scholarly journals A Dataset and a Convolutional Model for Iconography Classification in Paintings

2021 ◽  
Vol 14 (4) ◽  
pp. 1-18
Author(s):  
Federico Milani ◽  
Piero Fraternali
Keyword(s):  
Visual Features ◽  
Correct Identification ◽  
Automatic Extraction ◽  
Digital Archives ◽  
Visual Content ◽  
Average Precision ◽  
Religious Paintings ◽  
Active Research ◽  
Research And Education ◽  
And Diffusion

Iconography in art is the discipline that studies the visual content of artworks to determine their motifs and themes and to characterize the way these are represented. 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 of influences across artists and artworks. With the proliferation of digital archives of art images, the possibility arises of applying Computer Vision techniques to the analysis of art images at an unprecedented scale, which may support iconography research and education. In this article, we introduce a novel paintings dataset for iconography classification and present the quantitative and qualitative results of applying a Convolutional Neural Network ( CNN ) classifier to the recognition of the iconography of artworks. The proposed classifier achieves good performances (71.17% Precision, 70.89% Recall, 70.25% F1-Score, and 72.73% Average Precision) in the task of identifying saints in Christian religious paintings, a task made difficult by the presence of classes with very similar visual features. Qualitative analysis of the results shows that the CNN focuses on the traditional iconic motifs that characterize the representation of each saint and exploits such hints to attain correct identification. The ultimate goal of our work is to enable the automatic extraction, decomposition, and comparison of iconography elements to support iconographic studies and automatic artwork annotation.

scholarly journals A survey on compact features for visual content analysis

2016 ◽  
Vol 5 ◽  
Author(s):  
Luca Baroffio ◽  
Alessandro E. C. Redondi ◽  
Marco Tagliasacchi ◽  
Stefano Tubaro
Keyword(s):  
Content Analysis ◽  
Large Scale ◽  
Ad Hoc ◽  
State Of The Art ◽  
Large Body ◽  
Visual Features ◽  
Low Latency ◽  
Visual Content ◽  
Feature Encoding ◽  
Memory Footprint

Visual features constitute compact yet effective representations of visual content, and are being exploited in a large number of heterogeneous applications, including augmented reality, image registration, content-based retrieval, and classification. Several visual content analysis applications are distributed over a network and require the transmission of visual data, either in the pixel or in the feature domain, to a central unit that performs the task at hand. Furthermore, large-scale applications need to store a database composed of up to billions of features and perform matching with low latency. In this context, several different implementations of feature extraction algorithms have been proposed over the last few years, with the aim of reducing computational complexity and memory footprint, while maintaining an adequate level of accuracy. Besides extraction, a large body of research addressed the problem of ad-hoc feature encoding methods, and a number of networking and transmission protocols enabling distributed visual content analysis have been proposed. In this survey, we present an overview of state-of-the-art methods for the extraction, encoding, and transmission of compact features for visual content analysis, thoroughly addressing each step of the pipeline and highlighting the peculiarities of the proposed methods.

scholarly journals An Optimized Approach for Annotation of Large Eukaryotic Genomic Sequences using Genetic Algorithm

2016 ◽  
Author(s):  
Biswanath Chowdhury ◽  
Arnav Garai ◽  
Gautam Garai
Keyword(s):  
Genetic Algorithm ◽  
Gene Prediction ◽  
Research Area ◽  
Chromosome 21 ◽  
Correct Identification ◽  
Coding Regions ◽  
Comparable Performance ◽  
Benchmark Datasets ◽  
New Gene ◽  
Active Research

ABSTRACTDetection of important functional and/or structural elements and identifying their positions in a large eukaryotic genome is an active research area. Gene is an important functional and structural unit of DNA. The computation of gene prediction is essential for detailed genome annotation. In this paper, we propose a new gene prediction technique based on Genetic Algorithm (GA) for determining the optimal positions of exons of a gene in a chromosome or genome. The correct identification of the coding and non-coding regions are difficult and computationally demanding. The proposed genetic-based method, named Gene Prediction with Genetic Algorithm (GPGA), reduces this problem by searching only one exon at a time instead of all exons along with its introns. The advantage of this representation is that it can break the entire gene-finding problem into a number of smaller subspaces and thereby reducing the computational complexity. We tested the performance of the GPGA with some benchmark datasets and compared the results with the well-known and relevant techniques. The comparison shows the better or comparable performance of the proposed method (GPGA). We also used GPGA for annotating the human chromosome 21 (HS21) using cross species comparison with the mouse orthologs.

scholarly journals COLOR FEATURE WITH SPATIAL INFORMATION EXTRACTION METHODS FOR CBIR: A REVIEW

2019 ◽  
Vol 45 (1) ◽  
pp. 15-19
Author(s):  
Sarmad Abdul-samad
Keyword(s):  
Feature Extraction ◽  
Image Retrieval ◽  
Information Extraction ◽  
Spatial Information ◽  
Extraction Methods ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Visual Content ◽  
Color Feature ◽  
Color Correlogram

Inn then last two decades the Content Based Image Retrieval (CBIR) considered as one of the topic of interest for theresearchers. It depending one analysis of the image’s visual content which can be done by extracting the color, texture and shapefeatures. Therefore, feature extraction is one of the important steps in CBIR system for representing the image completely. Color featureis the most widely used and more reliable feature among the image visual features. This paper reviews different methods, namely LocalColor Histogram, Color Correlogram, Row sum and Column sum and Colors Coherences Vectors were used to extract colors featurestaking in consideration the spatial information of the image.

From a Traditional to an Entrepreneurial University

2020 ◽  
pp. 142-165
Author(s):  
Dino Arnaut
Keyword(s):  
Young People ◽  
Research University ◽  
Entrepreneurial University ◽  
University Funding ◽  
Entrepreneurial Skills ◽  
Triple Helix Model ◽  
Traditional Research ◽  
Career Option ◽  
Research And Education ◽  
And Diffusion

The transformation of a traditional research university to an entrepreneurial university is increasing because of the reduction in university funding from government sources and the constant emergence of a competitive market for research and education. A new approach has emerged, focusing on promoting the spillover of knowledge through university entrepreneurship. The creation of an entrepreneurial culture and the movement towards a Triple Helix model is a complex task that requires the efforts of many dedicated individuals. Universities as centres for knowledge creation and diffusion can be leveraged to generate future economic growth. For small transition countries, it is important that universities operate under policies that encourage entrepreneurship and innovation. The education of young people about entrepreneurship represents a highly valuable preparation for constant changes in the labour market. Entrepreneurial education is crucial to help young people develop entrepreneurial skills, attributes, and behaviour, as well as to embrace entrepreneurship as a career option.

scholarly journals Museum-Authorization of Digital Rights: A Sustainable and Traceable Cultural Relics Exhibition Mechanism

2021 ◽  
Vol 13 (4) ◽  
pp. 2046 ◽  
Author(s):  
Yun-Ciao Wang ◽  
Chin-Ling Chen ◽  
Yong-Yuan Deng
Keyword(s):  
Digital Rights Management ◽  
Practical Significance ◽  
Digital Content ◽  
Digital Archives ◽  
Digital Rights ◽  
Digital Signature Algorithm ◽  
Rights Management ◽  
Research And Education ◽  
Innovation Approach ◽  
Cultural Relics

The digital rights management of museums is a mechanism that protects digital content from being abused by controlling and managing its usage rights. Traditional museums attach importance to the collection, display, research, and education functions of “objects”. In response to natural or man-made disasters, people are often caught off guard, destroying material, intangible assets, and spiritual symbolism. Therefore, with the advancement of digital technology, this research is based on the mechanism of blockchain, through the authorization of cryptographic proxy re-encryption, and proposes a new method for the preservation and authorization of digital content in museums, which can effectively display, store, and promote “important cultural relics and digital archives”. In this research, the Elliptic Curve Digital Signature Algorithm (ECDSA), blockchain, and smart contracts are used to design a sustainable and traceable cultural relic exhibition mechanism. The proposed scheme achieves publicly verifiable, transparency, unforgeability, traceability, non-repudiation, standardization of stored data, timeliness, etc., goals. It is the museum’s preservation and innovation approach for the unpredictable future. Through appropriate preservation and management mechanisms, it has extremely important practical significance for the protection of museum collections, the inheritance of historical and cultural heritage, and the expansion of social education.

scholarly journals Exploiting Visual Content of Book Front Cover to Aggrandize the Content Based Book Recommendation System

2019 ◽  
Vol 8 (12) ◽  
pp. 1631-1634
Keyword(s):  
Recommendation System ◽  
Current User ◽  
User Preferences ◽  
Visual Features ◽  
Visual Content ◽  
Front Cover ◽  
Product Features ◽  
Scientific Papers ◽  
Textual Features ◽  
Content Based Filtering

In modern e-commerce world Recommendation Systems are playing a key role in supporting customers to take a decision. With this kind of services customers can choose comfortably the products as per their preferences from a long list of available products. It’s not only a boon for the customers; it will boost the sales for the organization and generate better revenues. Due to diverse domain characteristics, each domain requires different kinds of recommendation models. Content based recommendation model is one of the recommendation models which purely rely on product features and the current user preferences. This model is more effective for the domains like news, micro-blogs, books, movie plots and scientific papers etc. In this paper we propose a content-based filtering model for book recommender system by utilizing its overall textual features as well as visual features of its front cover. Numerous surveys have demonstrated that book readers are highly inclined to its covers that are visually attractive1 . Book front cover is the first representative candidate of the book that will reveal the overall sense of the book; hence we considered book front cover as one of the book contents along with the text. Our experiment shows that augmenting the visual features to the existing content-based recommender models performed well.

scholarly journals Comparison of YOLO v3, Faster R-CNN, and SSD for Real-Time Pill Identification

2021 ◽  
Author(s):  
Lu Tan ◽  
Tianran Huangfu ◽  
Liyao Wu ◽  
Wenying Chen
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Hospital Pharmacy ◽  
Correct Identification ◽  
Single Shot ◽  
Average Precision ◽  
Basic Principles ◽  
Image Dataset ◽  
The Mean ◽  
Detection Speed

Abstract Background: The correct identification of pills is very important to ensure the safe administration of drugs to patients. We used three currently mainstream object detection models, respectively Faster R-CNN, Single Shot Multi-Box Detector (SSD), and You Only Look Once v3(YOLO v3), to identify pills and compare the associated performance.Methods: In this paper, we introduce the basic principles of three object detection models. We trained each algorithm on a pill image dataset and analyzed the performance of the three models to determine the best pill recognition model. Finally, these models are then used to detect difficult samples and compare the results.Results: The mean average precision (MAP) of Faster R-CNN reached 87.69% but YOLO v3 had a significant advantage in detection speed where the frames per second (FPS) was more than eight times than that of Faster R-CNN. This means that YOLO v3 can operate in real time with a high MAP of 80.17%. The YOLO v3 algorithm also performed better in the comparison of difficult sample detection results. In contrast, SSD did not achieve the highest score in terms of MAP or FPS.Conclusion: Our study shows that YOLO v3 has advantages in detection speed while maintaining certain MAP and thus can be applied for real-time pill identification in a hospital pharmacy environment.

A New Content-Based Image Retrieval System Using Deep Visual Features

2021 ◽  
pp. 2150055
Author(s):  
Mohamed Hamroun ◽  
Karim Tamine ◽  
Frederic Claux ◽  
Mourad Zribi
Keyword(s):  
Image Retrieval ◽  
Feature Vector ◽  
Texture Features ◽  
Pso Algorithm ◽  
Image Feature ◽  
Combination Method ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Average Precision ◽  
Food Category

Content-based image retrieval (CBIR) is a technique for images retrieval based on their visual features, i.e. induced by their pixels. The images are, classically, described by the image feature vectors. Those vectors reflect the texture, color or a combination of them. The accuracy of the CBIR system is highly influenced by the (i) definition of the image feature vector describing the image, (ii) indexing and (iii) retrieval process. In this paper, we propose a new CBIR system entitled ISE (Image Search Engine). Our ISE system defines the optimum combination of color and texture features as an image feature vector, including the Particle Swarm Optimization (PSO) algorithm and employing an Interactive Genetic Approach (GA) for the indexing process. The performance analysis shows that our suggested PCM (Proposed Combination Method) upgrades the average precision metric from 66.6% to 89.30% for the “Food” category color histogram, from 77.7% to 100% concerning CCVs (Color Coherence Vectors) for the “Flower” category and from 58% to 87.65% regarding the DCD (Dominant Color Descriptor) for the “Building” category using the Corel dataset. Besides, our ISE system showcases an average precision of 98.23%, which is significantly higher than other CBIR systems presented in related works.

From a Traditional to an Entrepreneurial University

2021 ◽  
pp. 607-630
Author(s):  
Dino Arnaut
Keyword(s):  
Young People ◽  
Research University ◽  
Entrepreneurial University ◽  
University Funding ◽  
Entrepreneurial Skills ◽  
Triple Helix Model ◽  
Traditional Research ◽  
Career Option ◽  
Research And Education ◽  
And Diffusion

The transformation of a traditional research university to an entrepreneurial university is increasing because of the reduction in university funding from government sources and the constant emergence of a competitive market for research and education. A new approach has emerged, focusing on promoting the spillover of knowledge through university entrepreneurship. The creation of an entrepreneurial culture and the movement towards a Triple Helix model is a complex task that requires the efforts of many dedicated individuals. Universities as centres for knowledge creation and diffusion can be leveraged to generate future economic growth. For small transition countries, it is important that universities operate under policies that encourage entrepreneurship and innovation. The education of young people about entrepreneurship represents a highly valuable preparation for constant changes in the labour market. Entrepreneurial education is crucial to help young people develop entrepreneurial skills, attributes, and behaviour, as well as to embrace entrepreneurship as a career option.

Sign in / Sign up

Export Citation Format

Share Document