Original Image Research Articles

Defending Deepfakes by Saliency-Aware Attack

With the rapid development of deep learning, especially the generative adversarial network (GAN), face modification has been substantially advanced and enables the generated images to look more realistic. Given an image or a video frame of a person, such a system can create fake images, which manipulates the movement, expression, and even appearance, e.g., hair color, eye color, and age. Such a system is termed Deepfake, which has raised significant ethical issues, especially for celebrities. With the pretrained Deepfake models being widely available on the Internet, its negative applications, such as face manipulation and pornographic generation, have exposed the dark side of the Deepfake technology to the sociocyber world. In this article, we aim to defend a well-trained Deepfake model by manipulating the raw image with unperceived perturbation. To minimize the alterations to the original image while effectively fooling the Deepfake model, we propose to selectively perturb only the foreground person region and maintain the irrelevant background. This is based on the observation that the salient object in a person’s image is always the foreground face region. Such a strategy introduces negligible alterations to the original image, which makes the attack remain effective. We experimentally demonstrate the superiority of the proposed attacking framework over the existing models and show our approach is ready to be applied for out-of-the-box development.

The spillover effect of Chinese sportswear brands' relationship quality: a perspective of Confucian yuanfen culture

PurposeChinese consumers' brand preferences are shifting from foreign sportswear brands to domestic ones. This indicates an increasingly strong relationship between Chinese consumers and domestic sportswear brands. The purpose of this study is to explore the spillover effect of Chinese domestic sportswear brands’ relationship quality to uncover the psychological mechanisms driving this preference shift.Design/methodology/approachThe study used a brand relationship quality scale based on Chinese Confucian yuanfen culture, considering it as a second-order reflective-formative construct. The survey generated 326 valid responses online. Due to the presence of second-order reflective-formative construct in the variables, SmartPLS 4.0 was used for hypothesis testing.FindingsInteraction belief, intimate interaction and happiness as formative dimensions of Confucian yuanfen brand relationship quality are validated, while emotional expression and tolerance are not. The Confucian yuanfen brand relationship quality has a spillover effect on product origin image and domestic sportswear brand preference. Product origin image has a mediating role between Confucian yuanfen brand relationship quality and domestic sportswear brand preference. However, consumer xenocentrism does not moderate the spillover effect of Confucian yuanfen brand relationship quality on domestic sportswear brand preference.Originality/valueThis study tests brand relationship quality from Confucian yuanfen perspective as a second-order reflective-formative construct. It contributes to understanding how Chinese consumers perceive their relationships with domestic sportswear brands. The results advance the current body of knowledge on brand relationship quality and spillover effect in sports marketing, indicating that Chinese sportswear brands can explore the possibility of co-opetition to achieve mutual benefits.

Image-Driven Harmonious Color Palette Generation for Diverse Information Visualization.

Color has been widely used to encode data in all types of visualizations. Effective color palettes contain discriminable and harmonious colors, which allow information from visualizations to be accurately and aesthetically conveyed. However, predefined color palettes not only lack the flexibility of custom color palette generation but also ignore the context in which the visualizations are used. Designing an effective color palette is a time-consuming and challenging process for users, even experts. In this work, we propose the generation of an image-based visualization color palette to exploit the human perception of visually appealing images while considering visualization cognition. By analyzing color palette constraints, including harmony, discrimination, and context, we propose an image-driven color generation method. We design a color clustering method in the saliency-hue plane based on visual importance detection and then select the palette based on the visualization color constraints. In addition, we design two color optimization and assignment strategies for visualizations of different data types. Evaluations through numeric indicators and user experiments demonstrate that the palettes predicted by our method are visually related to the original images and are aesthetically pleasing, supporting diverse visualization contexts and data types in practical applications.

Image Domain Multi-Material Decomposition Noise Suppression Through Basis Transformation and Selective Filtering.

Spectral CT can provide material characterization ability to offer more precise material information for diagnosis purposes. However, the material decomposition process generally leads to amplification of noise which significantly limits the utility of the material basis images. To mitigate such problem, an image domain noise suppression method was proposed in this work. The method performs basis transformation of the material basis images based on a singular value decomposition. The noise variances of the original spectral CT images were incorporated in the matrix to be decomposed to ensure that the transformed basis images are statistically uncorrelated. Due to the difference in noise amplitudes in the transformed basis images, a selective filtering method was proposed with the low-noise transformed basis image as guidance. The method was evaluated using both numerical simulation and real clinical dual-energy CT data. Results demonstrated that compared with existing methods, the proposed method performs better in preserving the spatial resolution and the soft tissue contrast while suppressing the image noise. The proposed method is also computationally efficient and can realize real-time noise suppression for clinical spectral CT images.

Pubertal status and body image: An inquiry into experiences of adolescents in Ghana and Kenya.

The current study uses a mixed method design to investigate Kenyan and Ghanaian adolescents' experiences of puberty, and the relations between gender, country of origin, pubertal status, and body image appraisals (N = 86; Ghana = 46, Kenya = 40, 52.9% female aged 13 and 14). Qualitative results revealed seven major themes; puberty means a universal period of growth and transition into adulthood but also evokes negative emotions of shame, anxiety, and embarrassment, being in sync with peers during puberty is important and knowing that others in their lives similarly experience puberty is reassuring. Quantitative results revealed significant gender and country differences in pubertal status and body image. Ghanaian adolescents had more advanced pubertal status and more positive body image appraisals compared to Kenyan adolescents. Moderation analysis results revealed that for the Kenyan sample, post-pubertal males had less favorable body image appraisals than their counterparts who were still pre pubertal whilst for females, post-pubertal girls had more favorable body images than their counterparts. No such effects were observed with the Ghanaian sample. The findings highlight the need for context considerations in understanding body image during the pubertal transition to help identify relevant protective factors for possible interventions. The results affirm the importance of positive body image promotions for adolescents within the African context and suggest the need for much more comprehensive sex education with gender-specific components to help allay fears about puberty, thus preventing the development of possible adaptation problems.

Enhancing the transferability of adversarial attacks with diversified input strategies

Abstract Adversarial examples are often used to test and evaluate the security and robustness of image classification models. Though adversarial attacks under white-box setting can achieve a high attack success rate, due to overfitting, the success rate of black-box attacks is relatively low. To this end, this paper proposes diversified input strategies to improve the transferability of adversarial examples. In this method, various transformation methods are applied to randomly transform the original image multiple times, thereby generating a batch of transformed images. Then, in the process of back-propagation, the loss function gradient of the transformed images is calculated, and a weighted average of the obtained gradient values is performed to generate adversarial perturbation, which is iteratively added to the original image to generate adversarial examples. Meanwhile, by increasing the variety of data augmentation transformation types and the number of input images, the proposed method effectively alleviates overfitting and improves the transferability of adversarial examples. Extensive experiments on the ImageNet dataset indicate that the proposed method can perform black-box attacks better than benchmark methods, with an average of 97.2% success rate attacking multiple models simultaneously.

The ringed residual u-net with non-natural regions feature for image splicing forgery detection and localization

Recently, with the emergence of many image editing tools (photoshop, Topaz studio, etc.), the authenticity of images has been severely challenged. However, the performance of some existing traditional feature extraction methods and detection methods based on convolutional neural network (CNN) is poor, and the information provided by the features extracted from the network is limited and single. In this paper, an end-to-end ringed residual U-Net is proposed to detect image splicing forgery by blending features of non-natural regions. Some regions with significant differences from the image background are defined as non-natural regions(such as the irregular border at the splicing of images). In this paper, a feature enhancement module for non-natural regions is constructed, which the image through the pooling of four different scales, and these features are then combined with the original image and input to the backbone network for processing, aiming to highlight regions of the image that differ significantly from the background. Therefore, after adding the feature enhancement module for non-natural regions to the end-to-end ring residual U-Net, more attention will be paid to the tampering regions in the feature extraction stage, image manipulation detection and localization will also become more accurate. Compared with some mainstream methods, this method achieves better performance on the three standard datasets(CASIA2.0, NIST2016, COLUMBIA). In addition, it has excellent robustness under JPEG compression attack and noise corruption attack.

The influence of perceived country of origin image on Chinese consumers’ purchase intention of imported wine

PurposeThis study aims to examine how consumers’ propensity to purchase imported wines is influenced by their attitudes and perceptions toward the countries of origin (COO) of those wines.Design/methodology/approachThe questionnaires were distributed online and 298 valid completed questionnaires were received. This study measured the perception of the wines’ countries of origin by adopting two independent dimensions of competence and warmth in the stereotype content model.FindingsThe results show a relationship between the purchase intention and the perception of the country of origin of the wine. Furthermore, the perceived image of the country of origin impacts the brand image of the wine and the quality of wine from its country of origin.Research limitations/implicationsThis study’s questionnaire was distributed online. Future research would benefit from in-depth qualitative investigation and a wider range of sample sizes across countries.Practical implicationsThe results of this study guide imported wine companies in product marketing design and advertising. By promoting the countries of origin of premium wines to target consumers, trust in the quality of imported wine can be improved, thereby increasing consumers’ purchase intention.Originality/valueThis study contributes to the understanding of consumer perception of the country of origin in the context of wine marketing. It provides valuable implications for wine companies’ marketing positioning and strategy, benefiting wine marketers, distributors and importers.

A Conformable Moments-Based Deep Learning System for Forged Handwriting Detection.

Detecting forged handwriting is important in a wide variety of machine learning applications, and it is challenging when the input images are degraded with noise and blur. This article presents a new model based on conformable moments (CMs) and deep ensemble neural networks (DENNs) for forged handwriting detection in noisy and blurry environments. Since CMs involve fractional calculus with the ability to model nonlinearities and geometrical moments as well as preserving spatial relationships between pixels, fine details in images are preserved. This motivates us to introduce a DENN classifier, which integrates stenographic kernels and spatial features to classify input images as normal (original, clean images), altered (handwriting changed through copy-paste and insertion operations), noisy (added noise to original image), blurred (added blur to original image), altered-noise (noise is added to the altered image), and altered-blurred (blur is added to the altered image). To evaluate our model, we use a newly introduced dataset, which comprises handwritten words altered at the character level, as well as several standard datasets, namely ACPR 2019, ICPR 2018-FDC, and the IMEI dataset. The first two of these datasets include handwriting samples that are altered at the character and word levels, and the third dataset comprises forged International Mobile Equipment Identity (IMEI) numbers. Experimental results demonstrate that the proposed method outperforms the existing methods in terms of classification rate.

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.

수입개방 확대에 따른 한국의 수입 와인에 대한 소비자 태도 변화에 관한 연구

As the wine import market is showing explosive growth as the number of wine lovers increases, research on consumers' perceptions and attitudes is not being actively conducted. Therefore, the survey was conducted with the purpose of finding out consumer attitudes toward imported wine. The research was conducted through surveys. The results of the study showed that the benefits perceived by consumers regarding imported wine had a positive effect on brand attitude and repurchase intention, and the moderating effect of country of origin image perception also had a positive effect. It is believed that the establishment of STP strategies for each level of wine-related consumers is required in line with the increasing demand for high-end wine and the improving level of expert knowledge about wine in the future.

Multimodal Visual-Semantic Representations Learning for Scene Text Recognition

Scene Text Recognition (STR), the critical step in OCR systems, has attracted much attention in computer vision. Recent research on modeling textual semantics with Language Model (LM) has witnessed remarkable progress. However, LM only optimizes the joint probability of the estimated characters generated from the Vision Model (VM) in a single language modality, ignoring the visual-semantic relations in different modalities. Thus, LM-based methods can hardly generalize well to some challenging conditions, in which the text has weak or multiple semantics, arbitrary shape, and so on. To migrate the above issue, in this paper, we propose Multimodal Visual-Semantic Representations Learning for Text Recognition Network (MVSTRN) to reason and combine the multimodal visual-semantic information for accurate Scene Text Recognition. Specifically, our MVSTRN builds a bridge between vision and language through its unified architecture and has the ability to reason visual semantics by guiding the network to reconstruct the original image from the latent text representation, breaking the structural gap between vision and language. Finally, the tailored multimodal Fusion (MMF) module is motivated to combine the multimodal visual and textual semantics from VM and LM to make the final predictions. Extensive experiments demonstrate our MVSTRN achieves state-of-the-art performance on several benchmarks.

Adaptive mask-based brain extraction method for head CT images.

Brain extraction is an important prerequisite for the automated diagnosis of intracranial lesions and determines, to a certain extent, the accuracy of subsequent lesion identification, localization, and segmentation. To address the problem that the current traditional image segmentation methods are fast in extraction but poor in robustness, while the Full Convolutional Neural Network (FCN) is robust and accurate but relatively slow in extraction, this paper proposes an adaptive mask-based brain extraction method, namely AMBBEM, to achieve brain extraction better. The method first uses threshold segmentation, median filtering, and closed operations for segmentation, generates a mask for the first time, then combines the ResNet50 model, region growing algorithm, and image properties analysis to further segment the mask, and finally complete brain extraction by multiplying the original image and the mask. The algorithm was tested on 22 test sets containing different lesions, and the results showed MPA = 0.9963, MIoU = 0.9924, and MBF = 0.9914, which were equivalent to the extraction effect of the Deeplabv3+ model. However, the method can complete brain extraction of approximately 6.16 head CT images in 1 second, much faster than Deeplabv3+, U-net, and SegNet models. In summary, this method can achieve accurate brain extraction from head CT images more quickly, creating good conditions for subsequent brain volume measurement and feature extraction of intracranial lesions.

Segmentation of Drusen in Retinal Images for the Detection of Diabetic Retinopathy

Diabetic retinopathy (DR) is a most complicated eye disease that affects people with diabetes for an extended period. If necessary treatment is not given at the right time, DR leads to a severe loss of vision without prior symptoms. Therefore, patients with diabetes are recommended to undergo continuous screening for early detection of DR. In this paper, we proposed an automated detection process to detect the lesion called Drusen in retinal images. Drusen is not related to DR. The presence of Drusen does not indicate the disease DR. Still, it is used to identify the severity level of diabetes for the patient and to avoid the misdetection rate with other bright lesions (both exudates and cotton wool spots). This method is based on the Background image approach and inverse segmentation to detect the area affected by Drusen in retinal images. Inverse segmentation is used to segment the healthy areas based on regular texture rather than varying the texture of unhealthy areas. The segmented healthy areas are compared with the original image for segmenting Drusen. The segmentation process involved 40 images from the STARE database, producing better results based on accuracy and processing time.

Independently Trained Multi-Scale Registration Network Based on Image Pyramid.

Image registration is a fundamental task in various applications of medical image analysis and plays a crucial role in auxiliary diagnosis, treatment, and surgical navigation. However, cardiac image registration is challenging due to the large non-rigid deformation of the heart and the complex anatomical structure. To address this challenge, this paper proposes an independently trained multi-scale registration network based on an image pyramid. By down-sampling the original input image multiple times, we can construct image pyramid pairs, and design a multi-scale registration network using image pyramid pairs of different resolutions as the training set. Using image pairs of different resolutions, train each registration network independently to extract image features from the image pairs at different resolutions. During the testing stage, the large deformation registration is decomposed into a multi-scale registration process. The deformation fields of different resolutions are fused by a step-by-step deformation method, thereby addressing the challenge of directly handling large deformations. Experiments were conducted on the open cardiac dataset ACDC (Automated Cardiac Diagnosis Challenge); the proposed method achieved an average Dice score of 0.828 in the experimental results. Through comparative experiments, it has been demonstrated that the proposed method effectively addressed the challenge of heart image registration and achieved superior registration results for cardiac images.

Classification of multi-feature fusion ultrasound images of breast tumor within category 4 using convolutional neural networks.

Breast tumor is a fatal threat to the health of women. Ultrasound (US) is a common and economical method for the diagnosis of breast cancer. Breast imaging reporting and data system (BI-RADS) category 4 has the highest false-positive value of about 30% among five categories. The classification task in BI-RADS category 4 is challenging and has not been fully studied. This work aimed to use convolutional neural networks (CNNs) for breast tumor classification using B-mode images in category 4 to overcome the dependence on operator and artifacts. Additionally, this work intends to take full advantage of morphological and textural features in breast tumor US images to improve classification accuracy. First, original US images coming directly from the hospital were cropped and resized. In 1385 B-mode US BI-RADS category 4 images, the biopsy eliminated 503 samples of benign tumor and left 882 of malignant. Then, K-means clustering algorithm and entropy of sliding windows of US images were conducted. Considering the diversity of different characteristic information of malignant and benign represented by original B-mode images, K-means clustering images and entropy images, they are fused in a three-channel form multi-feature fusion images dataset. The training, validation, and test sets are 969, 277, and 139. With transfer learning, 11 CNN models including DenseNet and ResNet were investigated. Finally, by comparing accuracy, precision, recall, F1-score, and area under curve (AUC) of the results, models which had better performance were selected. The normality of data was assessed by Shapiro-Wilk test. DeLong test and independent t-test were used to evaluate the significant difference of AUC and other values. False discovery rate was utilized to ultimately evaluate the advantages of CNN with highest evaluation metrics. In addition, the study of anti-log compression was conducted but no improvement has shown in CNNs classification results. With multi-feature fusion images, DenseNet121 has highest accuracy of 80.22±1.45% compared to other CNNs, precision of 77.97±2.89% and AUC of 0.82±0.01. Multi-feature fusion improved accuracy of DenseNet121 by 1.87% from classification of original B-mode images (p<0.05). The CNNs with multi-feature fusion show a good potential of reducing the false-positive rate within category 4. The work illustrated that CNNs and fusion images have the potential to reduce false-positive rate in breast tumor within US BI-RADS category 4, and make the diagnosis of category 4 breast tumors to be more accurate and precise.

Accelerating randomized image secret sharing with GPU: contrast enhancement and secure reconstruction using progressive and convolutional approaches

AbstractImage Secret Sharing (ISS) is a cryptographic technique used to distribute secret images among multiple users. However, current Visual Secret Sharing (VSS) schemes produce a halftone image with only 50% contrast when reconstructing the original image. To overcome this limitation, the Randomized Image Secret Sharing (RISS) scheme was introduced. RISS achieves a higher contrast of 70% when extracting the secret image but comes with a high computational cost. This research paper presents a novel approach called Graphics Processing Unit (GPU)-based Randomized Image Secret Sharing (GRISS), which utilizes data parallelism within the RISS pipeline. The proposed technique also incorporates an Autoencoder-based Single Image Super-Resolution (ASISR) to enhance the contrast of the recovered image. The performance of GRISS is evaluated against RISS, and the contrast of the ASISR images is compared to current benchmark models. The results demonstrate that GRISS outperforms state-of-the-art models in both efficiency and effectiveness.

Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition.

One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial Networks (GANs) can potentially create additional training images. However, these GAN-generated images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. In this paper, we propose a meta-learning framework to combine generated images with original images, so that the resulting "hybrid" training images improve one-shot learning. Specifically, the generic image generator is updated by a few training instances of novel classes, and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. Our experiments demonstrate consistent improvement over baselines on one-shot fine-grained image classification benchmarks. Furthermore, our analysis shows that the reinforced images have more diversity compared to the original and GAN-generated images.

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization.

Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. An AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object. Our method achieves a new state-of-the-art performance in weakly and semi-supervised semantic segmentation, on both the PASCAL VOC 2012 and MS COCO 2014 datasets. In weakly supervised object localization, it achieves a new state-of-the-art performance on the CUB-200-2011 and ImageNet-1K datasets.

AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?

Understanding model decision under novel test scenarios is central to the community. A common practice is evaluating models on labeled test sets. However, many real-world scenarios see unlabeled test data, rendering the common supervised evaluation protocols infeasible. In this paper, we investigate such an important but under-explored problem, named Automatic model Evaluation (AutoEval). Specifically, given a trained classifier, we aim to estimate its accuracy on various unlabeled test datasets. We construct a meta-dataset: a dataset comprised of datasets (sample sets) created from original images via various transformations such as rotation and background substitution. Correlation studies on the meta-dataset show that classifier accuracy exhibits a strong negative linear relationship with distribution shift (Pearson's Correlation ). This new finding inspires us to formulate AutoEval as a dataset-level regression problem. Specifically, we learn regression models (e.g., a regression neural network) to estimate classifier accuracy from overall feature statistics of a test set. In the experiment, we show that the meta-dataset contains sufficient and diverse sample sets, allowing us to train robust regression models and report reasonable and promising predictions of the classifier accuracy on various test sets. We also provide insights into application scopes, limitations, and potential future directions of AutoEval.