ArticlePublisher preview available

Research on the factors affecting accuracy of abstract painting orientation detection

DOI:10.1007/s11042-023-15034-4
Authors:
Qiang Zhao
Qiang Zhao
Qiang Zhao
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Zheng Chang
Zheng Chang
Zheng Chang
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Ziwen Wang
Ziwen Wang
Ziwen Wang
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Read publisher preview
Download citation
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

An abstract painting’s hanging orientation directly affects how audiences judge its artistic value. Choosing the optimal hanging orientation can preserve the artist’s primary intention, preserving the original aesthetic value to a greater extent. Aesthetic value is frequently influenced by human subjective consciousness. Previous approaches improved direction recognition accuracy only by improving the feature extraction method and deep learning network. For this paper, the key factors that can influence recognition accuracy (such as painting content, image features and learning models) were investigated in conjunction with painting skills to find an experimental setting method that can enhance recognition accuracy. Experiment results show that the content of the painting has the greatest impact on classification accuracy. Furthermore, the average accuracy can be increased to more than 90% by reducing the number of painting categories in a dataset and the number of directions to be classified. While the outcome is superior to the state of the art, it is one-sided to rely solely on the information in the abstract painting. A combination of eye tracker data and questionnaires will be used in the future to examine the effect of audience subjective feelings on orientation classification.
Figures - available from: Multimedia Tools and Applications
This content is subject to copyright. Terms and conditions apply.
  • A preview of this full-text is provided by Springer Nature.
  • Learn more
Preview content only
Content available from Multimedia Tools and Applications
This content is subject to copyright. Terms and conditions apply.
https://doi.org/10.1007/s11042-023-15034-4
Research on the factors affecting accuracy of abstract
painting orientation detection
Qiang Zhao1,2 ·Zheng Chang3,4 ·Ziwen Wang2
Received:29 April 2022 / Revised: 6 November2022 / Accepted: 27 February 2023 /
©The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023
Abstract
An abstract painting’s hanging orientation directly affects how audiences judge its artistic
value. Choosing the optimal hanging orientation can preserve the artist’s primary inten-
tion, preserving the original aesthetic value to a greater extent. Aesthetic value is frequently
influenced by human subjective consciousness. Previous approaches improved direction
recognition accuracy only by improving the feature extraction method and deep learning
network. For this paper, the key factors that can influence recognition accuracy (such as
painting content, image features and learning models) were investigated in conjunction with
painting skills to find an experimental setting method that can enhance recognition accu-
racy. Experiment results show that the content of the painting has the greatest impact on
classification accuracy. Furthermore, the average accuracy can be increased to more than
90% by reducing the number of painting categories in a dataset and the number of direc-
tions to be classified. While the outcome is superior to the state of the art, it is one-sided
to rely solely on the information in the abstract painting. A combination of eye tracker data
and questionnaires will be used in the future to examine the effect of audience subjective
feelings on orientation classification.
Keywords Orientation detection ·Abstract paintings ·Recognition accuracy ·
Image feature ·Deep neural network
Qiang Zhao
hmoe@vip.qq.com
1Institute of Electronic and Information Engineering, University of Electronic Science
and Technology of China, Dongguan, China
2School of Automation and Software Engineering, Shanxi University, Taiyuan, China
3School of Computer Science and Engineering, University of Electronic Science
and Technology of China, Chengdu, China
4Faculty of Information Technology, University of Jyv¨
askyl¨
a,
P.O. Box 35, FIN-40014, Jyv¨
askyl¨
a, Finland
Published online: 17 March 2023
Multimedia Tools and Applications (2023) 82:36231–36254
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
ResearchGate has not been able to resolve any citations for this publication.
Novel energy management scheme in IoT enabled smart irrigation system using optimized intelligence methods
Article
Full-text available
In recent times, due to the growing global population and increased food demand, smart agriculture is becoming more vital. In this context, Internet of Things (IoT) technologies have emerged as a significant pathway to innovative agricultural techniques. Due to their low capacity, these IoT nodes have faced energy limits and complicated routing methods. As a result, in the sphere of IoT-based agriculture, transmitting data failure, energy consumption, network lifetime reduction, and delay occur. To overcome this problem, this study proposes a novel combination of optimized intelligent smart irrigation systems to improve the energy management performance of the system. Here, the optimal cluster head formation and selection is performed by Hierarchy Shuffled Shepherd Clustering (HSSC) method. Also, the finest energy regulation and routing path are provided by the proposed Emperor Penguin Jellyfish Optimizer (EPJO) method. The simulation of this work is performed on Network Simulator-2 (NS2) software. The simulation consequences from the proposed method are validated and compared with the conventional methods. Thus, the proposed approach results demonstrate that the developed model has much lesser energy consumption and improved network lifetime as compared to the traditional works.
View
Artificial Visual System for Orientation Detection
Article
Full-text available
  • Feb 2022
The human visual system is one of the most important components of the nervous system, responsible for visual perception. The research on orientation detection, in which neurons of the visual cortex respond only to a line stimulus in a particular orientation, is an important driving force of computer vision and biological vision. However, the principle underlying orientation detection remains a mystery. In order to solve this mystery, we first propose a completely new mechanism that explains planar orientation detection in a quantitative manner. First, we assume that there are planar orientation-detective neurons which respond only to a particular planar orientation locally and that these neurons detect local planar orientation information based on nonlinear interactions that take place on the dendrites. Then, we propose an implementation of these local planar orientation-detective neurons based on their dendritic computations, use them to extract the local planar orientation information, and infer the global planar orientation information from the local planar orientation information. Furthermore, based on this mechanism, we propose an artificial visual system (AVS) for planar orientation detection and other visual information processing. In order to prove the effectiveness of our mechanism and the AVS, we conducted a series of experiments on rectangular images which included rectangles of various sizes, shapes and positions. Computer simulations show that the mechanism can perfectly perform planar orientation detection regardless of their sizes, shapes and positions in all experiments. Furthermore, we compared the performance of both AVS and a traditional convolution neural network (CNN) on planar orientation detection and found that AVS completely outperformed CNN in planar orientation detection in terms of identification accuracy, noise resistance, computation and learning cost, hardware implementation and reasonability.
View
Research on the application of local binary patterns based on color distance in image classification
Article
Full-text available
Local Binary Patterns (LBP) is an texture feature, which is widely used in texture discrimination, face recognition, painting classification and other fields. The previous LBP feature extraction methods and many improved algorithms are all based on the gray scale image. Because there is information loss during the conversion from color image to gray image, the LBP methods need combine with other color features to improve the accuracy of classification. In this paper, a LBP encoding method for color image based on color space distance is proposed, which can not only directly achieve LBP feature from color image, but also can be applied to improve various previous methods. The experiment shows that color-based LBP method can filter background information better. With three different classifiers, the accuracy of classification which only used color-based LBP features is about 15% higher than that of existing LBP features. Finally, the application effect in local binary patterns histograms (LBPH) with color-based LBP further proves the advantage.
View
A deep-learning framework for human perception of abstract art composition
Article
Full-text available
Artistic composition (the structural organization of pictorial elements) is often characterized by some basic rules and heuristics, but art history does not offer quantitative tools for segmenting individual elements, measuring their interactions and related operations. To discover whether a metric description of this kind is even possible, we exploit a deep-learning algorithm that attempts to capture the perceptual mechanism underlying composition in humans. We rely on a robust behavioral marker with known relevance to higher-level vision: orientation judgements, that is, telling whether a painting is hung "right-side up." Humans can perform this task, even for abstract paintings. To account for this finding, existing models rely on "meaningful" content or specific image statistics, often in accordance with explicit rules from art theory. Our approach does not commit to any such assumptions/schemes, yet it outperforms previous models and for a larger database, encompassing a wide range of painting styles. Moreover, our model correctly reproduces human performance across several measurements from a new web-based experiment designed to test whole paintings, as well as painting fragments matched to the receptive-field size of different depths in the model. By exploiting this approach, we show that our deep learning model captures relevant characteristics of human orientation perception across styles and granularities. Interestingly, the more abstract the painting, the more our model relies on extended spatial integration of cues, a property supported by deeper layers.
View
Artificial Neural Networks and Deep Learning in the Visual Arts: a review
Article
Full-text available
In this article, we perform an exhaustive analysis of the use of Artificial Neural Networks and Deep Learning in the Visual Arts. We begin by introducing changes in Artificial Intelligence over the years and examine in depth the latest work carried out in prediction, classification, evaluation, generation, and identification through Artificial Neural Networks for the different Visual Arts. While we highlight the contributions of photography and pictorial art, there are also other uses for 3D modeling, including video games, architecture, and comics. The results of the investigations discussed show that the use of Artificial Neural Networks in the Visual Arts continues to evolve and have recently experienced significant growth. To complement the text, we include a glossary and table with information about the most commonly employed image datasets.
View
Context pre-modeling: an empirical analysis for classification based user-centric context-aware predictive modeling
Article
Full-text available
  • Jul 2020
Abstract Nowadays, machine learning classification techniques have been successfully used while building data-driven intelligent predictive systems in various application areas including smartphone apps. For an effective context-aware system, context pre-modeling is considered as a key issue and task, as the representation of contextual data directly influences the predictive models. This paper mainly explores the role of major context pre-modeling tasks, such as context vectorization by defining a good numerical measure through transformation and normalization, context generation and extraction by creating new brand principal components, context selection by taking into account a subset of original contexts according to their correlations, and eventually context evaluation, to build effective context-aware predictive models utilizing multi-dimensional contextual data. For creating models, various popular machine learning classification techniques such as decision tree, random forest, k-nearest neighbor, support vector machines, naive Bayes classifier, and deep learning by constructing a neural network of multiple hidden layers, are used in our study. Based on the context pre-modeling tasks and classification methods, we experimentally analyze user-centric smartphone usage behavioral activities utilizing their contextual datasets. The effectiveness of these machine learning context-aware models is examined by considering prediction accuracy, in terms of precision, recall, f-score, and ROC values, and has been made an empirical discussion in various dimensions within the scope of our study.
View
Warm, lively, rough? Assessing agreement on aesthetic effects of artworks
Article
Full-text available
The idea that simple visual elements such as colors and lines have specific, universal associations—for example red being warm—appears rather intuitive. Such associations have formed a basis for the description of artworks since the 18th century and are still fundamental to discourses on art today. Art historians might describe a painting where red is dominant as “warm,” “aggressive,” or “lively,” with the tacit assumption that beholders would universally associate the works’ certain key forms with specific qualities, or “aesthetic effects”. However, is this actually the case? Do we actually share similar responses to the same line or color? In this paper, we tested whether and to what extent this assumption of universality (sharing of perceived qualities) is justified. We employed—for the first time—abstract artworks as well as single elements (lines and colors) extracted from these artworks in an experiment in which participants rated the stimuli on 14 “aesthetic effect” scales derived from art literature and empirical aesthetics. To test the validity of the assumption of universality, we examined on which of the dimensions there was agreement, and investigated the influence of art expertise, comparing art historians with lay people. In one study and its replication, we found significantly lower agreement than expected. For the whole artworks, participants agreed on the effects of warm-cold, heavy-light, and happy-sad, but not on 11 other dimensions. Further, we found that the image type (artwork or its constituting elements) was a major factor influencing agreement; people agreed more on the whole artwork than on single elements. Art expertise did not play a significant role and agreement was especially low on dimensions usually of interest in empirical aesthetics (e.g., like-dislike). Our results challenge the practice of interpreting artworks based on their aesthetic effects, as these effects may not be as universal as previously thought.
View
Anomaly Detection and Classification of Household Electricity Data: A Time Window and Multilayer Hierarchical Network Approach
Article
  • Jul 2021
With the increasing popularity of the smart grid, huge volumes of data are gathered from numerous sensors. How to classify, store, and analyze massive datasets to facilitate the development of the smart grid has recently attracted much attention. In particular, with the popularity of household smart meters and electricity monitoring sensors, a large amount of data can be obtained to analyze household electricity usage so as to better diagnose the leakage and theft behaviors, identify man-made tampering and data fraud, and detect powerline loss. In this paper, the time window method is first proposed to obtain the features and potential periodicity of household electricity data. Combining the denoising ability of the autoencoder and the induction ability of the feedforward neural network, a multilayer hierarchical network (MLHN) is then established to detect anomalies in single sensor data and classify multiple groups of sensor data, respectively. The experimental results show that the accuracy of detecting abnormal data and data classification is significantly improved compared with the presented scheme.
View
Automatic orientation detection of abstract painting
Article
Detecting the correct orientation of an image is an important part of computer vision and the image processing pipeline. To determine the orientation of abstract paintings, as a special image type with ambiguous content, is difficult. There are several problems in the current orientation detection research: one is the use of a great deal of low-level image features for classification; the second is that the input image size is typically required to be consistent when using a deep learning model; the third is the problem of sample imbalance between the correct and incorrect orientations. To solve these problems, we propose a multi-scale and multi-layer feature fusion Net (MMFF-Net). First, local binary patterns (LBP) were used to generate three LBP-RGB feature maps with different scales in RGB mode, which could express the rotation characteristics of the image well; secondly, a neural network model based on AlexNet and spatial pyramid pooling (SPP) was constructed. Two data sets were selected to compare the training effect of different model parameters and model structures. Compared with the experimental results of several models, the proposed model effectively improved the accuracy of the correct orientation detection of abstract painting images.
View
Image Orientation Detection Using Convolutional Neural Network
Chapter
  • Oct 2020
Image orientation detection is often a prerequisite for many applications of image understanding and recognition. Recently, with the development of deep learning, mang significant Convolutional Neural Network (CNN) architectures are proposed and widely used in computer vision areas. In order to investigate the performance of CNN on image orientation detection task, in this paper, we first evaluate several famous CNN architectures, such as AlexNet, GoogleNet and VGGNet on this task, then we test a new CNN architecture by combining these networks. We collect six kinds of image, including landscape, block, indoor, human face, mail and natural images, in which the first three ones are regarded as difficult categories of orientation detection by previous work. The experiment results on these datasets indicate the effectiveness of the proposed network on image orientation detection task.
View