Search results
1 – 10 of over 11000This paper provides an introduction to research in the field of image forensics and asks whether advances in the field of algorithm development and digital forensics will…
Abstract
Purpose
This paper provides an introduction to research in the field of image forensics and asks whether advances in the field of algorithm development and digital forensics will facilitate the examination of images in the scientific publication process in the near future.
Design/methodology/approach
This study looks at the status quo of image analysis in the peer review process and evaluates selected articles from the field of Digital Image and Signal Processing that have addressed the discovery of copy-move, cut-paste and erase-fill manipulations.
Findings
The article focuses on forensic research and shows that, despite numerous efforts, there is still no applicable tool for the automated detection of image manipulation. Nonetheless, the status quo for examining images in scientific publications remains visual inspection and will likely remain so for the foreseeable future. This study summarizes aspects that make automated detection of image manipulation difficult from a forensic research perspective.
Research limitations/implications
Results of this study underscore the need for a conceptual reconsideration of the problems involving image manipulation with a view toward the need for interdisciplinary collaboration in conjunction with library and information science (LIS) expertise on information integrity.
Practical implications
This study not only identifies a number of conceptual challenges but also suggests areas of action that the scientific community can address in the future.
Originality/value
Image manipulation is often discussed in isolation as a technical challenge. This study takes a more holistic view of the topic and demonstrates the necessity for a multidisciplinary approach.
Details
Keywords
This chapter seeks to present a limited overview of some aspects of manipulated and/or fake images that contribute to society ‘becoming post-truth’. It subclassifies levels of…
Abstract
This chapter seeks to present a limited overview of some aspects of manipulated and/or fake images that contribute to society ‘becoming post-truth’. It subclassifies levels of manipulation and also presents the finding from a descriptive survey that gauges perceptions on awareness and recognisability of fake images. It also presents perceptions of effect on individuals of images modified for aesthetic reasons and carried by social media. The majority of respondents seemed affected by this, but with only a minority whose perception of self was affected. Another result of the survey is that there is a general mistrust of images not carried by gatekept sources.
Details
Keywords
Ambica Ghai, Pradeep Kumar and Samrat Gupta
Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered…
Abstract
Purpose
Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered with to influence public opinion. Since the consumers of online information (misinformation) tend to trust the content when the image(s) supplement the text, image manipulation software is increasingly being used to forge the images. To address the crucial problem of image manipulation, this study focusses on developing a deep-learning-based image forgery detection framework.
Design/methodology/approach
The proposed deep-learning-based framework aims to detect images forged using copy-move and splicing techniques. The image transformation technique aids the identification of relevant features for the network to train effectively. After that, the pre-trained customized convolutional neural network is used to train on the public benchmark datasets, and the performance is evaluated on the test dataset using various parameters.
Findings
The comparative analysis of image transformation techniques and experiments conducted on benchmark datasets from a variety of socio-cultural domains establishes the effectiveness and viability of the proposed framework. These findings affirm the potential applicability of proposed framework in real-time image forgery detection.
Research limitations/implications
This study bears implications for several important aspects of research on image forgery detection. First this research adds to recent discussion on feature extraction and learning for image forgery detection. While prior research on image forgery detection, hand-crafted the features, the proposed solution contributes to stream of literature that automatically learns the features and classify the images. Second, this research contributes to ongoing effort in curtailing the spread of misinformation using images. The extant literature on spread of misinformation has prominently focussed on textual data shared over social media platforms. The study addresses the call for greater emphasis on the development of robust image transformation techniques.
Practical implications
This study carries important practical implications for various domains such as forensic sciences, media and journalism where image data is increasingly being used to make inferences. The integration of image forgery detection tools can be helpful in determining the credibility of the article or post before it is shared over the Internet. The content shared over the Internet by the users has become an important component of news reporting. The framework proposed in this paper can be further extended and trained on more annotated real-world data so as to function as a tool for fact-checkers.
Social implications
In the current scenario wherein most of the image forgery detection studies attempt to assess whether the image is real or forged in an offline mode, it is crucial to identify any trending or potential forged image as early as possible. By learning from historical data, the proposed framework can aid in early prediction of forged images to detect the newly emerging forged images even before they occur. In summary, the proposed framework has a potential to mitigate physical spreading and psychological impact of forged images on social media.
Originality/value
This study focusses on copy-move and splicing techniques while integrating transfer learning concepts to classify forged images with high accuracy. The synergistic use of hitherto little explored image transformation techniques and customized convolutional neural network helps design a robust image forgery detection framework. Experiments and findings establish that the proposed framework accurately classifies forged images, thus mitigating the negative socio-cultural spread of misinformation.
Details
Keywords
Country of origin (COO) effect refers to the influence of COO on consumers' perception and evaluation of a product. This research explores the impact of consumers' power distance…
Abstract
Purpose
Country of origin (COO) effect refers to the influence of COO on consumers' perception and evaluation of a product. This research explores the impact of consumers' power distance on COO effect.
Design/methodology/approach
We conducted two experiments to test the relevant hypotheses.
Findings
The results indicate that power distance has a polarizing influence on COO effect. That means, for products from countries with good images, the higher the consumers' power distance, the better their evaluation of the products; while for products from countries with poor images, the higher the power distance, the worse their evaluation of the products. The research also finds the moderating effect of consumers' competence–related country-related affect (CRA). When holding positive competence–related CRA, for products from countries with good images, the higher the consumers' power distance, the better their evaluation of the products; for products from countries with poor images, consumers' power distance has no effect. When having negative competence–related CRA, for products from countries with poor images, the higher the consumers' power distance, the worse their evaluation of the products; for products from countries with good images, power distance has no effect.
Originality/value
This study finds that depending on the perception of COO image, power distance not only improves the evaluation of products but also lows such evaluation, reflecting a two-way polarizing feature.
Details
Keywords
Ying-Feng Kuo, Jian-Ren Hou and Yun-Hsi Hsieh
Netizens refer to citizens of the internet, and code-switching refers to the use of more than one language, style or form of expression to communicate. This study explores the…
Abstract
Purpose
Netizens refer to citizens of the internet, and code-switching refers to the use of more than one language, style or form of expression to communicate. This study explores the advertising communication effectiveness of using netizen language code-switching in Facebook ads. Moreover, if a brand is with negative brand images, using positive brand images as a control group, this study investigates not only the advertising communication effectiveness of netizen language code-switching but also its effectiveness of remedying the negative brand images.
Design/methodology/approach
Online experiments were conducted, and data were analyzed using independent sample t-test, MANOVA and ANOVA.
Findings
The results indicate that netizen language code-switching can enhance advertising communication effectiveness in Facebook ads. Furthermore, under a negative brand image, netizen language code-switching has significant effects on improving Facebook advertising communication effectiveness.
Originality/value
This study takes netizens as the research subjects to explore the advertising communication effectiveness of netizen language code-switching in Facebook ads. This study provides further insight into the effect of netizens' culture on Facebook advertising and enriches the existing literature on social media advertising, as well as expanding the application of code-switching. The results of this study provide enterprises a new perspective on the copywriting content design of Facebook ads.
Details
Keywords
This study aims to examine the visual effects of cause-related marketing (CM) posts on Instagram, with a focus on image resolution and consumer engagement.
Abstract
Purpose
This study aims to examine the visual effects of cause-related marketing (CM) posts on Instagram, with a focus on image resolution and consumer engagement.
Design/methodology/approach
Three studies were conducted through an experimental design. Study 1 (N = 155) uncovered the mediation underlying the effects of image quality (low and high image resolution). Study 2 (N = 160) replicated the findings of the first study and extended the investigation by examining the mediator (fluency) and moderator (visual sensitivity). Study 3 (N = 291) further extended the effects of image resolution by demonstrating its interactive effects with the visual complexity of an Instagram post design in a 2 × 2 factorial experiment.
Findings
The serial mediation analysis demonstrated that high image resolution CM posts yielded more favorable evaluations in terms of brand credibility and information costs saved, subsequently leading to positive brand attitudes, purchase intentions and increased Instagram engagement. Processing fluency mediated image effects on brand credibility, while individual differences in visual sensitivity moderated the image effects. The image resolution effects were greater for visually complex CM posts compared to simple ones.
Originality/value
To one's best knowledge, little to no research has examined the image quality of Instagram posts in the context of CM and the extent to which such visual cues can affect consumers' brand evaluations and engagement on the platform.
Research implications
Despite its practical significance, there exists a notable gap in understanding the specific role of CM posts on Instagram and the impact of visual elements on consumer behaviors. The current research findings aim to bridge the research gap.
Details
Keywords
This paper seeks to report on the study that proposed a model of image retrieval tasks for creative multimedia. The aim of this model was to understand the purpose of the tasks…
Abstract
Purpose
This paper seeks to report on the study that proposed a model of image retrieval tasks for creative multimedia. The aim of this model was to understand the purpose of the tasks, intended use of the images, mode of query submission, nature of the keywords given by the users, and relevance criteria.
Design/methodology/approach
A survey was done to compile a total of 35 image retrieval tasks from 35 academic staff members at Faculty of ICT, International Islamic University Malaysia, and Faculty of Creative Multimedia, Malaysia. A search using Google Image Search category was carried out to find images on the web that met the intended use of the academic staff members.
Findings
Findings revealed that images were mostly intended for analysis, decorations, design, illustrations, image processing, and inspiration. Users preferred linguistic query mode, and visual query mode if they had a sample of the image. Most users requested images with captions for making the relevance judgment. Technical attributes, topicality, and completeness were the most important relevance criteria. Users' keywords were of abstract and concrete elements, and were expressed in a visual way and as a subject. Images decided as relevant ranged from an object in the image to the whole image. This model reflected similar findings to other studies with some variations.
Practical implications
Results are useful for understanding the nature of image retrieval tasks for the area of creative multimedia.
Originality/value
This paper developed a model of image retrieval tasks in the area of creative multimedia, and offers a value in understanding the tasks that are intended to meet the demand of the Creative Multimedia Industry established in Malaysia.
Details
Keywords
Ziyan Guo, Xuhao Liu, Zehua Pan, Yexin Zhou, Zheng Zhong and Zilin Yan
In recent years, the convolutional neural network (CNN) based deep learning approach has succeeded in data-mining the relationship between microstructures and macroscopic…
Abstract
Purpose
In recent years, the convolutional neural network (CNN) based deep learning approach has succeeded in data-mining the relationship between microstructures and macroscopic properties of materials. However, such CNN models usually rely heavily on a large set of labeled images to ensure the accuracy and generalization ability of the predictive models. Unfortunately, in many fields, acquiring image data is expensive and inconvenient. This study aims to propose a data augmentation technique to enhance the performance of the CNN models for linking microstructural images to the macroscopic properties of composites.
Design/methodology/approach
Microstructures of composites are synthesized using discrete element simulations and Potts kinetic Monte Carlo simulations. Macroscopic properties such as the elastic modulus, Poisson's ratio, shear modulus, coefficient of thermal expansion, and triple-phase boundary length density are extracted on representative volume elements. The CNN model is trained using the 3D microstructural images as inputs and corresponding macroscopic properties as the labels. The comparison of the predictive performance of the CNN models with and without data augmentation treatment are compared.
Findings
The comparison between the prediction performance of CNN models with and without data augmentation showed that the former reduced the weighted mean absolute percentage error (WMAPE) for the prediction from 5.1627% to 1.7014%. This significant reduction signifies that the proposed data augmentation method can effectively enhance the generalization ability and robustness of CNN models.
Originality/value
This study demonstrates that data augmentation is beneficial for solving the problems of model overfitting, data scarcity, and sample imbalance for CNN-based deep learning tasks at a low cost. By developing more and advanced data augmentation techniques, deep learning accelerated homogenization will boost the multi-scale computational mechanics and materials.
Details
Keywords
Paul F. Whelan and Robert Sadleir
This paper details a free image analysis and software development environment for machine vision application development. The environment provides high‐level access to over 300…
Abstract
This paper details a free image analysis and software development environment for machine vision application development. The environment provides high‐level access to over 300 image manipulation, processing and analysis algorithms through a well‐defined and easy to use graphical interface. Users can extend the core library using the developer's interface via a plug‐in which features automatic source code generation, compilation with full error feedback and dynamic algorithm updates. Also discusses key issues associated with the environment and outline the advantages in adopting such a system for machine vision application development.
Details
Keywords
Alena Kostyk and Bruce A. Huhmann
Two studies investigate how different structural properties of images – symmetry (vertical and horizontal) and image contrast – affect social media marketing outcomes of consumer…
Abstract
Purpose
Two studies investigate how different structural properties of images – symmetry (vertical and horizontal) and image contrast – affect social media marketing outcomes of consumer liking and engagement.
Design/methodology/approach
In Study 1’s experiment, 361 participants responded to social media marketing images that varied in vertical or horizontal symmetry and level of image contrast. Study 2 analyzes field data on 610 Instagram posts.
Findings
Study 1 demonstrates that vertical or horizontal symmetry and high image contrast increase consumer liking of social media marketing images, and that processing fluency and aesthetic response mediate these relationships. Study 2 reveals that symmetry and high image contrast improve consumer engagement on social media (number of “likes” and comments).
Research limitations/implications
These studies extend theory regarding processing fluency’s and aesthetic response’s roles in consumer outcomes within social media marketing. Image posts’ structural properties affect processing fluency and aesthetic response without altering brand information or advertising content.
Practical implications
Because consumer liking of marketing communications (e.g. social media posts) predicts persuasion and sales, results should help marketers design more effective posts and achieve brand-building and behavioral objectives. Based on the results, marketers are urged to consider the processing fluency and aesthetic response associated with any image developed for social media marketing.
Originality/value
Addressing the lack of empirical investigations in the existing literature, the reported studies demonstrate that effects of symmetry and image contrast in generating liking are driven by processing fluency and aesthetic response. Additionally, these studies establish novel effects of images’ structural properties on consumer engagement with brand-based social media marketing communications.
Details