Iconography studies the visual content of artworks by considering the themes portrayed in them and their representation. 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. However, it still has to be demonstrated if the classification results obtained by CNNs rely on the same iconographic properties that human experts exploit when studying iconography and if the architecture of a classifier trained on whole artwork images can be exploited to support the much harder task of object detection. 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. This work compares state-of-the-art algorithms (CAM, Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++) in terms of their capacity of identifying the iconographic attributes that determine the classification of characters in Christian art paintings. Quantitative and qualitative analyses show that Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++ have similar performances while CAM has lower efficacy. Smooth Grad-CAM++ isolates multiple disconnected image regions that identify small iconographic symbols well. Grad-CAM produces wider and more contiguous areas that cover large iconographic symbols better. The salient image areas computed by the CAM algorithms have been used to estimate object-level bounding boxes and a quantitative analysis shows that the boxes estimated with Grad-CAM reach 55% average IoU, 61% GT-known localization and 31% mAP. The obtained results are a step towards the computer-aided study of the variations of iconographic elements positioning and mutual relations in artworks and open the way to the automatic creation of bounding boxes for training detectors of iconographic symbols in Christian art images.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321385PMC
http://dx.doi.org/10.3390/jimaging7070106DOI Listing

Publication Analysis

Top Keywords

christian art
12
smooth grad-cam++
12
iconographic symbols
12
cam algorithms
8
salient image
8
classification characters
8
characters christian
8
art paintings
8
grad-cam grad-cam++
8
grad-cam++ smooth
8

Similar Publications

Religion contributes to the identity, well-being, and life satisfaction of many people globally, however, its traditional stance on infertility and assisted reproductive technologies (ART) can conflict with individuals' personal reproductive aspirations and desire for a family. As the fertility rates of certain ethnic and religious groups decline, it is essential to discuss the interface between religion, infertility and ART, to understand how to best navigate the infertility journeys of proclaimed Christians. This article contextualises this discussion in the experiences of eight Pacific Christian adults living with infertility and/or accessing ART in Aotearoa New Zealand.

View Article and Find Full Text PDF

SD-LayerNet: Robust and label-efficient retinal layer segmentation via anatomical priors.

Comput Methods Programs Biomed

January 2025

Christian Doppler Laboratory for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria; Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna, Vienna, Austria.

Background And Objectives: Automated, anatomically coherent retinal layer segmentation in optical coherence tomography (OCT) is one of the most important components of retinal disease management. However, current methods rely on large amounts of labeled data, which can be difficult and expensive to obtain. In addition, these systems tend often propose anatomically impossible results, which undermines their clinical reliability.

View Article and Find Full Text PDF

Formulating the title and abstract of a manuscript is crucial to convey the essence of the research paper to the reader at a superficial glance. The title should be short and crisp, yet it should define critical information about the paper, such as the disease highlighted, any intervention studied, or the primary outcome. A structured abstract is required in most journals for an original research article, conveying a summary of the research.

View Article and Find Full Text PDF

Explainable unsupervised anomaly detection for healthcare insurance data.

BMC Med Inform Decis Mak

January 2025

Department of Electrical Engineering, ESAT-STADIUS, KU Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium.

Background: Waste and fraud are important problems for health insurers to deal with. With the advent of big data, these insurers are looking more and more towards data mining and machine learning methods to help in detecting waste and fraud. However, labeled data is costly and difficult to acquire as it requires expert investigators and known care providers with atypical behavior.

View Article and Find Full Text PDF

Background/objectives: Brown adipose tissue (BAT) plays a crucial role in energy expenditure and thermoregulation and has thus garnered interest in the context of metabolic diseases. Segmentation in medical imaging is time-consuming and prone to inter- and intra-operator variability. This study aims to develop an automated BAT segmentation method using the nnU-Net deep learning framework, integrated into the TotalSegmentator software, and to evaluate its performance in a large cohort of patients with lymphoma.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!