Browsing by Author "Sarvazyan, Narine"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Advancing Armenian Inscription Recognition
    (The Eurographics Association, 2025) Nersesian, Gevorg; Sarvazyan, Narine; Khachatryan, Suren; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
    Armenian monuments are rich in carved stone inscriptions. These inscriptions serve as vital records of cultural and linguistic heritage, offering insights into the lives, beliefs, and traditions of Armenians during the Middle ages. However, detecting and comprehending these inscriptions pose significant challenges. Due to weathering, vandalism, erosion, and the complexity of ancient scripts, many of these texts remain unreadable. Yet, the few existing studies indicate that deciphering these messages from the past is feasible with technological advancements. In the present project we study a unique, newly created and unex- plored collection of digital twins of Armenian tapanakars (tombstones) and khachkars (cross-stones) focusing on hierarchical segmentation of the images using the detected geometrical and statistical features. The results are applied to character classi- fication and the accuracy of the generated images is estimated. Since the detection stage of the algorithm is universal for any kind of shapes, it opens up new research avenues that extend beyond text recognition alone. The same pipeline can be adapted to identify decorative motifs, geometric symbols, and other visual patterns commonly found on tapanakar surfaces.
  • Thumbnail Image
    Item
    Bringing Stones to Life: The First Digital 3D Library of Ancient Armenian Gravestones
    (The Eurographics Association, 2025) Andrianov, Aleksei; Muradyan, Garegin; Andrianova, Zhanna; Sarvazyan, Narine; Campana, Stefano; Ferdani, Daniele; Graf, Holger; Guidi, Gabriele; Hegarty, Zackary; Pescarin, Sofia; Remondino, Fabio
    We report the creation of a high-resolution 3D digital libraries of khachkars and tapanakars, ornately carved gravestones that offer a rare glimpse into the daily lives of ordinary Armenians during the Middle Ages. Khachkars are vertical stelae bearing ornate crosses and geometric motifs, while tapanakars feature a pyramidal form adorned with various everyday scenes such as horseback riding, dancing, trading, and communal feasting. Centuries of physical and environmental stress have threatened these carvings and no 3D digital records of them currently exist. Using photogrammetry and LiDAR scanning technologies, we have created fully rotatable 3D digital twins of over 70 tapanakars and 150 khachkars with the millimeter-level precision. These models capture the intricate carvings and iconography that traditional photography often misses, especially on weathered or lichen-covered surfaces. We also developed image processing steps to help convert barely visible carvings into their linear outlines enabling future epigraphic interpretation and the use of machine learning algorithms. Two dedicated websites have been created to make these 3D libraries publicly accessible and to allow scholars, students, and enthusiasts worldwide to explore their cultural and artistic significance across different interdisciplinary projects. These unique collections offer a valuable dataset for image processing and computer vision studies, such as pattern recognition, feature extraction, and 3D modeling techniques. Beyond academic use, this resource has potential applications in education, virtual exhibitions, and cultural tourism promoting Armenian cultural heritage on an international scale.