Image Content Analysis Research Articles

Flickr Photos Analysis for Beach Tourism Management in Bantul Regency, Indonesia: Popularity and Tourist Attractions

Photos shared by social media users act as an approach in identifying tourist activity. Popular tourist attractions are judged based on the large number of photos or high photo density. In Bantul Regency, Indonesia, beaches have diverse attractions which tourists can enjoy and immortalize through photos. Analyzing the contents of photos on Flickr provides information on the type(s) of beaches or coastal attractions preferred by tourists. This study examined the availability of geotagged Flickr photos to assist in making relevant beach tourism management policies. It employed pattern analysis with the average nearest neighbor, density analysis with kernel density estimation, image content analysis with tourist attraction as the variable, and overlay analysis to formulate recommendations for beach tourism management based on the popularity level of the attractions. The results indicate that each of the local beaches offers different attractions with varying popularity levels and that natural beauty is the main feature attracting tourists to visit all beaches, except Baros. Based on the pattern analysis, the Flickr photos are clustered on several beaches of high popularity, such as Parangtritis, Baros, Depok, and Cemara Sewu. By using geotagged Flickr photo data and refers to the concept of tourism supply and demand, recommendations for developing the attractive features on these beaches have been compiled according to their respective themes and popularity levels to target specific tourist market segments and design integrated tour or travel packages.

Commodification of Urban Space and the Image of ‘New’ Istanbul

This study aims to identify the urban transformation strategy implemented in Istanbul for the last 15 years as a tool to promote the ‘new’ city discourse. This marking strategy leads to a thoroughly manipulated or re-written urban texture, constructed through concepts of identity, context and historicism. By decoding its actors, their roles, and branding images of five selected urban projects which relied on a top-down approach, the research exposes the implicit and explicit targets behind the political discourse of ‘new’ İstanbul. Through a qualitative content analysis of branding images and promotional media, the research focuses on the unseen agenda of the governing authority concerning the urban image and the state economy, which, on the contrary, undermines legitimate laws covering disaster mitigation. The conceptual framework of the study draws on Tafuri’s (1969) seminal article "Toward a Critique of Architectural Ideology" to deepen our examination of the leading forces of urban ideology that are reshaping the city. The article aims to spark a debate over the ‘new’ Istanbul discourse and its planning practices through its re-reading of urban projects, the field of architecture and planning, development strategies, and their relevant actors.

Commodification of Urban Space and the Image of ‘New’ Istanbul: Decoding the prevailing discourse

This study aims to identify the urban transformation strategy implemented in Istanbul for the last 15 years as a tool to promote the ‘new’ city discourse. This marking strategy leads to a thoroughly manipulated or re-written urban texture, constructed through concepts of identity, context and historicism. By decoding its actors, their roles, and branding images of five selected urban projects which relied on a top-down approach, the research exposes the implicit and explicit targets behind the political discourse of ‘new’ İstanbul. Through a qualitative content analysis of branding images and promotional media, the research focuses on the unseen agenda of the governing authority concerning the urban image and the state economy, which, on the contrary, undermines legitimate laws covering disaster mitigation. The conceptual framework of the study draws on Tafuri’s (1969) seminal article "Toward a Critique of Architectural Ideology" to deepen our examination of the leading forces of urban ideology that are reshaping the city. The article aims to spark a debate over the ‘new’ Istanbul discourse and its planning practices through its re-reading of urban projects, the field of architecture and planning, development strategies, and their relevant actors.

An Educational Approach to Critical Content Analysis of Visual Images in Picturebooks for Young Readers

An Educational Approach to Critical Content Analysis of Visual Images in Picturebooks for Young Readers 의 이용 수, 등재여부, 발행기관, 저자, 초록, 목차, 참고문헌 등 논문에 관한 다양한 정보 및 관련논문 목록과 논문의 분야별 BEST, NEW 논문 목록을 확인 하실 수 있습니다.

REMEDYING THE POLLUTION OF ATHI RIVER IN KENYA

The Athi River, which is 390 km before entering the Indian Ocean, is the second-longest river in Kenya. As it flows through the grasslands and valleys of Kenya, the river forms the majestic Fourteen Falls, meanders through Nairobi, and eventually passes through Tsavo National Park, the largest in Kenya. Here, hippopotamus, crocodiles, and pythons are attracted to the river’s waters and the life it carries. Millions of Kenyans rely on the Athi River for drinking water and irrigation. However, the Athi River also receives large amounts of pollution from Nairobi–an area with a population of over four million people. Along with population growth and rapid urbanization, poor solid waste management is emerging as a key risk for health in Kenya. The river is increasingly choking with uncollected garbage; human waste from informal settlements; industrial waste in the form of gaseous emissions, liquid affluence, and solids waste; agrochemicals, and other wastes especially petrochemicals and metals from microenterprises – the hot sun and overflowing sewers. This situation has occasioned the spread of waterborne diseases, loss of sustainable livelihoods, loss of biodiversity, reduced availability and access to safe potable water, and various toxic substances and heavy metal poisoning, affecting human productivity. The paper is not empirically grounded and its content is a result of desktop research and content analysis of literature, images, and news related to pollution. The paper hopes to provoke further deliberations and empirical research on the river.

Slow tourism on Instagram: an image content and geotag analysis

ABSTRACT Slow tourism is a holistic tourism concept that promotes sustainability in all aspects of a traveller’s journey. Slow tourism promotes positive outcomes for local communities such as stimulating local economies and minimising aversive environmental impacts; however, little is known about what the term ‘slow tourism’ means to tourists. The current study analysed 600 user generated images including the hashtag ‘slowtourism’ on Instagram to determine the locations and activities associated with slow tourism on the social media platform. Images were coded for geotag location and elements including landscapes, architecture, and transport. Results indicated most images were from Italy and France, and while some trends emerged such as images commonly featuring natural landscapes and architecture, there was substantial variance of content within these trends which suggests that people are associating a variety of types of tourism destinations and architecture with slow tourism. However other elements of slow tourism such as culinary experiences and transportation choices were evident less frequently. This research highlights how social media can be used to effectively investigate trends and future research opportunities within the tourism sector.

Places of Joy and Worries

Facebook (FB) has increasingly entered the daily lives of Latvians, and, as in other countries, the various virtual communities created within this social network site are directly connected to or even derived from communities existing in the physical world, such as place-based. This article focuses on two such virtual communities that have emerged as groups of residents of Rīga city neighbourhoods, focusing on the analysis of the images posted in these groups. There are several research questions which are centred on the neighbourhood places that are depicted in the FB posts. What do they say about the everyday mobility and borders of the neighbourhood? What places cause joy and worries? How do these visual representations differ in two FB groups? In exploring these questions, both qualitative and quantitative approaches and methods were used. An additional methodological question arose: which of these approaches is the optimal way for such a small-scale ad hoc study? At the end of this pilot study, it was concluded that the visual content (mainly photographs) generated by FB groups of urban residents is a valuable reference material that helps researchers understand specific neighbourhoods as if they were looking through the eyes of residents. Their vision has recorded not only the places of their neighbourhood. Comparing the content of the two FB groups, there are significant differences in this regard. By combining qualitative and quantitative image content analysis, more reliable results can be achieved, but at the same time, quantitative content analysis (both sampling and image coding) require relatively huge resources, especially if the aim is to automate workflow, which raises the question of how rational the use of this or that approach is.

Enhanced Content-Based Image Retrieval Using Information Oriented Angle-Based Local Tri-Directional Weber Patterns

In diverse computer applications, the analysis of image content plays a key role. This image content might be either textual (like text appearing in the images) or visual (like shape, color, texture). These two image contents consist of image’s basic features and therefore turn out to be as the major advantage for any of the implementation. Many of the art models are based on the visual search or annotated text for Content-Based Image Retrieval (CBIR) models. There is more demand toward multitasking, a new method needs to be introduced with the combination of both textual and visual features. This paper plans to develop the intelligent CBIR system for the collection of different benchmark texture datasets. Here, a new descriptor named Information Oriented Angle-based Local Tri-directional Weber Patterns (IOA-LTriWPs) is adopted. The pattern is operated not only based on tri-direction and eight neighborhood pixels but also based on four angles [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text]. Once the patterns concerning tri-direction, eight neighborhood pixels, and four angles are taken, the best patterns are selected based on maximum mutual information. Moreover, the histogram computation of the patterns provides the final feature vector, from which the new weighted feature extraction is performed. As a new contribution, the novel weight function is optimized by the Improved MVO on random basis (IMVO-RB), in such a way that the precision and recall of the retrieved image is high. Further, the proposed model has used the logarithmic similarity called Mean Square Logarithmic Error (MSLE) between the features of the query image and trained images for retrieving the concerned images. The analyses on diverse texture image datasets have validated the accuracy and efficiency of the developed pattern over existing.

Listening to Heartbeat: the pulse of ecofeminism in a picturebook

Using an ecofeminist theoretical frame along with critical content analysis of visual images, this article examines the environmental discourse of the picturebook, Heartbeat, written and illustrated by Evan Turk (2018). In this picturebook, Turk uses the heartbeat, the history, and the song of a whale to draw the reader into a sense of cosmic interconnectivity with nature. This critical content analysis of Heartbeat seeks to extend the research on evaluating environmental children’s literature by taking a deeper look at the specific ways the images and text in Heartbeat provide a unique and much needed counter-narrative to the devaluation and domination of nature.

Content-based medical image retrieval using a novel hybrid scattering coefficients - bag of visual words - DWT relevance fusion

Image content analysis plays a major role in image classification, retrieval, and indexing together with object and scene recognition. Numerous image content descriptors are proposed in the literature, but their high computational costs and lower-performance scores make them inappropriate for content-based medical image retrieval (CBMIR) for large medical image datasets. To overcome these drawbacks, a novel hybrid Scattering Coefficients - Bag of Visual Words – Discrete Wavelet Transform (SC-BoVW- DWT) relevance fusion algorithm is proposed for effective CBMIR. For preprocessing, resizing and contrast limited adaptive histogram equalization (CLAHE) are carried out. Then scattering transform (ST), BoVW and DWT are applied to extract texture features, visual features, and low-level features of the preprocessed images respectively. A hybrid Grey Wolf Optimization - Particle Swarm Optimization (GWO-PSO) approach is used for optimal feature selection. Finally, image fusion (IF) is carried out with a relevance fusion based Euclidean distance technique. Experiments based on three standard medical computer tomography image databases namely, EXACT-09, TCIA-CT and NEMA-CT, are carried out. The proposed hybrid method outperforms the existing techniques in terms of precision, F-score, and recall values. Improvement in the average rate of precision (ARP), average rate of recall (ARR) and F-score values of 6.02%, 2.82% and 3.57% respectively, for the EXACT-09 dataset and 3.55%, 1.84%, and 2.12% respectively for the TCIA-CT dataset are observed compared with the existing Scattering Transform- canonical correlation analysis vertical projection (ST-CCAv). For NEMA-CT an improvement of 0.21% (ARP) is obtained compared with the existing Histogram of compressed scattering coefficients (HCSC).

Framing Women’s Roles in Twentieth-Century Farming: A Content Analysis of Cover Images from Successful Farming and the Farm Journal

This content analysis examined how women were portrayed throughout the twentieth century on the covers of two high-circulation farm magazines. Coders identified gender, age, activity, gendered stereotypes, and predominance of the figures in 801 farm magazine cover images. Findings suggest an underrepresentation and stereotypical portrayal of women on the covers throughout the twentieth century. This research contributes to an understanding of the framing role of farm magazines in the representation of women’s contributions to agriculture.

Image Source Identification Using Convolutional Neural Networks in IoT Environment

Digital image forensics is a key branch of digital forensics that based on forensic analysis of image authenticity and image content. The advances in new techniques, such as smart devices, Internet of Things (IoT), artificial images, and social networks, make forensic image analysis play an increasing role in a wide range of criminal case investigation. This work focuses on image source identification by analysing both the fingerprints of digital devices and images in IoT environment. A new convolutional neural network (CNN) method is proposed to identify the source devices that token an image in social IoT environment. The experimental results show that the proposed method can effectively identify the source devices with high accuracy.

Образ Петра I в структуре политического сознания современников (на примере анализа сообщений в социальных сетях)

Objective. Analysis of the psychological characteristics of the image of Peter I in the structure of the political consciousness of users of the social network Twitter. Background. The leading basis of the study is the provision on the subjective determination of political consciousness, which manifests itself in the multiple attitudes of people to the same facts of history. Secondly, the phenomenon of historical memory is one of the important foundations of the national self-identification of an individual, and manipulation of political consciousness becomes a means of influencing the self-consciousness of a person and society. Thirdly, it is important to turn to “digital” research technologies, which is associated with the promising development of scientific technologies and the acquisition of socially significant knowledge relevant to society as a whole. Methodology. Concepts of image psychology, structural and content analysis of messages, methods of grounded theory, neural network model, analysis of the emotional background of short non-formalized texts. Conclusions. It was revealed that the image of Peter I is highly appreciated in the field of international, military, economic, educational, legislative and administrative activities and is due to his outstanding achievements at the international and domestic political levels. At the same time, the development of political institutions under the emperor is not assessed so highly and unequivocally, the social essence of state administration and the rejection of the cultural traditions of the people are subjected to the greatest criticism. In particular, analysis of the emotional background of messages showed that the bulk of user messages differ in a moderately negative or neutral background.

ПРОГІБІЦІОНІСТСЬКИЙ РУХ У США: ПАРТІЯ СУХОГО ЗАКОНУ У КАРИКАТУРІ КІНЦЯ ХІХ – ПОЧАТКУ ХХ СТ.

The present paper has three main objectives: 1) to cover the history of American temperance movements at the turn of the 19th-20th centuries, and their key characteristics; 2) to trace the Prohibition Party history and activity; 3) to do a content-analysis of «Prohibition Cartoons» published in 1904 to support the Prohibition Party candidates to the House of Representatives. Research methodology provides a critical approach to interpreting cartoons based on E. Panofsky’s three strata analysis from the primary subject through conventional subject matter to intrinsic content. Quantitative and qualitative content analysis of images and accompanying texts revealed the frequency of specific themes, images, allusions that authors had used. The scientific novelty lies in studying the history of the Prohibition Party through the prism of its propaganda visual materials, the possibilities of their influence on voters. The Conclusions. Alcohol consumption was a part of Americans’ usual way of life and diet. The American Revolution and postwar economic and financial troubles were the main circumstances that formed this habit. Temperance organizations, both national and local, have been active since the 1820s and were closely associated with denominational groups. Saloons as a source of liquor, gambling, prostitution, and crime were the main objects of their criticism. They also condemned the governmental license system as a promoter of liquor traffic. Lack of systemic funding and propaganda, and the split of 1896 sharply reduced the Prohibition Party chances of becoming a real opponent for the Republicans or Democrats. Content analysis of cartoons demonstrated a range of symbols, allusions, and metaphors, which should influence public opinion. The majority of them called to vote for the Prohibition Party. Cartoons content a lack of emphasis on the harm of alcohol to human physical and mental health.

An Intelligent Ubiquitous Learning Environment and Analytics on Images for Contextual Factors Analysis

Contextual factors in which learning occurs are crucial aspects that learning analytics and related disciplines aim to understand for optimizing learning and the environments in which learning occurs. In foreign vocabulary development, taking the notes or memos of learning contexts along with other factors, play an essential role in quick memorization and reflection. However, conventional tools fail to automate the learning contexts generation process as learners still need to take memos or e-notes to describe their vocabulary learning contexts. This paper presents the Image Understanding Project (hereafter IUEcosystem) that could produce smartly-generated learning contexts primarily in a learner’s target languages. The IUEcosystem uses visual content analysis of lifelogging images as the sensor data to produce smartly-generated learning contexts that could be used as an alternative to handwritten memos or electronic notes. The IUEcosystem uses applied artificial intelligence to produce smartly-generated learning contexts. This intelligent learning environment collects a learner’s learning satisfaction and interaction data and, later on, analyzes them to produce time-based notifications for enhancing retention. Furthermore, a new learning design is presented that aims to map a learner’s prior vocabulary knowledge with new learning vocabularies to be learned. This learning design would help learners to review and recall prior knowledge while learning new vocabulary.

The impact of social media on self-evaluations of men striving for a muscular ideal.

This paper describes an innovative approach combining a content analysis of commentary and images on a Facebook page with a thematic analysis of the subjective experience expressed in interviews of those impacted by the text and images. Interview participants were asked about their perceptions of the representation of the muscularity-focused identity on social media, including the specific Facebook page. Content analysis of the Facebook page comments showed that very muscular male images attracted predominantly negative feedback from the public, a trend supported by the interview participants. Thematic analysis of the interviews indicated that a negative social media representation and commentary can affect young men's self-esteem and increase body concern. Some men represented on the Page found it humorous, which could serve as a form of bonding for the muscularity-focused online community. Other young men acknowledged how harmful such negative feedback can be on their self-evaluations and body image, consistent with the sociocultural framework whereby negative representations can lead to increased body dissatisfaction.

Is this what a female yogi looks like? A content analysis of yoga images on Instagram

As yoga continues to increase in global popularity, idealized representations of a thin, athletic ‘yoga body’ have also become more prominent across commercial media. To examine how yoga is typically represented on social media, a content analysis of the posts of female yoga practitioners on Instagram was undertaken. Images were sourced using hashtags #yoga, #yogabody, #yogapractice, and #yogawoman, and 200 females per hashtag were then coded on demographic factors, body shape, activity, objectification, and practice of yoga. Results showed that over 90 % of women in the images were coded as being under 40 years of age with the vast majority in their 20 s. Almost three-quarters of women were perceived to be white, 100 % appeared able bodied. More than 80 % were classed as thin and/or athletic, while less than 15 % displayed average levels of visible body fat. More than 50 % of yoga poses were advanced while a quarter displayed potentially unsafe alignment. The findings demonstrate that the typical ‘yoga body’ on Instagram was perceived to conform to the young, thin/athletic ideal and that overall yoga is not being represented as an inclusive physical practice that can be adapted for women of diverse ages, body types, and abilities.

Promotion of inclusive tourism by national destination management organizations

Purpose Inclusive tourism has the potential to counter balance some of the disadvantages relating to tourism development and effectively exert positive impacts on society at large and specifically on tourist destinations. However, there is a research gap in studies on inclusiveness related to the promotional efforts of national destination management organizations. Design/methodology/approach Data science-based methods, mainly text mining and image mining, were used to analyze both the explicit and implicit content in text and images in the English brochures published by nine European official destination management organizations. Findings Results highlighted that the countries' attitudes towards inclusion were aligned with what the countries’ destination management organizations were promoting, especially in the case of highly ranked countries on an inclusiveness index. However, there were differences between their explicit content (what they write in text) and their implicit content (what they show in images). Originality/value The combined analysis of text and image content allowed for a complete understanding as to how national’s destination management organizations are promoting inclusion, showing that destination management organizations should make an effort in improving their promotional material and above all the images they use.

A scalable sub-graph regularization for efficient content based image retrieval with long-term relevance feedback enhancement

The goal of content-based image retrieval (CBIR) is to search relevant images through the analysis of image content. Manifold Ranking (MR) and Efficient Manifold Ranking (EMR) method has been successfully applied to content-based image retrieval due to its ability to discover underlying geometrical structure of dataset given the query data. But given the image database is scalable, the graph in MR and EMR cannot be extended or updated as their graph size is fixed. In this paper, to solve the above problem, we consider to formulate a sub-graph based on fixed anchors, instead of constructing the graph based on the while dataset, where the anchors are selected by utilizing conventional k-means method and the sub-graph weight matrix is defined by the similarity between any pair-wise anchors. Since the number of anchors is much smaller than the original dataset, updating the sub-graph is much easier than the original graph of whole dataset. Motivated by such sub-graph construction, we then develop an efficient graph regularization framework to predict the ranking scores for the whole data along the sub-graph, where the ranking score is first propagated from query image to the partial anchors, then from partial anchors to all anchors via the sub-graph and finally to the whole dataset. It can also utilize user relevance feedbacks to update the sub-graph so that the discriminative information can be involved to enhance the retrieval performance in a long term. Extensive simulations verify the effectiveness of the proposed method.

Spatiotemporal retrieval of dynamic video object trajectories in geographical scenes

AbstractCurrent studies on video trajectory retrieval focus on the retrieval and analysis of image content, neglecting the gap between the spatiotemporal continuity of retrieval conditions and the spatiotemporal discontinuity of multi‐camera video trajectories. In this study, we propose a method for the spatiotemporal retrieval of dynamic video object trajectories in geographic scenes. Based on the camera calibration, the proposed method organizes the scene, cameras, and trajectories, constructs the spatiotemporal constraints, and queries the trajectories using two measures: camera‐by‐camera retrieval and global trajectory retrieval. The proposed method was verified through experiments, and the results demonstrate that both measures can query trajectories effectively and reduce the spatiotemporal video review range under different spatiotemporal constraints. Furthermore, compared with camera‐by‐camera retrieval, global trajectory retrieval can reduce the spatiotemporal video review range further and return more accurate results. The proposed method may provide support for the spatial analysis and understanding of surveillance video data.