Images Of Artworks Research Articles

Digital technology integration innovation and visual symbol design of Huizhou ink painting skills under bioengineering

In response to the problems of insufficient interactive experience and unstable inheritance caused by information loss and deformation in the teaching process of Huizhou ink painting skills, this article explores a new method to protect and inherit Huizhou ink painting skills through the integration of biotechnology and digital technology. At the same time, a modern visual symbol design is developed to revitalize this ancient art form in contemporary society and promote its dissemination and exchange worldwide. Firstly, traditional Huizhou ink painting materials were analyzed using biotechnology to understand their composition, structure, and aging mechanism. Scientific and effective protective measures were proposed, and a database was constructed by collecting and matching images of each step in the process. Then use 3D modeling to model the manufacturing tools. By extracting visual elements from micro ink artwork images, drawing basic graphics, and completing visual symbol design. Finally, integrate Unity and Vuforia Engine to design an interactive experience module for Weizhou ink painting production skills, creating an immersive digital interactive environment. In the improved micro ink production process experience display experiment, compared with the existing graphic and textual display methods, the audience's satisfaction and innovation scores for the digital integration method were 19.1% and 21.6% higher, respectively. The conclusion indicates that bioengineering analysis can accurately identify and delay the aging process of ink painting materials, while digital technology has successfully achieved high-quality digital reconstruction of classic works.

Style recommendation and simulation for handmade artworks using generative adversarial networks

Today, artificial intelligence (AI) is used in the design and production of artworks as a powerful tool that helps artists and designers to create more creative and attractive artworks. AI as a new tool has created new opportunities to create and improve artworks. Therefore, in this study, a new model for recommending and simulating the style of handmade artworks using generative adversarial networks (GANs) is presented. This model operates in two distinct phases: style recommendation and style simulation. The reason for using these two separate phases is to increase the accuracy and efficiency of the model. In the first phase, a pre-trained GAN is used to suggest different styles to the artist. In the second phase, a new GAN specifically designed to produce realistic images of handmade artwork is used to simulate the artist’s selected style. Also, in order to improve the accuracy, the genetic algorithm (GA) was used to adjust the activity configuration of Self-Attention (SA) modules. The results of a case study on two types of data, including samples without and with the initial background pattern, GA-SAGAN model has been able to significantly reduce the validation error. As a result, adjusting the activity configuration of SA modules using GA can be effective in producing realistic and accurate artworks. The outputs produced by the GA-SAGAN model have a loss rate close to zero. Also, the Entropy values and Precision and Recall indices are higher than GAN and SAGAN models, it shows the higher diversity of production output patterns and the superiority of the proposed model.

TOLGAN: An End-To-End Framework for Producing Traditional Orient Landscape

We present TOLGAN that generates traditional oriental landscape (TOL) image from a map that specifies the locations and shapes of the elements composing TOL. Users can create a TOL map by using a user interface or a segmentation scheme from a photograph. We design the generator of TOLGAN as a series of decoding layers where the map is applied between the layers. The generated TOL image is further enhanced through an AdaIN architecture. The discriminator of TOLGAN processes a generated image and its groundtruth TOL artwork image. TOLGAN is trained through a dataset composed of paired TOL artwork images and their TOL maps. We present a tool through which users can produce a TOL map by specifying and organizing the elements of TOL artworks. TOLGAN successfully generates a series of TOL images from the TOL map. We evaluate our approach using a quantitative way by estimating FID and ArtFID scores and a qualitative way by executing two user studies. Through these studies, we prove the excellence of our approach by comparing our results with those from several important existing works.

A Chaos-Based Encryption Algorithm to Protect the Security of Digital Artwork Images

Due to the security weaknesses of chaos-based pseudorandom number generators, in this paper, a new pseudorandom number generator (PRNG) based on mixing three-dimensional variables of a cat chaotic map is proposed. A uniformly distributed chaotic sequence by a logistic map is used in the mixing step. Both statistical tests and a security analysis indicate that our PRNG has good randomness and is more complex than any one-dimensional variable of a cat map. Furthermore, a new image encryption algorithm based on the chaotic PRNG is provided to protect the content of artwork images. The core of the algorithm is to use the sequence generated by the pseudorandom number generator to achieve the process of disruption and diffusion of the image pixels, so as to achieve the effect of obfuscation and encryption of the image content. Several security tests demonstrate that this image encryption algorithm has a high security level.

Teaching Visual Arts Using Virtual Exhibitions: An Investigation of Student Usage and Impact on Learning

Amid the imperative call for using digital artwork images and e-learning activities in planning and delivering the art curriculum heightened by rapid technological development and COVID-19, we propose a visual arts teacher–curator pedagogy and investigate its effectiveness in Hong Kong’s primary and secondary schools. The pedagogy is set out to empower visual arts teachers to assume the role of “digital museum curators” and to facilitate student learning using virtual exhibitions. Design-based research was the methodology adopted for the study. Six teachers and 331 students participated in the study in the 2021–2022 academic year. The study, which examined the effectiveness of the proposed pedagogy, revealed a substantial improvement in student learning, including (1) motivating students toward self-directed and active learning, (2) stimulating artmaking ideas and skills, and (3) enhancing students’ confidence through peer learning.

ArtProtect: Blockchain and NFC‐based anti‐counterfeit system for physical art

AbstractCounterfeit artwork presents a significant risk to copyright holders and the economy. Without expertise in art, it is not straightforward to distinguish an artwork counterfeit from a genuine piece. This work designs and implements a reliable solution that enables users with near‐field communication‐enabled Android smartphones to verify artwork authenticity by accessing its respective certificate of authenticity stored in the Ethereum blockchain. To represent a physical artwork, the artwork image and metadata are stored in an inter‐planetary file system and minted as an ERC721 non‐fungible token to a smart contract deployed in Ethereum Rinkeby Testnet. The mobile app ArtProtect was developed to generate certificate of authenticity based on each non‐fungible token fetched through OpenSea Testnet API. Users access this information by scanning an near‐field communication tag embedded into the artwork. The content of the tag is signed by the respective artwork's artist and responsible agent by using Ethereum signing with their Ethereum wallet accounts. Through testing and analysis, the implemented work is secure, tamper‐evident, usable, flexible, and inexpensive to be applied to a real‐world scenario.

Examining the gray cube effect on naïve viewers’ appreciation of street-based art in Hong Kong and Poland

The present research investigates the appreciation of sanctioned street-based art among naïve viewers. It examines the role of viewing context in art appreciation, by experimentally testing a gray cube effect, which posits that street-based artworks are more likely to be identified as art (H1), liked more (H2), and understood more (H3) when viewed on the street. Identical procedures were carried out in Hong Kong (Experiment 1) and Lublin, Poland (Experiment 2), separately, sampling local artworks and local viewers. Experiment 1 tested 14 murals with 100 Hong Kongers; Experiment 2 tested 7 sculptures and 7 murals with 88 Poles. Participants were randomly assigned to either viewing street-based artworks on the street (gray cube) or viewing digital images of street-based artworks in a laboratory. The participants assessed each artwork in terms of art identification, liking, and understanding. These “twin” experiments yielded identical results, i.e., street-based artworks were liked more (H2) and understood more (H3) but not more likely to be identified as art (H1) on the street than in the laboratory. Overall, the present findings support the gray cube effect with ecologically valid data, and the effect seems robust across Western and Eastern cultural contexts and across genres of sculpture and mural.

Images, Words, and Imagination: Accessible Descriptions to Support Blind and Low Vision Art Exploration and Engagement.

The lack of accessible information conveyed by descriptions of art images presents significant barriers for people with blindness and low vision (BLV) to engage with visual artwork. Most museums are not able to easily provide accessible image descriptions for BLV visitors to build a mental representation of artwork due to vastness of collections, limitations of curator training, and current measures for what constitutes effective automated captions. This paper reports on the results of two studies investigating the types of information that should be included to provide high-quality accessible artwork descriptions based on input from BLV description evaluators. We report on: (1) a qualitative study asking BLV participants for their preferences for layered description characteristics; and (2) an evaluation of several current models for image captioning as applied to an artwork image dataset. We then provide recommendations for researchers working on accessible image captioning and museum engagement applications through a focus on spatial information access strategies.

Controllable multi-domain semantic artwork synthesis

We present a novel framework for the multi-domain synthesis of artworks from semantic layouts. One of the main limitations of this challenging task is the lack of publicly available segmentation datasets for art synthesis. To address this problem, we propose a dataset called ArtSem that contains 40,000 images of artwork from four different domains, with their corresponding semantic label maps. We first extracted semantic maps from landscape photography and used a conditional generative adversarial network (GAN)-based approach for generating high-quality artwork from semantic maps without requiring paired training data. Furthermore, we propose an artwork-synthesis model using domain-dependent variational encoders for high-quality multi-domain synthesis. Subsequently, the model was improved and complemented with a simple but effective normalization method based on jointly normalizing semantics and style, which we call spatially style-adaptive normalization (SSTAN). Compared to the previous methods, which only take semantic layout as the input, our model jointly learns style and semantic information representation, improving the generation quality of artistic images. These results indicate that our model learned to separate the domains in the latent space. Thus, we can perform fine-grained control of the synthesized artwork by identifying hyperplanes that separate the different domains. Moreover, by combining the proposed dataset and approach, we generated user-controllable artworks of higher quality than that of existing approaches, as corroborated by quantitative metrics and a user study.

Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.

This study aimed to develop image-analysis-based classification models for distinguishing individuals younger and older than 30 using the medial clavicle. We extracted 2D images of the medial clavicle from multi-slice computed tomography (MSCT) scans from Clinical Hospital Center Split (n = 204). A sample was divided into a training (164 images) and testing (40 images) dataset. The images were loaded into the Orange Data Mining 3.32.0., and transformed into vectors using the pre-trained neural network Painters: A model trained to predict painters from artwork images. We conducted Principal Components Analysis (PCA) to visualize regularities within data and reduce data dimensionality in classification. We employed three classifiers that provided >80% accuracy: Support Vector Machine (SVM), Logistic Regression (LR), and Neutral Network Identity SGD (NNI-SGD). We used 5-fold cross-validation (CV) to obtain optimal variables and performances and validated data on the independent test set, with a standard posterior probabilities (pp) threshold of 0.5 and 0.95. The explainability of the model was accessed visually by analyzing clusters and incorrectly classified images using anthropology field knowledge. Based on the PCA, clavicles clustered into categories under 30 and 40 years, between 40 and 55 years, and over 80 years. The overall accuracy with standard pp ranged from 82.5% to 92.5% for CV and 82.5% to 92.5% for the test set. The posterior probability of 0.95 provided classification accuracy up to 100% but with a lower proportion of images that could be classified. The study showed that image analysis based on a pre-trained deep neural network could contribute to distinguishing clavicles of individuals younger and older than 30.

Interpreting Geometric Constructions in Artworks through Capsule Network Modeling

Abstract Interpreting the geometric structure of artworks enhances our intuitive grasp of their deeper meanings. This study employs a Capsule network model, incorporating a dynamic routing algorithm to correlate high and low-level geometric structural features of artworks. Additionally, an attention mechanism is introduced, forming a spatial attention capsule to capture the spatial context of the artwork’s geometric structure. To obtain images, a fixed-focus camera is utilized, followed by median filtering for image preprocessing and threshold segmentation using the maximum inter-class variance method to optimize recognition accuracy. The efficacy of the geometric structure recognition model, grounded in the Capsule network, is confirmed using a dataset of collected artwork images. The model achieves stability after 380 epochs, exhibiting an impressive accuracy of approximately 99.7% and a minimal loss of 0.025. Removing the attention mechanism results in a 4.06 percentage point decrease in model accuracy, whereas incorporating a dynamic routing algorithm boosts efficiency by 7.36%. Thus, the Capsule model proves highly effective in precisely recognizing and interpreting the geometric structures of artworks.

Dual attention and channel transformer based generative adversarial network for restoration of the damaged artwork

Artworks are treasures of valuable cultural and historical heritage. Artworks get damaged due to environmental and other factors. The artificial intelligence-based restoration of digitized artwork images can guide the artists in physically restoring the damaged artworks. Previous methods have not been able to restore artwork images well. This paper proposes a dual (spatial and channel) attention and channel transformer-based generative adversarial network to restore damaged artwork images digitally. The proposed generative adversarial network has spatial and channel attention layers in the encoder part of the generator and a channel transformer between skip connections from the encoder to the decoder part of the generator. Spatial and channel attention helps learn inter-spatial and inter-channel global relationships among image features. Channel transformer ensures multiscale feature fusion and reduces the semantic gap between encoder and decoder layer features. Moreover, the proposed network has been trained using a linear combination of perceptual, adversarial, and structured similarity index measure loss, which helps better train the network. Further, the proposed network has been validated on two different datasets, and the results indicate that the proposed method outperforms state-of-the-art artwork restoration methods.

Review

Art can be particularly an effective means of building transnational understanding across cultural divides. Specifically, the act of making art to express conflict, sexuality and identity is significant as Arab women have frequently been marginalised and excluded from such a site of visibility and meaning. Contemporary Arab women artists not only contribute to global feminist theory but also deal with their aesthetic, visual and personal concerns. The Body in Twilight: Representation of the Human Body, Sexuality and Struggle in Contemporary Arab Art is a book by the Syrian professor of visual art and design Fassih Keiso. In this book, Keiso explores the representation of the human body in contemporary Arab art and its relationship to issues of sexuality and struggle. He argues that the representation of the body in Arab art reflects broader societal changes and struggles and that the use of the body as a site of resistance and political commentary is a common theme in contemporary Arab art. Despite the lack of images of artworks by the artists discussed in this book, the book provides a compelling contribution to comparative gender and feminist art and the broader international art on the centrality of sexuality in politics and society.

Research on the development strategy of art industry based on RNN model

Abstract In this paper, we firstly propose an art style classification system based on the RNN model to study the development of the art industry, and continuously fine-tune this white noise image according to the long and short-term memory network and gated recurrent unit network until it makes this white noise image similar to the artwork image style, and the ink painting image feature extraction is mainly studied from the recurrent neural network based ink style feature extraction and the overall nested edge based The two aspects of brushstroke feature extraction based on overall nested edge detection are studied. Then, based on the art industry and big data, the ink painting style classification system is constructed, and the effectiveness of the system is verified by model art classification effect analysis. The results show that the RNN performs well on the face dataset, where the accuracy of multiple classifications up to 10 categories is above 85%. This indicates that the RNN model in this paper can maintain good performance in the ink painting art classification task.

Building an Online Licensing Platform for Digital Images of Artwork

Digital artwork can facilitate the spread of culture while preserving and sustaining its value. However, digital image transactions are trapped in the traditional trading modes. As digital technology and the Internet of Things progressed, society moved into the information age. Thus, our conceptualization of private intellectual property rights evolved, allowing for the removal of artificial barriers between rights owners and consumers. This study bridges this gap by developing an individually-tailored authorized trading platform for digital artwork. First, we use copyrights underlying digital artwork licensing as a lens to examine new copyright licensing model challenges and the use of value-added applications in the modern digital environment. Second, we analyze foreign digital artwork trading platforms to better understand the functions of a digital artwork image licensing platform. By using the questionnaire to determine what functions digital artwork platforms should include, we can shift the object of investigation to the artists themselves.

Teachers Curating Virtual Exhibitions for Learning Visual Arts: A Study of Impact and Effectiveness

AbstractAlthough visual arts teachers have free access to high quality online artwork images offering them immense teaching resources, making meaningful use of them remains a pedagogical challenge. During the COVID‐19 pandemic, the transition from face‐to‐face to online teaching caused an immediate need for teachers to enhance their digital competencies and technological capability for planning and delivering a blended art curriculum. Herein, I propose a ‘teacher‐curator pedagogy’ via a study in six primary and secondary schools in Hong Kong to assess its effectiveness. The study took place in the academic year of 2021‐22 with 331 student participants. The proposed pedagogy puts visual arts teachers in the role of ‘digital curators’ who create virtual exhibitions for teaching art appreciation and artmaking. This paper addresses the theoretical framework, implementation strategies, and the results of the study highlighting its effectiveness, impact and limitations on teaching when using teacher‐curated virtual exhibitions in both physical and virtual learning contexts. It was found that the technological capacity and confidence of the teacher participants was enhanced through the use of online resources and virtual exhibition tools. Making use of the 3D presentation of exhibits in themes and context through digital content curation, the teachers engaged students with deep interaction through the blending of online and face‐to‐face teaching. However, the proposed pedagogy was limited by the high demand of training and preparation work, hardware and software support, and difficulties in assessing and monitoring learning beyond class.

Toward cross‐domain object detection in artwork images using improved YoloV5 and XGBoosting

AbstractObject recognition in natural images has achieved great success, while recognizing objects in style‐images, such as artworks and watercolor images, has not yet achieved great progress. Here, this problem is addressed using cross‐domain object detection in style‐images, clipart, watercolor, and comic images. In particular, a cross‐domain object detection model is proposed using YoloV5 and eXtreme Gradient Boosting (XGBoosting). As detecting difficult instances in cross domain images is a challenging task, XGBoosting is incorporated in this workflow to enhance learning of the proposed model for application on hard‐to‐detect samples. Several ablation studies are carried out by training and evaluating this model on the StyleObject7K, ClipArt1K, Watercolor2K, and Comic2K datasets. It is empirically established that this proposed model works better than other methods for the above‐mentioned datasets.

Container

Ten images of artworks created using found photographs are shown as a means of containing the stories of their clients and therapist. In these pieces, the author uses a photocopy from a Google search, broken jewellery and a canvas in a multimedia art style. The photocopy is used to create the shape of a boundary on the canvas and the broken jewellery is used to organize the trauma of the client.

The Personality Predictors of Art Preferences in Children

Art has been considered as a means of enriching oneself with values, transferring socio-cultural experience and traditions. Children articulate their wonder and excitement while engaging with an artwork and it is evident through their spontaneous responses. Aesthetic experience is regarded as fundamental to human existence. Experiencing and enjoying artworks help children to encounter diversities and prepare them for a facing challenge in life. The objective of the present quantitative study is to explore the relation between personality traits and art appreciation of children. The sample constituted sixty children of grade IX from the state of Telangana. The number of boys and girls participated in the study from rural and urban backgrounds are equal and children are in the age group of 13-15 years. Children’s artistic preferences are measured by showing 48 images of artworks of two dimensions: ‘abstractedness’ and ‘complexity’. The ‘abstractedness’ dimension include representational/realistic, semi-representational and highly abstract artworks and the ‘complexity’ dimension encompass low complexity, medium complexity, and high complexity artworks. Each group has four types of paintings: landscape, portrait, still life and animal representations. The results of analysis of the relation between children’s personality traits and their art preferences using Pearson product-moment correlation coefficient (r) reveals that Agreeableness and Conscientiousness is moderately positively correlated with the perceived attractiveness of abstract paintings which is statistically significant. The results do not show any statistically significant correlation between Openness to Experience and perceived attractiveness for abstract artworks. Further, there exists a low negative correlation between Neuroticism and perceived attractiveness for abstract artworks which is statistically significant. There are no significant correlations between children’s personality traits and perceived attractiveness for Realistic, High Complexity and Low Complexity artworks. The research findings are an indication for teachers to better design their classroom activities for enriching the lives of children.

A Method for Style Transfer from Artistic Images Based on Depth Extraction Generative Adversarial Network

Depth extraction generative adversarial network (DE-GAN) is designed for artistic work style transfer. Traditional style transfer models focus on extracting texture features and color features from style images through an autoencoding network by mixing texture features and color features using high-dimensional coding. In the aesthetics of artworks, the color, texture, shape, and spatial features of the artistic object together constitute the artistic style of the work. In this paper, we propose a multi-feature extractor to extract color features, texture features, depth features, and shape masks from style images with U-net, multi-factor extractor, fast Fourier transform, and MiDas depth estimation network. At the same time, a self-encoder structure is used as the content extraction network core to generate a network that shares style parameters with the feature extraction network and finally realizes the generation of artwork images in three-dimensional artistic styles. The experimental analysis shows that compared with other advanced methods, DE-GAN-generated images have higher subjective image quality, and the generated style pictures are more consistent with the aesthetic characteristics of real works of art. The quantitative data analysis shows that images generated using the DE-GAN method have better performance in terms of structural features, image distortion, image clarity, and texture details.