood structure. With the concatenation of original features and augmented features, we examine the classification performance of the proposed granule correlation-based feature augmentation (GOFA) on well-established second-order multi-label classification methods. Extensive comparisons on thirteen benchmarks demonstrate the statistical superiority of GOFA over state-of-the-art multi-label classifications.

Digital Dental Biometrics for Human Identification Based on Automated 3D Point Cloud Feature Extraction and Registration.

Intraoral scans (IOS) provide precise 3D data of dental crowns and gingival structures. This paper explores an application of IOS in human identification. We propose a dental biometrics framework for human identification using 3D dental point clouds based on machine learning-related algorithms, encompassing three stages: data preprocessing, feature extraction, and registration-based identification. In the data preprocessing stage, we use the curvature principle to extract distinguishable tooth crown contours from the original point clouds as the holistic feature identification samples. Based on these samples, we construct four types of local feature identification samples to evaluate identification performance with severe teeth loss. In the feature extraction stage, we conduct voxel downsampling, then extract the geometric and structural features of the point cloud. In the registration-based identification stage, we construct a coarse-to-fine registration scheme in order to realize the identification task. Experimental results on a dataset of 160 individuals demonstrate that our method achieves a Rank-1 recognition rate of 100% using complete tooth crown contours samples. Utilizing the remaining four types of local feature samples yields a Rank-1 recognition rate exceeding 96.05%. The proposed framework proves effective for human identification, maintaining high identification performance even in extreme cases of partial tooth loss.

A novel facial expression recognition model based on harnessing complementary features in multi-scale network with attention fusion

This paper presents a novel method for facial expression recognition using the proposed feature complementation and multi-scale attention model with attention fusion (FCMSA-AF). The proposed model consists of four main components: the shallow feature extractor module, parallel structured two-branch multi-scale attention module (MSA), feature complementing module (FCM), and attention fusion and classification module. The MSA module contains multi-scale attention modules in a cascaded fashion in two paths to learn diverse features. The upper and lower paths use left and right multi-scale blocks to extract and aggregate the features at different receptive fields. The attention networks in MSA focus on salient local regions to extract features at granular levels. The FCM uses the correlation between the feature maps in two paths to make the multi-scale attention features complementary to each other. Finally, the complementary features are fused through an attention network to form an informative holistic feature which includes subtle, visually varying regions in similar classes. Hence, complementary and informative features are used in classification to minimize information loss and capture the discriminating finer aspects of facial expression recognition. Experimental evaluation of the proposed model carried out on AffectNet and CK+ datasets achieve accuracies of 64.59% and 98.98%, respectively, outperforming some of the state-of-the-art methods.

PND-Net: plant nutrition deficiency and disease classification using graph convolutional network

Crop yield production could be enhanced for agricultural growth if various plant nutrition deficiencies, and diseases are identified and detected at early stages. Hence, continuous health monitoring of plant is very crucial for handling plant stress. The deep learning methods have proven its superior performances in the automated detection of plant diseases and nutrition deficiencies from visual symptoms in leaves. This article proposes a new deep learning method for plant nutrition deficiencies and disease classification using a graph convolutional network (GNN), added upon a base convolutional neural network (CNN). Sometimes, a global feature descriptor might fail to capture the vital region of a diseased leaf, which causes inaccurate classification of disease. To address this issue, regional feature learning is crucial for a holistic feature aggregation. In this work, region-based feature summarization at multi-scales is explored using spatial pyramidal pooling for discriminative feature representation. Furthermore, a GCN is developed to capacitate learning of finer details for classifying plant diseases and insufficiency of nutrients. The proposed method, called Plant Nutrition Deficiency and Disease Network (PND-Net), has been evaluated on two public datasets for nutrition deficiency, and two for disease classification using four backbone CNNs. The best classification performances of the proposed PND-Net are as follows: (a) 90.00% Banana and 90.54% Coffee nutrition deficiency; and (b) 96.18% Potato diseases and 84.30% on PlantDoc datasets using Xception backbone. Furthermore, additional experiments have been carried out for generalization, and the proposed method has achieved state-of-the-art performances on two public datasets, namely the Breast Cancer Histopathology Image Classification (BreakHis 40×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document}: 95.50%, and BreakHis 100×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document}: 96.79% accuracy) and Single cells in Pap smear images for cervical cancer classification (SIPaKMeD: 99.18% accuracy). Also, the proposed method has been evaluated using five-fold cross validation and achieved improved performances on these datasets. Clearly, the proposed PND-Net effectively boosts the performances of automated health analysis of various plants in real and intricate field environments, implying PND-Net’s aptness for agricultural growth as well as human cancer classification.

A Prior-Guided Dual Branch Multi-Feature Fusion Network for Building Segmentation in Remote Sensing Images

The domain of remote sensing image processing has witnessed remarkable advancements in recent years, with deep convolutional neural networks (CNNs) establishing themselves as a prominent approach for building segmentation. Despite the progress, traditional CNNs, which rely on convolution and pooling for feature extraction during the encoding phase, often fail to precisely delineate global pixel interactions, potentially leading to the loss of vital semantic details. Moreover, conventional CNN-based segmentation models frequently neglect the nuanced semantic differences between shallow and deep features during the decoding phase, which can result in subpar feature integration through rudimentary addition or concatenation techniques. Additionally, the unique boundary characteristics of buildings in remote sensing images, which offer a rich vein of prior information, have not been fully harnessed by traditional CNNs. This paper introduces an innovative approach to building segmentation in remote sensing images through a prior-guided dual branch multi-feature fusion network (PDBMFN). The network is composed of a prior-guided branch network (PBN) in the encoding process, a parallel dilated convolution module (PDCM) designed to incorporate prior information, and a multi-feature aggregation module (MAM) in the decoding process. The PBN leverages prior region and edge information derived from superpixels and edge maps to enhance edge detection accuracy during the encoding phase. The PDCM integrates features from both branches and applies dilated convolution across various scales to expand the receptive field and capture a more comprehensive semantic context. During the decoding phase, the MAM utilizes deep semantic information to direct the fusion of features, thereby optimizing segmentation efficacy. Through a sequence of aggregations, the MAM gradually merges deep and shallow semantic information, culminating in a more enriched and holistic feature representation. Extensive experiments are conducted across diverse datasets, such as WHU, Inria Aerial, and Massachusetts, revealing that PDBMFN outperforms other sophisticated methods in terms of segmentation accuracy. In the key segmentation metrics, including mIoU, precision, recall, and F1 score, PDBMFN shows a marked superiority over contemporary techniques. The ablation studies further substantiate the performance improvements conferred by the PBN’s prior information guidance and the efficacy of the PDCM and MAM modules.

Better life stories make better lives: a reply to Berg

Is it good for us if the different parts of our lives are connected to each other like the parts of a good story? Some philosophers have thought so, while others have firmly rejected it. In this paper, I focus on the state-of-the-art anti-narrativist arguments Amy Berg has recently presented in this journal. I argue that while she makes a good case that the best kind of lives for us do not revolve around a single project or theme, the best kind of narrativist views actually encourage us to pursue a variety of different projects, as long as they are mutually supportive. I claim that when interpreted in the most plausible way, prudentially good-making narrative coherence arises precisely out of this kind of unity in diversity. Well-roundedness and narrative coherence are thus not inherently in tension, but are both good-making holistic features of our lives.

Infant Faces Induce Behavioral Approach Tendencies: Evidence From a Manikin Task1,2

AbstractInfant faces are generally perceived as being cute and motivate the observer to look at them longer. This phenomenon is thought to be based on elemental features called baby schema (e.g., a round face and a large forehead). This study investigated the behavioral tendencies of observers in approaching infant faces using a manikin task in which infant and adult face images were presented as stimuli. Participants (N = 40) were instructed to identify with the manikin, discriminate a face on the screen, and respond by moving the manikin closer to the face (approach trials) or farther away from it (avoidance trials). The faces were presented either upright or inverted. The results showed that the approach–avoidance indices (the mean reaction time and error rate of avoidance trials minus those of approach trials) were larger for infant faces than for adult faces regardless of face orientation, although the difference was greater for upright faces than for inverted faces. This approach tendency toward infant faces is possibly due to elemental features rather than face‐specific holistic features.

Contrastive Masked Autoencoders are Stronger Vision Learners.

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this goal, we propose Contrastive Masked Autoencoders (CMAE), a new self-supervised pre-training method for learning more comprehensive and capable vision representations. By elaboratively unifying contrastive learning (CL) and masked image model (MIM) through novel designs, CMAE leverages their respective advantages and learns representations with both strong instance discriminability and local perceptibility. Specifically, CMAE consists of two branches where the online branch is an asymmetric encoder-decoder and the momentum branch is a momentum updated encoder. During training, the online encoder reconstructs original images from latent representations of masked images to learn holistic features. The momentum encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart. To make CL compatible with MIM, CMAE introduces two new components, i.e., pixel shifting for generating plausible positive views and feature decoder for complementing features of contrastive pairs. Thanks to these novel designs, CMAE effectively improves the representation quality and transfer performance over its MIM counterpart. CMAE achieves the state-of-the-art performance on highly competitive benchmarks of image classification, semantic segmentation and object detection. Notably, CMAE-Base achieves 85.3% top-1 accuracy on ImageNet and 52.5% mIoU on ADE20k, surpassing previous best results by 0.7% and 1.8% respectively.

Holistic-Guided Disentangled Learning With Cross-Video Semantics Mining for Concurrent First-Person and Third-Person Activity Recognition.

The popularity of wearable devices has increased the demands for the research on first-person activity recognition. However, most of the current first-person activity datasets are built based on the assumption that only the human-object interaction (HOI) activities, performed by the camera-wearer, are captured in the field of view. Since humans live in complicated scenarios, in addition to the first-person activities, it is likely that third-person activities performed by other people also appear. Analyzing and recognizing these two types of activities simultaneously occurring in a scene is important for the camera-wearer to understand the surrounding environments. To facilitate the research on concurrent first- and third-person activity recognition (CFT-AR), we first created a new activity dataset, namely PolyU concurrent first- and third-person (CFT) Daily, which exhibits distinct properties and challenges, compared with previous activity datasets. Since temporal asynchronism and appearance gap usually exist between the first- and third-person activities, it is crucial to learn robust representations from all the activity-related spatio-temporal positions. Thus, we explore both holistic scene-level and local instance-level (person-level) features to provide comprehensive and discriminative patterns for recognizing both first- and third-person activities. On the one hand, the holistic scene-level features are extracted by a 3-D convolutional neural network, which is trained to mine shared and sample-unique semantics between video pairs, via two well-designed attention-based modules and a self-knowledge distillation (SKD) strategy. On the other hand, we further leverage the extracted holistic features to guide the learning of instance-level features in a disentangled fashion, which aims to discover both spatially conspicuous patterns and temporally varied, yet critical, cues. Experimental results on the PolyU CFT Daily dataset validate that our method achieves the state-of-the-art performance.

Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes

Partial label learning (PLL), a significant research area, addresses the challenge of annotating each sample with a candidate label set containing the true label when obtaining accurate labels is infeasible. However, existing PLL methods often rely on generic datasets like CIFAR, where annotators can readily differentiate candidate labels and are unlikely to confuse, making it less realistic for real-world partial label applications. In response, our research focuses on a rarely studied problem, PLL on fine-grained images with attributes. And we propose a novel framework called Shared to Learn, Distinct to Disambiguate (SoDisam). Within the candidate label set, the categories may exhibit numerous shared attribute features, posing a challenge in accurately distinguishing them. Rather than perceiving it as an impediment, we capitalize on these shared attributes as definitive sources of supervision. This insight guides us to learn attribute space visual representation to focus on the information from these shared attributes. Moreover, we introduce an attribute attention mechanism tailored to harness the remaining distinct attributes. This mechanism directs the originally holistic feature towards specific regions, capturing corresponding discriminative features. In addition, a dynamic disambiguation module is introduced, continuously adjusting the two aforementioned mechanisms and achieve the final disambiguation process. Extensive experiments demonstrate the effectiveness of our approach on fine-grained partial label datasets. The proposed SoDisam framework not only addresses the challenges associated with fine-grained partial label learning but also provides a more realistic representation of real-world partial label scenarios.

GAN-based data augmentation and pseudo-label refinement with holistic features for unsupervised domain adaptation person re-identification

Person re-identification (re-ID) by using an unsupervised domain adaptation (UDA) approach has drawn considerable attention in contemporary security research. Thus, UDA person re-ID usually employs a model learned from a labeled source domain, adjusted by pseudo-labels, for an unlabeled target domain. However, it still needs to overcome three main challenges: the significant distribution gap between the source and target domain data, the disregarding of important information during the learning process, and the accuracy of pseudo-labels generated by a clustering algorithm. To tackle these problems, we propose a novel method to improve UDA person re-ID performance by combining GAN-based data augmentation and unsupervised pseudo-label refinement with holistic features method for training on target domain, named DAPRH. In particular, we first use a generative adversarial network (GAN) method to generate style-transferred images with the target domain style to enrich the training set and the domain invariant mapping (DIM) technique to effectively mitigate the distribution gap between the source and target domains. Next, we also utilize information from partial regions along with the global feature as holistic features to ensure that all necessary information is obtained during the learning process. Finally, we propose a centroid-based pseudo-label refinement method using a soft target label (one-soft) instead of the originally fixed label (one-hot) to enhance the teacher-student architecture-based unsupervised learning process. Extensive experiments on three well-known datasets, Market-1501, DukeMTMC-reID, and MSMT17, demonstrate that DAPRH can significantly surpass the state-of-the-art performance of the UDA person re-ID.

A heterogeneous attention fusion mechanism for the cross-environment scene classification of the home service robot

There have been many methods to improve the capacity of scene classification of service robots. However, most of them are proposed from a technical standpoint but without reference to any cognitive principle of the brain, and furthermore, from design to evaluation, the particularity of the robot task is still not fully considered, such as cross-environment generalization, explicit semantic preservation and interpretation. Thus, the scene cognitive behavior of robots is far from humans, and their environmental adaptability is still poor. It is difficult to complete learning place concepts from discrete fragments and then continuously perceiving them with a limited view in unvisited spaces. Inspired by the recent findings from neuroscience, an attention-based global and object attribute fusion mechanism (AGOFM for short) constructed by three parts is proposed to overcome these deficiencies. In the global attribute part, a global feature extractor and a sequence context extractor are used to generate the holistic feature. The involved context integrates limited views to form an overall impression of a scene for guiding attention. In the object attribute part, a novel object vector is proposed. It simultaneously involves the detected object quantity, category and confidence information, which are all related to the vector index and high-level semantics. In the attention generation part, two sorted top-X characteristics deriving from the above two parts are fed into a fully connected (FC) network with batch normalization to generate effective attention. The attention weights are then applied to the batch normalized global and object vectors respectively, and subsequently, the two heterogeneous information are directly fused by another FC network to achieve scene classification. The policies for multi-learner fusion and frame rejection are also provided. Finally, a novel evaluation paradigm is proposed that the model is trained on a discrete prior dataset, and then the inference is tested on a traditional dataset and two robot view datasets. This simulates the cross-environment situation. Under such severe conditions, the results demonstrate that the proposed method outperforms several popular methods.

Learning Fine-Grained Information with Capsule-Wise Attention for Salient Object Detection

With the popularity of convolutional neural networks being used for salient object detection (SOD), the performance has been significantly improved. However, how to integrate crucial features for modeling salient objects needs further exploration. In this work, we propose an effective feature selection scheme to solve this task. Firstly, we provide a Simplified Atrous Spatial Pyramid Pooling (SASPP) module to lightweight the multi-scale features. Dealing with the SASSP features, we design a pixel-level local feature selection scheme named Multi-Scale Capsule-wise Attention (MSCA). It aggregates features from multi-scales by dynamic routing and helps the network to generate fine-grained prediction maps. In addition, we exploit holistic features by the Spatial-wise Attention and Channel-wise Attention (SA/CA) mechanisms, which adaptively extracts spatial or channel information. We also propose a Multi-crossed Layer Connections (MLC) structure in the upsampling stage, to fuse features from not only different levels but also different scales. The salient object prediction is performed in a coarse-to-fine manner. By conducting comprehensive experiments on five benchmark datasets, our method achieves the best performance when compared to existing state-of-the-art approaches.

“Travelling to Greek Neighborhoods with English”: Design and Implementation of a CLIL Program at a Primary School

Content and Language Integrated Learning (CLIL) is an innovative approach which attempts to comprise holistic features, focusing on the meaning and at the same time providing opportunities for purposeful language use (Dalton – Puffer, 2007). Based on the triptych language of learning, language for learning and language through learning- this program aims at creating innovative educational escape rooms, in order to adopt CLIL, to develop skills in the target language (English) and at the same time to emphasize context and meaning. The program -designed for 5th grade students of a Primary School in Northern Greece- was piloted for 5 months, giving them the opportunity to “travel to Greek neighborhoods” and enganging them in the subjects of geography, history and culture, using English, -with great enthusiasm. Various web2 tools, videos, games, websites were incorporated in the escape rooms to provide authentic material so as to enhance authentic communication in the English language and also to use different types of context so as to support language and content knowledge. The program was assessed and evaluated using alternative ways and the results indicated the positive effects of CLIL on the students’ skills in English (TL) along with the significantly developed familiarization with the content through a creative, enthusiastic, motivating setting for students promoting active involvement and participation.

Progressive normalizing flow with learnable spectrum transform for style transfer

Most current style transfer models are designed as encoder–decoder structures. Some encoding operations, such as downsampling and pooling, cause a loss of image details. If the encoder and decoder are not compatible, it can also introduce distortion. Reversible neural networks have demonstrated their superior power in lossless projection. However, since the inputs and outputs of neural flows are holistic features, merely the high-level features can be utilized for image generation through reverse inference. These high-level features emphasize the image style more, leading to the generated results easily losing content details and producing abstract colors. To address the above issues, we propose LSTFlow, the first progressive reversible neural network capable of feature decomposition. First, LSTFlow incorporates our proposed reversible Learnable Spectrum Transform (LST), which can dynamically decompose the feature into feature spectrum and recover them losslessly. LSTFlow can retain more details by enabling multi-level features to be fused in backward inference. Second, we propose a Progressive Flow Stylization Strategy (PFSS) to balance the model’s emphasis between content and style and enhance the color perception. Forward inference based PFSS is carried out progressively, while the backward inference focuses on progressive generation. To demonstrate the effectiveness of our proposed method, we conducted comparative experiments with seven other state-of-the-art algorithms. The stylized effects are evaluated in terms of visual effects and quantitative indicators. The experiments show that the lightest LSTFlow performs the best in SSIM, Color Entropy, Color Uniformity and FID indicators and outperforms state-of-the-art methods.

Deep Learning-Based Holistic Speaker Independent Visual Speech Recognition

From a broader perspective, the objective of Visual Speech Recognition (VSR) is to comprehend the speech spoken by an individual using visual deformations. However, some of the significant limitations of existing solutions include the dearth of training data, improper end-to-end deployed solutions, lack of holistic feature representation, and less accuracy. To resolve these limitations, this study proposes a novel, scalable, and robust VSR system that uses the videotape of the user to determine the word which is being spoken. In this regard, a customized 3-Dimensional Convolutional Neural Network (3D CNN) architecture is proposed by extracting the Spatio-temporal features and eventually mapping the prediction probabilities of the elements in the corpus. We have created a customized dataset resembling the metadata contained in the MIRACL-VC1 dataset to validate the concept of person-independence. While being robust to a broad spectrum of lighting conditions across multiple devices, our model achieves a training accuracy of 80.2% and a testing accuracy of 77.9% in predicting the word spoken by the user.

W poszukiwaniu „pierwszego”, wspólnotowego języka. Refleksje fizyka

In view of the rapid development of science, there is a need to search for a common language. The article points out the existence of potential lines of correspondence and interrelation between seemingly disparate fields, such as the humanities and the natural sciences. It is surprising that the holistic feature of Nature resonates most strongly in the language of quanta, the most prophetic that science has at its disposal.

What can go wrong with the medication adherence a patient suffers due to diabetes distress? A narrative review

Background: Type 2 Diabetes Mellitus (T2DM) is a major public health concern associated with distress. Distress is a rational emotional response to living with T2DM. Diabetes distress has been found to significantly affect the clinical outcome of T2DM. However, little is known regarding how distress may affect medication adherence. Objective: To investigate the relationship between distress and poor medication adherence in people with T2DM. Method: A literature search was conducted to identify relevant research articles published from 2014 to 2022 in three electronic databases (Scopus, PubMed, and SpringerLink) regarding “diabetes distress”, “T2DM management” and “medication adherence”. In addition, a search was also carried out using Google Scholar. Results: A total of seven articles were identified. Amongst these articles, three studies revolved around evaluating the effect of diabetes distress on blood glucose control. All articles mentioned the significant association between distress and poor medication adherence, leading to seemingly comprehensive findings regarding the impact of diabetes distress on T2DM patients. Conclusion: It is important for healthcare providers, particularly pharmacists, to understand the holistic feature of T2DM patients.

Novel Multi-Feature Fusion Facial Aesthetic Analysis Framework

Machine learning has been used in facial beauty prediction studies. However, the integrity of facial geometric information is not considered in facial aesthetic feature extraction, and the impact of other facial attributes (expression) on aesthetics. We propose a novel multi-feature fusion facial aesthetic analysis framework (NMFA) to overcome this problem. First, we designed a facial shape feature, which is an intuitive, visual quantitative description, based on B-spline. Second, we designed a representative low-dimensional facial structural feature to establish the theoretical basis of the facial structure, based on facial aesthetic structure and expression recognition theory. Next, we designed texture and holistic features based on Gabor and VGG-face network. Finally, we used a multi-feature fusion strategy to fuse them for aesthetic evaluation. Experiments were conducted on four databases. The results revealed that the proposed method realizes the visualization of facial shape features, enriches geometric information, solves the problem of lack of facial geometric information and difficulty to understand, and achieves excellent performance with fewer parameters.