Search Results (54)

Background/Objectives: Identification of human remains is of utmost importance for criminal investigations and providing closure to the families. The reconstruction of a biological profile of the individual will narrow down the list of candidates for identification. From another perspective, facial approximations performed by a forensic artist can provide investigative leads, with the identity being confirmed by primary or secondary methods of identification. In recent years, DNA analysis has evolved, trying to create a portrait of the perpetrator/victim based on External Visible Characteristics (EVCs), the color of the eyes, hair, and skin and Biogeographical ancestry (BGA), called DNA phenotyping. Despite these advances, currently, there are no studies integrating the biological profile performed by forensic anthropologists, the facial approximation created by forensic artists and EVCs determined by DNA. The goal of this work was to integrate these three investigative leads to enhance the possibility of human identification. Methods: Five donated remains from Mercyhurst were studied through these approaches: reconstruction of biological profile, facial approximation and estimation of EVCs based on previous studies. Results: Our results indicated the feasibility of integrating this biological profile and EVCs data into the facial approximation developed by the forensic artist, aiming to an enhance portrait of the remains. In a second phase of this project, the accuracy of the integrated facial approximation will be assessed. Conclusions: This study pointed out the importance of an interdisciplinary approach towards the identification of human remains, as well as the combination of current methods with new technologies. Full article

Nowadays, portrait drawing has become increasingly popular as a means of developing artistic skills and nurturing emotional expression. However, it is challenging for novices to start learning it, as they usually lack a solid grasp of proportions and structural foundations of the five senses. To address this problem, we have studied Portrait Drawing Learning Assistant System (PDLAS) for guiding novices by providing auxiliary lines of facial features, generated by utilizing OpenPose and OpenCV libraries. For PDLAS, we have also presented the exactness assessment method to evaluate drawing accuracy using the Normalized Cross-Correlation (NCC) algorithm. It calculates the similarity score between the drawing result and the initial portrait photo. Unfortunately, the current method does not assess the hair drawing, although it occupies a large part of a portrait and often determines its quality. In this paper, we present a hair drawing evaluation algorithm for the exactness assessment method to offer comprehensive feedback to users in PDLAS. To emphasize hair lines, this algorithm extracts the texture of the hair region by computing the eigenvalues and eigenvectors of the hair image. For evaluations, we applied the proposal to drawing results by seven students from Okayama University, Japan and confirmed the validity. In addition, we observed the NCC score improvement in PDLAS by modifying the face parts with low similarity scores from the exactness assessment method. Full article

Facial Expression Recognition (FER) has been widely explored in realistic settings; however, its application to artistic portraiture presents unique challenges due to the stylistic interpretations of artists and the complex interplay of emotions conveyed by both the artist and the subject. This study addresses these challenges through three key contributions. First, we introduce the PortraitEmotion3D (PE3D) dataset, designed explicitly for FER tasks in artistic portraits. This dataset provides a robust foundation for advancing emotion recognition in visual art. Second, we propose an innovative 3D emotion estimation method that leverages three-dimensional labeling to capture the nuanced emotional spectrum depicted in artistic works. This approach surpasses traditional two-dimensional methods by enabling a more comprehensive understanding of the subtle and layered emotions often in artistic representations. Third, we enhance the feature learning phase by integrating a self-attention module, significantly improving facial feature representation and emotion recognition accuracy in artistic portraits. This advancement addresses this domain’s stylistic variations and complexity, setting a new benchmark for FER in artistic works. Evaluation of the PE3D dataset demonstrates our method’s high accuracy and robustness compared to existing state-of-the-art FER techniques. The integration of our module yields an average accuracy improvement of over 1% in recent FER systems. Additionally, combining our method with ESR-9 achieves a comparable accuracy of 88.3% on the FER+ dataset, demonstrating its generalizability to other FER benchmarks. This research deepens our understanding of emotional expression in art and facilitates potential applications in diverse fields, including human–computer interaction, security, healthcare diagnostics, and the entertainment industry. Full article

At the beginning of the 21st century, there were sensational discoveries in two palaces located in Ciechanowice and Struga in Silesia (Poland). During their renovations, Renaissance fresco cycles of portraits of emperors from the Roman, medieval, and early modern times appeared under the layer of plaster in the representative dining rooms (27 in the palace in Struga and about 50 in the palace in Ciechanowice). They were painted in the 1580s (in Ciechanowice, the date is 1588) by the same unknown artist. This article is the first to attempt to establish the most important facts related to the creation of both fresco cycles. The frescoes were founded by representatives of influential Silesian Protestant nobility: Heinrich von Reichenbach (Ciechanowice) and Abraham von Czettritz und Neuhaus (Struga). Both nobles attended the funeral of Emperor Maximilian II, which took place in Prague in 1577. This is where they purchased a work by the Dutch printmaker, painter, and numismatist, Hubert Goltzius, Lebendige Bilder Gar Nach Aller Keysern […] (published in Antwerp in 1557), whose specially prepared copy had been solemnly presented to Emperor Maximilian II in 1562. The book contains 133 monochrome woodcut illustrations with portraits of emperors in circular frames by the Dutch artist Joss van Gietleughen, which—together with accompanying inscriptions—were used as models for fresco paintings in both Silesian palaces. The foundation of the cycles of portraits of the emperors of the Roman Empire and the Holy Roman Empire of the German Nation in the representative halls of the palaces in Ciechanowice and Struda, which ended with a joint representation of Emperor Maximilian II and the King of Spain, Philip II Habsburg, was a way to show the gratitude of both prominent and wealthy Protestant nobles towards Emperor Maximilian II. During his reign, imperial power was the source and guarantee of religious freedoms for Protestants in Silesia. It is significant that both cycles left out the person of emperor regnant, Rudolf II, who soon after assuming the imperial throne abandoned his father’s tolerant policy towards Protestants. Although the author of both series of frescoes was probably a local painter, they are a unique artistic realization not only in Silesia but also in the whole of Central Europe, and they can only be compared to the popular Renaissance portrait galleries of “famous men” (uomini famosi). Full article

In the mid-seventeenth century, Chinese Chan master Yinyuan Longqi 隱元隆琦 (Jp. Ingen Ryūki, 1592–1673), accompanied by several disciples, traveled to Japan and established Ōbaku Zen, a new sect of Zen Buddhism in Tokugawa Japan. Ōbaku art, particularly portrait paintings of Ōbaku abbots and their spiritual predecessors, became critical representations of the sect and greatly influenced later Japanese Buddhist art. While much of the existing scholarship focuses on the artistic and stylistic aspects of Ōbaku portraiture, this paper emphasizes its religious context and doctrinal dimensions. Building on Elizabeth Horton Sharf’s inquiry into the “meaning and function” of Ōbaku portrait painting, the paper investigates how Ōbaku doctrine is expressed through these images. Using the Triptych of Three Zen Masters: Linji, Bodhidharma, and Deshan as a case study, this paper explores the role of portraiture in visually conveying Ōbaku teachings and the religious aspirations of those Chinese immigrant monks. By examining the integration of image, inscription, and seal as a unified “pictorial trinity”, the paper argues that Ōbaku portraiture embodies the sect’s distinct doctrine, rooted in Ming-era Chan practices such as beating, shouting, and strict dharma transmission. Moreover, the prominence of Bodhidharma in Ōbaku portraits, as illustrated in the triptych, reflects these Chinese immigrant monks’ desire to emulate Bodhidharma in spreading the dharma and expanding their sect’s influence in a new land. Full article

God the Father was considered so completely inexpressible and unembodied that his visual appearance in early modern masterpieces has long challenged the theological accuracy of such works. A recent discovery complicates that issue. Albrecht Dürer’s 1500 Self-portrait as Christ is incorrectly considered an isolated example of divine self-representation. It was, in fact, as shown here, part of a long tradition throughout Europe between at least the fifteenth and seventeenth centuries. The praxis, potentially sacrilegious, raises questions about the truth of art at its highest level. To address this conundrum, this article analyzes works by three eminent, but very different, artists: Michelangelo, Raphael, and Dürer. Two current methodologies—visual exegesis and the poetics of making—support the argument. The analysis reveals that there is a fundamental unity to their work, which has not been recognized on account of three popular misconceptions about the nature of art, divinity, and the mind. This article concludes that depictions of God the Father and Christ by these artists are neither heretical nor false because, as the evidence shows, all three were part of a continuous spiritual tradition embedded within their craft. Full article

In art-historical terms, a self-portrait in assistenza refers to an artist having inserted their own likeness into a larger work. In Renaissance-era art, more than 90 examples have been identified, famously including Botticelli’s Adoration of the Magi (c. 1478/1483). There, Botticelli glances out from the painting, making direct eye contact with the viewer, a feature that appears in other self-portraits of the type. In ancient Egypt, it was not commonly accepted that an artist would lay claim to it, especially when the work’s scale imposed diversification of tasks to be performed or teamwork organized on a workshop basis. This article will present evidence discovered in the Chapel of Hatshepsut in her temple at Deir el-Bahari that can be interpreted as a self-portrait in assistenza and indicates that Djehuty, Overseer of the Treasury under Hatshepsut, took the lead role there. If this identification is valid, the room’s decoration gains an additional layer of meaning and may be “read” in terms of Djehuty’s message, comparable to Botticelli gazing out from his Adoration of the Magi. This ancient Egyptian case will illustrate how that artist-designer, in interweaving subtle indicators of his involvement in the work, expresses awareness both of his intellectual skills and of his pride in creation. Full article

The rise of comics and games has led to increased artistic processing of portrait photos. With growing commercial demand and advancements in deep learning, neural networks for rapid facial style transfer have become a key research area in computer vision. This involves converting face photos into different styles while preserving content. Face images are more complex than regular images, requiring extensive modification. However, current methods often face issues such as unnatural color transitions, loss of detail in highlighted areas, and noticeable artifacts along edges, resulting in low-quality stylized images. In this study, an enhanced generative adversarial network (GAN) is proposed, which is based on Adaptive Layer Instance Normalization (AdaLIN) + Laplacian. This approach incorporates the AdaLIN normalization method, allowing for the dynamic adjustment of Instance Normalization (IN) and Layer Normalization (LN) parameters’ weights during training. By combining the strengths of both normalization techniques, the model selectively preserves and alters content information to some extent, aiming to strike a balance between style and content. This helps address problems such as unnatural color transitions and loss of details in highlights that lead to color inconsistencies. Furthermore, the introduction of a Laplacian regularization term aids in denoising the image, preventing noise features from interfering with the color transfer process. This regularization also helps reduce color artifacts along the face’s edges caused by noise while maintaining the image’s contour information. These enhancements significantly enhance the quality of the generated face images. To compare our method with traditional CycleGAN and recent algorithms such as XGAN and CariGAN, both subjective and objective evaluations were conducted. Subjectively, our method demonstrates more natural color transitions and superior artifact elimination, achieving higher scores in Mean Opinion Score (MOS) evaluations. Objectively, experiments using our method yielded better scores across three metrics: FID, SSIM, and MS-SSIM. The effectiveness of the proposed methods is validated through both objective and subjective evaluations. Full article

This article documents the discovery of ‘bismuth white’ on three late eighteenth-century portrait miniatures in the Victoria and Albert Museum collections, painted by renowned English artist George Engleheart. Metallic bismuth and bismuth-containing minerals have been known for centuries and were used on various types of artistic production, from German Wismutmalerei to medieval manuscripts and Renaissance paintings. However, until now they had never been documented on portrait miniatures, despite documentary evidence that suggests their use. The Raman analysis of the three miniatures shows that bismuth oxychloride (BiOCl, corresponding to the mineral bismoclite) is present, and XRF data prove that this material was used as a white pigment in its own right. This work is a pilot study: it represents the first step in the rediscovery of bismuth white as an artist’s pigment, and hopes to provide encouragement to other institutions to look deeper in their collections and map out the use of a relatively rare white material which until now had not been detected or documented in fine art objects. Full article

Street art, with a particular emphasis on murals, plays a crucial role in shaping the cultural DNA of contemporary cities. A prime example of this is the mural “Four Seasons with Kora” in Warsaw, which is dedicated to the renowned Polish artist Kora (Olga Jackowska). This large-scale mural, which combines the artist’s portrait with a chestnut tree motif, visually changes with the season, influencing the artist’s social perception. This study analyzed murals’ functions in social, cultural, and ecological contexts, highlighting their role in informal education and as a platform for social dialogue and integration. Using research methods such as visual analysis and examining comments and reactions on social media, this work aimed to understand how a mural integrates with its surroundings and is perceived throughout different seasons. The results indicated that the mural has become an important element of public space, not only for beautifying the city but also for stimulating social and cultural reflection. Full article

The Michelangelo effect is a phenomenon that shows a reduction in perceived effort and an improvement in performance among both healthy subjects and patients when completing a motor task related to artistic stimuli, compared to performing the same task with non-artistic stimuli. It could contribute to the efficacy of art therapy in neurorehabilitation. In this study, the possible occurrence of this effect was tested in a cognitive task by asking 15 healthy subjects and 17 patients with a history of stroke to solve a digital version of the classical memory card game. Three different types of images were used in a randomized order: French cards, artistic portraits, and photos of famous people (to compensate for the possible effects of face recognition). Healthy subjects were involved to test the usability and the load demand of the developed system, reporting no statistically significant differences among the three sessions (p > 0.05). Conversely, patients had a better performance in terms of time (p = 0.014) and the number of attempts (p = 0.007) needed to complete the task in the presence of artistic stimuli, accompanied by a reduction in the perceived effort (p = 0.033). Furthermore, artistic stimuli, with respect to the other two types of images, seemed more associated with visuospatial control than linguistic functions. Full article

The aim of this paper is to analyse facial similarity and apply it to identify the individuals depicted in the mural paintings of the apse of St. Leocadia Church, located in Chaves Municipality (North of Portugal), which were painted during the first quarter of the 16th century. This study also compares the portraits of this mural paintings with the oil paintings by the Proto-Renaissance Portuguese painter Nuno Gonçalves. Through this research, the feasibility of face recognition technology is explored to answer many ambiguities about Manueline stylistic identity and iconography. Additionally, it aims to associate historical events, artistic discoveries, and the expansion of portraiture as propaganda of power during the Portuguese Proto-Renaissance and Early Renaissance. On the other hand, it focuses on the prevalence of the religious and devotional over the sacred in Manueline painting. A proposal was made to identify the characters that are fundamental to the meaning of the mural paintings. An experiment was conducted on seven characters from the paintings at St. Leocadia Church, which were then compared to Nuno Gonçalves’ portraits. Facial similarity analysis was conducted on the faces portrayed in the Panels of St. Vincent, a remarkable portrait gallery from 15th-century Portugal, which has been the subject of national and international research for 130 years. Other paintings that were analysed were the oil paintings of St. Peter and St. Paul and of Infanta St. Joana, which were created by the same Quattrocento master. The purpose of the mural paintings of St. Leocadia Church could be catechetical in nature or related to the ritual practices of royal ancestor worship in royal portrait apses of the churches. It could also be associated with the Portuguese maritime expansion and the macro-imperial ideology of D. Manuel I. Full article

Generating artistic portraits from face photos presents a complex challenge that requires high-quality image synthesis and a deep understanding of artistic style and facial features. Traditional generative adversarial networks (GANs) have made significant strides in image synthesis; however, they encounter limitations in artistic portrait generation, particularly in the nuanced disentanglement and reconstruction of facial features and artistic styles. This paper introduces a novel approach that overcomes these limitations by employing feature disentanglement and reconstruction techniques, enabling the generation of artistic portraits that more faithfully retain the subject’s identity and expressiveness while incorporating diverse artistic styles. Our method integrates six key components: a U-Net-based image generator, an image discriminator, a feature-disentanglement module, a feature-reconstruction module, a U-Net-based information generator, and a cross-modal fusion module, working in concert to transform face photos into artistic portraits. Through extensive experiments on the APDrawing dataset, our approach demonstrated superior performance in visual quality, achieving a significant reduction in the Fréchet Inception Distance (FID) score to 61.23, highlighting its ability to generate more-realistic and -diverse artistic portraits compared to existing methods. Ablation studies further validated the effectiveness of each component in our method, underscoring the importance of feature disentanglement and reconstruction in enhancing the artistic quality of the generated portraits. Full article

We present a diffusion model-based approach that applies the artistic style of an artist or an art movement to a portrait photograph. Learning the style from the artworks of an artist or an art movement requires a training dataset composed of a lot of samples. We resolve this limitation by combining Contrastive Language Image Pretraining (CLIP) encoder and diffusion model, since the CLIP encoder extracts the features from an input portrait in a very effective way. Our framework includes three independent CLIP encoders that extract the text features, color features and Canny edge features from an input portrait, respectively. These features are incorporated to the style information extracted through a diffusion model to complete the stylization on an input portrait. The diffusion model extracts the style information from the sample images in the training dataset using an image encoder. The denoising steps in the diffusion model applies the style information from the training dataset to the CLIP-based features from an input portrait. Finally, our framework produces an artistic portrait that presents both the identity of the input portrait and the artistic style from the training dataset. The most important contribution of our framework is that our framework requires less than a hundred sample images for an artistic style. Therefore, our framework can successfully extract styles from an artist who has drawn less than a hundred artworks. We sample three artists and three art movements and apply these styles to the portraits of various identities and produce visually pleasing results. We evaluate our results using various metrics, including Frechet Inception Distance (FID), ArtFID and Language-Image Quality Evaluator (LIQE) to prove the excellence of our results. Full article

A selection of the most outstanding white marble sculptures from Tarraco has been archaeometrically studied to know more about the marble sources and their respective artistic workshops. All are imperial portraits of the 2nd century AD (Trajan, Hadrian, Lucius Verus and Marcus Aurelius) and a thoracata bust assigned to Hadrian, found on display at the National Archaeological Museum of Tarragona (MNAT). The well-established multimethod approach, combining petrography, cathodoluminescence, C and O isotopes and Sr and Mn trace element composition, has revealed the use of different very fine- to fine-grained marbles of the highest quality exploited in classical times. In contrast to what was thought until now, in which all the pieces had been assigned to Luni-Carrara, this present study identifies the use of two varieties of the recently discovered site of Göktepe near Aphrodisias and Paros-lychnites marbles, being Carrara, in minority. This study confirms the importance of strontium concentration and the contribution of cathodoluminescence to distinguish Göktepe from Carrara marble, while carbon and oxygen isotopes were crucial for the identification of Cycladic marble. Finally, in line with recent published interdisciplinary studies, the marble provenance forces us to rethink the discourse on the use of marble, its sculptural workshops and its distribution in this temporal context. Full article