Can We Teach Computers to Understand Art? Domain Adaptation for Enhancing Deep Networks Capacity to De-Abstract Art

Humans comprehend a natural scene at a single glance; painters and other visual artists, through their abstract representations, stressed this capacity to the limit. The performance of computer vision solutions matched that of humans in many problems of visual recognition. In this paper we address the problem of recognizing the genre (subject) in digitized paintings using Convolutional Neural Networks (CNN) as part of the more general dealing with abstract and/or artistic representation of scenes. Initially we establish the state of the art performance by training a CNN from scratch. In the next level of evaluation, we identify aspects that hinder the CNNs' recognition, such as artistic abstraction. Further, we test various domain adaptation methods that could enhance the subject recognition capabilities of the CNNs. The evaluation is performed on a database of 80,000 annotated digitized paintings, which is tentatively extended with artistic photographs, either original or stylized, in order to emulate artistic representations. Surprisingly, the most efficient domain adaptation is not the neural style transfer. Finally, the paper provides an experiment-based assessment of the abstraction level that CNNs are able to achieve.

Pandora: Description of a Painting Database for Art Movement Recognition with Baselines and Perspectives

To facilitate computer analysis of visual art, in the form of paintings, we introduce Pandora (Paintings Dataset for Recognizing the Art movement) database, a collection of digitized paintings labelled with respect to the artistic movement. Noting that the set of databases available as benchmarks for evaluation is highly reduced and most existing ones are limited in variability and number of images, we propose a novel large scale dataset of digital paintings. The database consists of more than 7700 images from 12 art movements. Each genre is illustrated by a number of images varying from 250 to nearly 1000. We investigate how local and global features and classification systems are able to recognize the art movement. Our experimental results suggest that accurate recognition is achievable by a combination of various categories.To facilitate computer analysis of visual art, in the form of paintings, we introduce Pandora (Paintings Dataset for Recognizing the Art movement) database, a collection of digitized paintings labelled with respect to the artistic movement. Noting that the set of databases available as benchmarks for evaluation is highly reduced and most existing ones are limited in variability and number of images, we propose a novel large scale dataset of digital paintings. The database consists of more than 7700 images from 12 art movements. Each genre is illustrated by a number of images varying from 250 to nearly 1000. We investigate how local and global features and classification systems are able to recognize the art movement. Our experimental results suggest that accurate recognition is achievable by a combination of various categories.

High Dynamic Range Imaging by Perceptual Logarithmic Exposure Merging

In this paper we emphasize a similarity between the Logarithmic-Type Image Processing (LTIP) model and the Naka-Rushton model of the Human Visual System (HVS). LTIP is a derivation of the Logarithmic Image Processing (LIP), which further replaces the logarithmic function with a ratio of polynomial functions. Based on this similarity, we show that it is possible to present an unifying framework for the High Dynamic Range (HDR) imaging problem, namely that performing exposure merging under the LTIP model is equivalent to standard irradiance map fusion. The resulting HDR algorithm is shown to provide high quality in both subjective and objective evaluations.

Pain Intensity Estimation by a Self--Taught Selection of Histograms of Topographical Features

Pain assessment through observational pain scales is necessary for special categories of patients such as neonates, patients with dementia, critically ill patients, etc. The recently introduced Prkachin-Solomon score allows pain assessment directly from facial images opening the path for multiple assistive applications. In this paper, we introduce the Histograms of Topographical (HoT) features, which are a generalization of the topographical primal sketch, for the description of the face parts contributing to the mentioned score. We propose a semi-supervised, clustering oriented self--taught learning procedure developed on the emotion oriented Cohn-Kanade database. We use this procedure to improve the discrimination between different pain intensity levels and the generalization with respect to the monitored persons, while testing on the UNBC McMaster Shoulder Pain database.

Robust Eye Centers Localization with Zero--Crossing Encoded Image Projections

This paper proposes a new framework for the eye centers localization by the joint use of encoding of normalized image projections and a Multi Layer Perceptron (MLP) classifier. The encoding is novel and it consists in identifying the zero-crossings and extracting the relevant parameters from the resulting modes. The compressed normalized projections produce feature descriptors that are inputs to a properly-trained MLP, for discriminating among various categories of image regions. The proposed framework forms a fast and reliable system for the eye centers localization, especially in the context of face expression analysis in unconstrained environments. We successfully test the proposed method on a wide variety of databases including BioID, Cohn-Kanade, Extended Yale B and Labelled Faces in the Wild (LFW) databases.