scholarly journals An automatic workflow for orientation of historical images with large radiometric and geometric differences

2021 ◽  
Author(s):  
Ferdinand Maiwald ◽  
Hans‐Gerd Maas
Keyword(s):  
Historical Images

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Geografía de la mirada. el paisaje desde la mirada fotográfica contemporánea

2016 ◽  
Vol 11 (18) ◽  
pp. 138
Author(s):  
Mateo Pérez
Keyword(s):  
Historical Context ◽  
Photographic Images ◽  
The Gaze ◽  
Historical Images ◽  
Cette Question ◽  
The Way

GEOGRAFÍA DE LA MIRADA. EL PAISAJE DESDE LA MIRADA FOTOGRÁFICA CONTEMPORÁNEA RESUMEN ¿Cómo entender el concepto de paisaje a partir de las prácticas fotográficas contemporáneas? Este artículo busca responder a esta pregunta con la ayuda de un proyecto finalizado de creación artística que tenía como objetivo exponer una serie de imágenes fotográficas del Salto del Tequendama y alrededores, en las inmediaciones de Bogotá. Se trata de comprender la manera en que se abordó este proyecto artístico y también de dilucidar ciertos aspectos del concepto de paisaje, especialmente la forma en que hoy se le considera desde la fotografía. Con este acercamiento, se hace una revisión histórica de las imágenes que existen del Salto del Tequendama de modo que, a través de ellas, se pueda comprender e interpretar mejor las formas de representación actuales, específicamente las que se produjeron para la exposición. El artículo señala cómo el concepto de paisaje es un concepto dinámico, construido a partir de su contexto histórico. PALABRAS CLAVES Fotografía, paisaje, Romanticismo, Salto del Tequendama, sublime, suicidio. AWANINAMANDA KUWANGAPA ATUN LLAGTA KAWANGAPA MAIPI NUKANCHI KAUSAGTA SUGLLAPI Kaipi ninakumi imasai kawachinaku nukanchipakausadiruta parlanakume sug kilkawa imasami karunimanda kawanaku tapuchiskata añispa kawachispa kunauramandakunata kai fotokuna salto de Tequendama suti, paikuna rurankuna sug iachachikuna mana chingaringapa kai ñugpamanda kausaikuna chasallata tukui rurakuna tukuikunata iachachispa kawachispa tukuikunamanda. IMA SUTI RIMAI SIMI: Kawachiikuna, sachaku, llakii, wañui kawachispa sutipa llullangapa. GEOGRAPHY OF THE GAZE LANDSCAPE AS SEEN FROM THE CONTEMPORARY PHOTOGRAPHIC GAZE ABSTRACT How to understand the concept of landscape based upon contemporary photography practices? This article tries to answer this question with the help of a concluded artistic project, whose main objective was exposing a series of photographic images of Tequendama Falls and its surroundings, near Bogotá. The article tries to understand the way in which this artistic project was addressed and to explain certain aspects of the concept of landscape and of the way it is conceived by photography today. With this approach, an historic overview of some historical images of Tequendama Falls is carried out, so as to improve the processes of understanding and interpreting contemporary forms of representation, specifically the ones produced for the exhibition. The article points out how the concept of landscape is a dynamic one and how it is based on its historical context. KEYWORDS Photography, landscape, Romanticism, Tequendama Falls, sublime, suicide. GEOGRAPHIE DU REGARD LE PAYSAGE A PARTIR DU REGARD PHOTOGRAPHIQUE CONTEMPORAIN RÉSUMÉ Comment comprendre le concept de paysage basé sur les pratiques de la photographie contemporaine ? Cet article tente de répondre à cette question avec l’aide d’un projet artistique conclu, dont l’objectif principal était d’exposer une série d’images photographiques du Salto del Tequendama et ses environs, près de Bogotá. L’article tente de comprendre la façon dont ce projet artistique a été abordé et aussi d’expliquer certains aspects de la notion de paysage et de la façon dont il est conçu par la photographie aujourd’hui. Avec cette approche, un aperçu historique de quelques images historiques du Salto del Tequendama est réalisé de manière à améliorer les processus de compréhension et d’interprétation des formes contemporaines de représentation, en particulier celles produites pour l’exposition. L’article souligne comment le concept de paysage est dynamique et comment il est basé sur son contexte historique. MOTS-CLEFS Photographie, paysage, romantisme, Salto del Tequendama, sublime, suicide. GEOGRAFIA DO OLHAR A PAISAGEM DESDE O OLHAR FOTOGRÁFICA CONTEMPORÂNEA RESUMO Como entender o conceito da paisagem a partir das práticas fotográficas contemporâneas? Este artigo procura responder a esta pergunta com a ajuda de um projeto finalizado de criação artística que tinha como objetivo expor uma série de imagens fotográficas do Salto do Tequendama e aos redores, nas imediações de Bogotá. Trata-se de compreender a maneira em que se abordou este projeto artístico e também de (desoxidar) certos aspectos do conceito da paisagem, especialmente a forma em que hoje se lhe considera desde a fotografia. Com esta aproximação, se faz uma revisão histórica das imagens que existem do Salto do Tequendama de maneira que, a través delas, se possa compreender e interpretar melhor as formas de representação atuais, especificamente as que se produziram para a exposição. O artigo assinala como o conceito da paisagem é um conceito dinâmico, construído a partir de seu contexto históricoPALAVRAS CHAVES Fotografia, paisagem, Romantismo, Salto del Tequendama, sublime, suicídio.   Recibido el 07 de octubre de 2014 Aceptado el 03 de diciembre de 2015

scholarly journals QGIS plugin or web app? Lessons learned in the development of a 3D georeferencer

2016 ◽  
Author(s):  
Timothee Produit ◽  
Jens Ingensand ◽  
Gillian Milani
Keyword(s):  
Spatial Data ◽  
Geographic Information ◽  
Lessons Learned ◽  
Development Effort ◽  
Historical Images ◽  
Web App ◽  
Scientific Value

Collections of historical images are currently being scanned to stop their degradation and to enable a numeric exploitation. These collections have a high cultural, artistic and scientific value. However, they are not fully exploited because the photographs do not have a georeference (geographic information cannot be extracted from the picture) and are poorly labeled (makes searching in a database inefficient). During the last years, we developed a QGIS plugin and a web app dedicated to the georeferencing of photographs and the linking of images with spatial data. In this paper, we discuss the technologies involved and compare both implementations. The results suggest that both approaches are valuable but provide different advantages in term of target users and development effort.

scholarly journals Fully Automated Pose Estimation of Historical Images in the Context of 4D Geographic Information Systems Utilizing Machine Learning Methods

2021 ◽  
Vol 10 (11) ◽  
pp. 748
Author(s):  
Ferdinand Maiwald ◽  
Christoph Lehmann ◽  
Taras Lazariv
Keyword(s):  
Information Systems ◽  
Geographic Information Systems ◽  
Image Retrieval ◽  
Pose Estimation ◽  
Large Scale ◽  
Feature Matching ◽  
Geographic Information ◽  
Content Based Image Retrieval ◽  
Matching Methods ◽  
Historical Images

The idea of virtual time machines in digital environments like hand-held virtual reality or four-dimensional (4D) geographic information systems requires an accurate positioning and orientation of urban historical images. The browsing of large repositories to retrieve historical images and their subsequent precise pose estimation is still a manual and time-consuming process in the field of Cultural Heritage. This contribution presents an end-to-end pipeline from finding relevant images with utilization of content-based image retrieval to photogrammetric pose estimation of large historical terrestrial image datasets. Image retrieval as well as pose estimation are challenging tasks and are subjects of current research. Thereby, research has a strong focus on contemporary images but the methods are not considered for a use on historical image material. The first part of the pipeline comprises the precise selection of many relevant historical images based on a few example images (so called query images) by using content-based image retrieval. Therefore, two different retrieval approaches based on convolutional neural networks (CNN) are tested, evaluated, and compared with conventional metadata search in repositories. Results show that image retrieval approaches outperform the metadata search and are a valuable strategy for finding images of interest. The second part of the pipeline uses techniques of photogrammetry to derive the camera position and orientation of the historical images identified by the image retrieval. Multiple feature matching methods are used on four different datasets, the scene is reconstructed in the Structure-from-Motion software COLMAP, and all experiments are evaluated on a newly generated historical benchmark dataset. A large number of oriented images, as well as low error measures for most of the datasets, show that the workflow can be successfully applied. Finally, the combination of a CNN-based image retrieval and the feature matching methods SuperGlue and DISK show very promising results to realize a fully automated workflow. Such an automated workflow of selection and pose estimation of historical terrestrial images enables the creation of large-scale 4D models.

Historical Images

2018 ◽  
pp. 21-44
Author(s):  
Richard W. Waterman ◽  
Robert Wright ◽  
St. Gilbert Clair
Keyword(s):  
Historical Images

scholarly journals A Neural Networks Approach to Detecting Lost Heritage in Historical Video

2020 ◽  
Vol 9 (5) ◽  
pp. 297
Author(s):  
Francesca Condorelli ◽  
Fulvio Rinaudo ◽  
Francesco Salvadore ◽  
Stefano Tagliaventi
Keyword(s):  
Architectural Heritage ◽  
Time Intervals ◽  
Large Dataset ◽  
Time Saving ◽  
The Past ◽  
Historical Images ◽  
Virtual Reconstruction ◽  
Human Effort ◽  
Video Material

Documenting Cultural Heritage through the extraction of 3D measures with photogrammetry is fundamental for the conservation of the memory of the past. However, when the heritage has been lost the only way to recover this information is the use of historical images from archives. The aim of this study is to experiment with new ways to search for architectural heritage in video material and to save the effort of the operator in the archive in terms of efficiency and time. A workflow is proposed to automatically detect lost heritage in film footage using Deep Learning to find suitable images to process with photogrammetry for its 3D virtual reconstruction. The performance of the network was tested on two case studies considering different architectural scenarios, the Tour Saint Jacques which still exists for the tuning of the networks, and Les Halles to test the algorithms on a real case of an architecture which has been destroyed. Despite the poor quantity and low quality of the historical images available for the training of the network, it has been demonstrated that, with few frames, it was possible to reach the same results in terms of performance of a network trained on a large dataset. Moreover, with the introduction of new metrics based on time intervals the measure of the real time saving in terms of human effort was achieved. These findings represent an important innovation in the documentation of destroyed monuments and open new ways to recover information about the past.

Ned Kelly

2014 ◽  
Keyword(s):  
Forensic Investigation ◽  
Handwriting Analysis ◽  
Scientific Process ◽  
Mass Graves ◽  
Community History ◽  
Exact Location ◽  
Historical Images ◽  
Collaborative Community ◽  
Metallurgical Analysis ◽  
Medical Analysis

Ned Kelly was hanged at the Old Melbourne Gaol on 11 November 1880, and his body buried in the graveyard there. Many stories emerged about his skull being separated and used as a paperweight or trophy, and it was finally put on display at the museum of the Old Melbourne Gaol — until it was stolen in 1978. It wasn’t only Ned Kelly’s skull that went missing. After the closure of the Old Melbourne Gaol in 1929, the remains of deceased prisoners were exhumed and reinterred in mass graves at Pentridge Prison. The exact location of these graves was unknown until 2002, when the bones of prisoners were uncovered at the Pentridge site during redevelopment. This triggered a larger excavation that in 2009 uncovered many more coffins, and led to the return of the skull and a long scientific process to try to identify and reunite Ned Kelly’s remains. But how do you go about analysing and accurately identifying a skeleton and skull that are more than 130 years old? Ned Kelly: Under the Microscope details what was involved in the 20-month scientific process of identifying the remains of Ned Kelly, with chapters on anthropology, odontology, DNA studies, metallurgical analysis of the gang's armour, and archaeological digs at Pentridge Prison and Glenrowan. It also includes medical analysis of Ned's wounds and a chapter on handwriting analysis — that all lead to the final challenging conclusions. Illustrated throughout with photographs taken during the forensic investigation, as well as historical images, the book is supplemented with breakout boxes of detailed but little-known facts about Ned Kelly and the gang to make this riveting story a widely appealing read. Winner of the Collaborative Community Award at the 2015 Victorian Community History Awards.

Sign in / Sign up

Export Citation Format

Share Document