Filters








64 Hits in 3.3 sec

A Data Set and a Convolutional Model for Iconography Classification in Paintings [article]

Federico Milani, Piero Fraternali
2020 arXiv   pre-print
In this paper we introduce a novel paintings data set for iconography classification and present the quantitativeand qualitative results of applying a Convolutional Neural Network (CNN) classifier to the  ...  It is a subject of active research for a variety of purposes, including the interpretation of meaning, the investigation of the origin and diffusion in time and space of representations, and the study  ...  A Data Set and a Convolutional Model for Iconography Classification in Paintings • 111:15 "La vergine in trono con il Bambino e tra san Girolamo e san Pietro", Andrea d'Assisi, 1490 9 "Madonna della  ... 
arXiv:2010.11697v2 fatcat:swhjiq4i5rdwrocnxjg4fl6uuy

Comparing CAM Algorithms for the Identification of Salient Image Features in Iconography Artwork Analysis

Nicolò Oreste Pinciroli Pinciroli Vago, Federico Milani, Piero Fraternali, Ricardo da Silva Torres
2021 Journal of Imaging  
Computer Vision has been used to identify iconographic subjects in paintings and Convolutional Neural Networks enabled the effective classification of characters in Christian art paintings.  ...  A suitable approach for exposing the process of classification by neural models relies on Class Activation Maps, which emphasize the areas of an image contributing the most to the classification.  ...  Data Availability Statement: Publicly available datasets were analyzed in this study. This data can be found here: http://www.artdl.org (accessed on 29 June 2021).  ... 
doi:10.3390/jimaging7070106 fatcat:5ahrrnd2h5bhhdd6wtopwk3cse

Adversarial Learning Approach to Unsupervised Labeling of Fine Art Paintings

Catherine Sandoval, Elena Pirogova, Margaret Lech
2021 IEEE Access  
This study aims to provide meaningful automatic labeling of fine art paintings (machine labeling) without the need for human annotation.  ...  The proposed method was tested on three different fine-art datasets, including two sets of paintings previously categorized by art experts and one never categorized collection of Australian Aboriginal  ...  As previously shown in [1] , a supervised CNN model was able to categorize the five movements included in Dataset 1 with high accuracy. 2) DATASET 2 The second dataset was the Painting Database for  ... 
doi:10.1109/access.2021.3086476 fatcat:l3xkbjoihvbsrcjaibyd3pcmje

Knowledge Graph Embedding-Based Domain Adaptation for Musical Instrument Recognition

Victoria Eyharabide, Imad Eddine Ibrahim Bekkouch, Nicolae Dragoș Constantin
2021 Computers  
Convolutional neural networks raised the bar for machine learning and artificial intelligence applications, mainly due to the abundance of data and computations.  ...  The experimental results showed a significant increase in the baselines and state-of-the-art performance compared with other domain adaptation methods.  ...  We report the f1-scores for every main class in our dataset (Viele, Lute, Bow) and the macro F1-score for the models in Table 1 , as it strikes a good balance between precision and recall and evaluates  ... 
doi:10.3390/computers10080094 fatcat:jflkr5uwqvazdop2pfhsqj73lq

Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning [article]

Gerardo Ibarra-Vazquez, Gustavo Olague, Mariana Chan-Ley, Cesar Puente, Carlos Soubervielle-Montalvo
2021 arXiv   pre-print
Finally, BP also gets four categories using adversarial patches without changes and for the remaining three classes with a variation of 1\%.  ...  We tested a prevailing bag of visual words approach from computer vision, four state-of-the-art DCNN models (AlexNet, VGG, ResNet, ResNet101), and the Brain Programming (BP) algorithm.  ...  This dataset comprises five categories of art media: drawing, painting, iconography, engraving, and sculpture.  ... 
arXiv:2103.01359v1 fatcat:7gkb6x7odbclfaj6ynh4oil55e

Recognizing Characters in Art History Using Deep Learning

Prathmesh Madhu, Ronak Kosti, Lara Mührenberg, Peter Bell, Andreas Maier, Vincent Christlein
2019 Proceedings of the 1st Workshop on Structuring and Understanding of Multimedia heritAge Contents - SUMAC '19  
We present experiments and analysis on three different models and show that the model trained on domain related data gives the best performance for recognizing character.  ...  The limitations of this method, and the inherent ambiguity in the representation of Gabriel, motivated us to consider their bodies (a bigger context) to analyze in order to recognize the characters.  ...  We would also like to thank NVIDIA for their generous hardware donations.  ... 
doi:10.1145/3347317.3357242 dblp:conf/mm/MadhuKMBMC19 fatcat:gmwdirp22jhhhfsw6ayqzzpr4u

Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Madhab Raj Joshi, Lewis Nkenyereye, Gyanendra Prasad Joshi, S. M. Riazul Islam, Mohammad Abdullah-Al-Wadud, Surendra Shrestha
2020 Mathematics  
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  ...  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 authors are grateful for this support. Conflicts of Interest: The authors declare that there is no conflict of interest.  ... 
doi:10.3390/math8122258 fatcat:xgai33bt4rd2fgpagqmfvpp764

Two-stage deep learning approach to the classification of fine-art paintings

Catherine Sandoval, Elena Pirogova, Margaret Lech
2019 IEEE Access  
It created a demand for efficient software tools that would allow rapid retrieval and semantic categorization of art.  ...  At the first stage, the proposed approach divides the input image into five patches and applies a deep convolutional neural network (CNN) to train and classify each patch individually.  ...  For each dataset, and for each one of the six pretrained CNN models, seven different classification scenarios were evaluated and compared.  ... 
doi:10.1109/access.2019.2907986 fatcat:3dq6xs2krvbgvfwqyz3nbwh4ge

Understanding and Creating Art with AI: Review and Outlook [article]

Eva Cetinic, James She
2021 arXiv   pre-print
In the context of AI-related research for art understanding, we present a comprehensive overview of artwork datasets and recent works that address a variety of tasks such as classification, object detection  ...  Technologies related to artificial intelligence (AI) have a strong impact on the changes of research and creative practices in visual arts.  ...  The availability of large-scale and well-annotated datasets is a necessary requirement for adopting deep learning models for various tasks.  ... 
arXiv:2102.09109v1 fatcat:ztuhedmgqrbdziwogxjq46spzq

Towards Generating and Evaluating Iconographic Image Captions of Artworks

Eva Cetinic
2021 Journal of Imaging  
Using this dataset, a captioning model is developed by fine-tuning a transformer-based vision-language pretrained model.  ...  Recently, a lot of progress has been made by adopting multimodal deep learning approaches for integrating vision and language.  ...  Iconclass is a classification system designed for art and iconography and is widely accepted by museums and art institutions as a tool for the description and retrieval of subjects represented in images  ... 
doi:10.3390/jimaging7080123 pmid:34460759 fatcat:z2qhpdf3dzbwfbydaedvfz5wbq

Toward Fine-grained Image Retrieval with Adaptive Deep Learning for Cultural Heritage Image

Sathit Prasomphan
2023 Computer systems science and engineering  
Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different  ...  The key contribution of this research was the creation of a retrieval model that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing  ...  In [27] , a piecewise cross entropy loss function was introduced. A convolution neural network model was introduced for retrieval performance in fine-grained images.  ... 
doi:10.32604/csse.2023.025293 fatcat:ggtexahsv5fr5ax2cpz2hnsa6u

Machine Learning for Cultural Heritage: A Survey

Marco Fiorucci, Marina Khoroshiltseva, Massimiliano Pontil, Arianna Traviglia, Alessio Del Bue, Stuart James
2020 Pattern Recognition Letters  
We survey across ML and CH literature to identify the theoretical changes which contribute to the algorithm and in turn them suitable for CH applications.  ...  From such an analysis, we give a critical look at the use of ML in CH and consider why CH has only limited adoption of ML.  ...  Acknowledgement Partially supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 870743.  ... 
doi:10.1016/j.patrec.2020.02.017 fatcat:smayxo3wcbfmhm33c6q4rnmr6i

Generative Digital Humanities

Fabian Offert, Peter Bell
2020 Workshop on Computational Humanities Research  
While generative machine learning has recently attracted a significant amount of attention in the computer science community, its potential for the digital humanities has so far not been fully evaluated  ...  If "all models are wrong, some are useful", as the often-cited passage reads, we argue that, in case of the digital humanities, the most useful-wrong models are generative.  ...  We can design a model that learns the most salient difference between apples and oranges from the dataset.  ... 
dblp:conf/chr/Offert020 fatcat:szivogi7jnevdhpb22gkcudjla

Dream Formulations and Deep Neural Networks: Humanistic Themes in the Iconology of the Machine-Learned Image [article]

Emily L. Spratt
2018 arXiv   pre-print
of art historical research in iconography and formalism in the age of AI is essential for shaping the future navigation and interpretation of all machine-learned images, given the rapid developments in  ...  Utilizing the examples of Google's DeepDream and the Machine Learning and Perception Lab at Georgia Tech's Grad-CAM: Gradient-weighted Class Activation Mapping programs, this study suggests that a revival  ...  It cannot be stressed enough how critical the dataset that the program is trained on is for the process of image recognition, and a large and vetted dataset that is specified for the image-recognition  ... 
arXiv:1802.01274v1 fatcat:ndfkatx74zeqnbfzklwzy2k4my

Weakly Supervised Object Detection in Artworks [chapter]

Nicolas Gonthier, Yann Gousseau, Said Ladjal, Olivier Bonfait
2019 Landolt-Börnstein - Group III Condensed Matter  
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed.  ...  To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings.  ...  In particular, impressive classification results are obtained on painting databases by using convolutional neural networks (CNNs) designed for the classification of photographs [10, 55] .  ... 
doi:10.1007/978-3-030-11012-3_53 fatcat:xyf6rztlcjg3vbgi5vfeys3noq
« Previous Showing results 1 — 15 out of 64 results