Cartoon Images Research Articles

Aplikasi Pengenalan Identitas Gambar Dengan Menggunakan Metode Backpropagation

With today's technological developments, many types of identifier systems have been developed for the benefit of users of the technology. This recognition system is used for some objects or also on humans. Image recognition applications have great hopes for the future. Start with the introduction of sketch images or static photos in a certain format. Of course, this is supported by the development of science and technology in the fields of image processing, analysis, and image understanding. To recognize the identity of the image so far it is very rare, but in this study describes how to identify the identity of the image with human photos. The image (image) in question is an image or human image whose identity is not known. Currently, many manipulate images or photos with the same image. However, it is not known which one was manipulated and which one was genuine. Based on these problems, it is necessary to apply an identity recognition system so that it can be known which ones are manipulated and which ones are genuine, by applying the backpropagation method. According to previous research entitled facial recognition applications using the backpropagation algorithm and voila jones with the authors Sayuti Rahman, Emil Fitranhah, Andi Marwan Elhanafi stated that to be able to recognize a person's image with the backpropagation algorithm, one must go through several stages of training and testing stages. Image is a method found in artificial neural networks. Where the artificial neural network is an artificial representation of the human brain which always tries to simulate the learning process in the human brain. one of them is the backpropagation method, backpropagation is one of the artificial neural network models that has the ability to get a balance between the network's ability to recognize the patterns used during training and the network's ability to provide the correct response to input patterns that are similar (but not the same) with the same pattern. used during training.

Recognition of cartoon-based e-cigarette-related marketing is associated with e-cigarette use among adolescents

IntroductionRecent research has shown that e-cigarette companies use cartoon-based marketing. Recognition of this cartoon-based marketing has been associated with increased risk for e-cigarette use in young adults, however it is unclear if this generalizes to adolescents. This study examined the associations between recognition of e-liquid packaging with cartoons and e-cigarette use, susceptibility to use, and expectations of benefits and risks of use in adolescents. MethodsA cross-sectional sample of adolescents drawn from three Southern California high schools (n = 1,734; 55% female; Mean [SD] age = 15.2[0.9]) completed online surveys assessing e-cigarette use, susceptibility to use, expectations about benefits and risks of use, and tobacco marketing exposure. To assess recognition of cartoon images, participants were presented with 40 images of e-liquid packages (20 with and 20 without cartoons) and asked to endorse whether they recognized the products. The primary predictor was relative cartoon recognition (i.e., percentage of cartoons recognized out of the total images recognized). ResultsRelative recognition of cartoon images was positively associated with e-cigarette use, susceptibility to use, and a perceived social benefit of use. ConclusionsAdolescents recognize e-cigarette-related cartoon marketing, and these adolescents are using e-cigarettes. The restriction of cartoon-based marketing of e-cigarettes may affect e-cigarette uptake among adolescents.

LineGAN: An image colourisation method combined with a line art network

The work on grayscale image colourisation has been significantly improved. Currently, learning-based methods have achieved some great colourisation effects, but existing colour edge bleeding, especially when colourful cartoon characters. In this paper, we focus on the colourisation of cartoon characters from a series in an adversarial environment with a line art network, whose name is LineGAN. LineGAN learns the corresponding colour mapping from datasets, improving the accuracy of image colourisation. Our methods limit the colour boundary overflow by adding a line art frame in the generator. Extensive experiment results on cartoon image colourisation tasks demonstrate that the proposed method can achieve effective results.

Understanding vaginal hysterectomy for pelvic organ prolapse

The objective of the video is to create a patient-facing education video about how to choose a vaginal surgeon for surgical treatment of pelvic organ prolapse. Fifth-grade-level explanations of hysterectomy route, vaginal hysterectomy steps, complications, and convalescence are described using cartoon images. We believe that perhaps other vaginal surgeons and SGS will find this educational tool helpful when counseling patients.

Sketch-Based Image Retrieval Using Novel Edge Detector and Feature Descriptor

With the explosive increase of digital images, intelligent information retrieval systems have become an indispensable tool to facilitate users’ information seeking process. Although various kinds of techniques like keyword-/content-based methods have been extensively investigated, how to effectively retrieve relevant images from a large-scale database remains a very challenging task. Recently, with the wide availability of touch screen devices and their associated human-computer interaction technology, sketch-based image retrieval (SBIR) methods have attracted more and more attention. In contrast to keyword-based methods, SBIR allows users to flexibly manifest their information needs into sketches by drawing abstract outlines of an object/scene. Despite its ease and intuitiveness, it is still a nontrivial task to accurately extract and interpret the semantic information from sketches, largely because of the diverse drawing styles of different users. As a consequence, the performance of existing SBIR systems is still far from being satisfactory. In this paper, we introduce a novel sketch image edge feature extraction algorithm to tackle the challenges. Firstly, we propose a Gaussian blur-based multiscale edge extraction (GBME) algorithm to capture more comprehensive and detailed features by continuously superimposing the edge filtering results after Gaussian blur processing. Secondly, we devise a hybrid barycentric feature descriptor (RSB-HOG) that extracts HOG features by randomly sampling points on the edges of a sketch. In addition, we integrate the directional distribution of the barycenters of all sampling points into the feature descriptor and thus improve its representational capability in capturing the semantic information of contours. To examine the efficiency of our method, we carry out extensive experiments on the public Flickr15K dataset. The experimental results indicate that the proposed method is superior to existing peer SBIR systems in terms of retrieval accuracy.

Realistic galaxy image simulation via score-based generative models

ABSTRACT We show that a denoising diffusion probabilistic model (DDPM), a class of score-based generative model, can be used to produce realistic mock images that mimic observations of galaxies. Our method is tested with Dark Energy Spectroscopic Instrument (DESI) grz imaging of galaxies from the Photometry and Rotation curve OBservations from Extragalactic Surveys (PROBES) sample and galaxies selected from the Sloan Digital Sky Survey. Subjectively, the generated galaxies are highly realistic when compared with samples from the real data set. We quantify the similarity by borrowing from the deep generative learning literature, using the ‘Fréchet inception distance’ to test for subjective and morphological similarity. We also introduce the ‘synthetic galaxy distance’ metric to compare the emergent physical properties (such as total magnitude, colour, and half-light radius) of a ground truth parent and synthesized child data set. We argue that the DDPM approach produces sharper and more realistic images than other generative methods such as adversarial networks (with the downside of more costly inference), and could be used to produce large samples of synthetic observations tailored to a specific imaging survey. We demonstrate two potential uses of the DDPM: (1) accurate inpainting of occluded data, such as satellite trails, and (2) domain transfer, where new input images can be processed to mimic the properties of the DDPM training set. Here we ‘DESI-fy’ cartoon images as a proof of concept for domain transfer. Finally, we suggest potential applications for score-based approaches that could motivate further research on this topic within the astronomical community.

Research on the Application of Deep Learning Technology Oriented to the Construction and Innovation of Smart City Image Cognition

City image is the observer’s subjective impression of the city image. It is an important content of urban geography and planning research and has important guiding significance for shaping a unique urban space. Cognitive research on traditional urban imagery is mainly by means of questionnaires and image sketches. It has problems such as high cost, low update frequency, and limited data coverage, which cannot meet the needs of quantitative research on smart cities and urban economic development in the information age. With the advent of the era of big data and the development of Internet technology, there are more and more quantitative research results on smart city image cognition with the help of big data and deep learning technology. It will be a feasible way to apply it to urban image research. This article combines the development and transformation of smart cities with the transformation of urban planning and leads to an innovation in the construction of urban image cognition based on urban image, active representation data as the data source, and deep learning as the core technology. The theoretical connotation and cognitive dimension of urban imagery are expanded to establish a cognitive model of urban imagery. The city image is cognitively analyzed from three dimensions: image structure, image type, and image evaluation. Specific cities are taken as examples to verify the applicability and scientificity of the cognitive methods and models, so as to enhance the practicality and applicability of urban imagery in urban planning. At the same time, this research is used to answer the development dilemma of big data, summarize the development trend of big data, and explore the new changes that artificial intelligence brings to urban planning. The experimental results show that the model we designed efficiently evaluates the image of the city and can also effectively recognize the image of the city in the main urban area of Chongqing.

Cross-Domain Attention and Center Loss for Sketch Re-Identification

Matching all RGB photos of the target person in the gallery database with the full-body sketch image drawn by the professional is defined as Sketch re-identification (Sketch Re-id). The big gap between the sketch domain and RGB domain makes Sketch Re-id challenging. This paper addresses the problem by proposing a new framework to obtain domain-invariant features, which uses CNN as the backbone. To make the model focus more on the regions related to the sketch image in the RGB photo, we propose a novel cross-domain attention (CDA) mechanism. It uses different ways of splitting feature maps in its two branches and calculates the relationship between different parts in the sketch images and RGB photos. Moreover, we designed the cross-domain center loss (CDC), which breaks through the limitations that datasets need to be in the same domain in the traditional center loss. It effectively reduces the gap between two domains and makes the features with the same ID closer. The experiment is performed on the Sketch Re-id dataset. Each person has one sketch image and two RGB photos. To evaluate the generalization, we also experimented on two popular sketch-photo face datasets. The result in the Sketch Re-id dataset shows the model performs 3.7% higher than the previous methods. And the result in the CUHK student dataset performs 0.38% higher than the state-of-the-art methods.

CartoonLossGAN: Learning Surface and Coloring of Images for Cartoonization.

Cartoonization as a special type of artistic style transfer is a difficult image processing task. The current existing artistic style transfer methods cannot generate satisfactory cartoon-style images due to that artistic style images often have delicate strokes and rich hierarchical color changes while cartoon-style images have smooth surfaces without obvious color changes, and sharp edges. To this end, we propose a cartoon loss based generative adversarial network (CartoonLossGAN) for cartoonization. Particularly, we first reuse the encoder part of the discriminator to build a compact generative adversarial network (GAN) based cartoonization architecture. Then we propose a novel cartoon loss function for the architecture. It can imitate the process of sketching to learn the smooth surface of the cartoon image, and imitate the coloring process to learn the coloring of the cartoon image. Furthermore, we also propose an initialization strategy, which is used in the scenario of reusing the discriminator to make our model training easier and more stable. Extensive experimental results demonstrate that our proposed CartoonLossGAN can generate fantastic cartoon-style images, and outperforms four representative methods.

Representation and Memory in Graphic Novels by Golnar Nabizadeh

Reviewed by: Representation and Memory in Graphic Novels by Golnar Nabizadeh Yun Lan Golnar Nabizadeh, Representation and Memory in Graphic Novels. London: Routledge, 2019. 208 pp. The past decade has witnessed an explosive interest in graphic narrative, which was once dismissed as frivolous and heterodox but is now praised as innovative and flexible in its ability to accommodate both fiction and nonfiction and to address an array of topics, old or new. Among thought-provoking studies such as Hillary L. Chute's Graphic Women: Life Narrative and Contemporary Comics (2010), Elisabeth El Refaie's Autobiographical Comics: Life Writing in Pictures (2012), Karin Kukkonen's Contemporary Comics Storytelling (2013) and Studying Comics and Graphic Novels (2013), Daniel Stein and Jan-Noël Thon's From Comic Strips to Graphic Novels (2013), Achim Hescher's Reading Graphic Novels (2016), Kai Mikkonen's The Narratology of Comic Art (2017), and Bettina Kümmerling-Meibauer's The Routledge Companion to Picturebooks (2018), Golnar Nabizadeh's Representation and Memory in Graphic Novels is noteworthy for its original focus. It centers on the issue of how marginalized and minority groups reproduce their memories in comic form. Nabizadeh attempts to do justice to the enormous potential of a word-image alliance to "materialize" the past, contending that the fragmented panels, the gutters, and the drawings in comics document the episodic, imaginative, reconstructive, and visual nature of memory, especially traumatic memory. Comics are valorized as an effective medium for the socially excluded and the neglected to challenge authoritative discourses and to make their suppressed voices heard. The ethics of comics that stand for occluded voices is showcased in Nabizadeh's selection of the works analyzed. The book covers memory of sundry types of human experience and shows how the texts discussed, incorporating both fictional and non-fictional, realistic and non-realistic constituents, represent individual and collective memories through multifarious visual techniques, media, and distribution channels. Chapter 1 examines two graphic narratives that display the experience of immigrant arrival in foreign countries. When analyzing Henry Yoshitaka Kiyama's The Four Immigrants Manga: A Japanese Experience in San Francisco, 1904–1924 [Manga Yonin Shosei] (1999 [1931]), Nabizadeh attends to the work's major technical features: humor, cinematic and comic elements, the appropriation of Western art styles, bilingual conversations, and, most importantly, references to influential historical events—for instance, "The Turlock Incident"—which are interconnected with episodes embodying the immigrants' painful memories. When coming to Shaun Tan's The Arrival (2006), which reproduces the experience of an unnamed migrant in an unknown place, Nabizadeh dissects references to historical facts as well as the artistic and conceptual inspirations that the book draws from films, pictures, and literary works. She discusses the material features of the book—the spine, the cover, the page color, the use of a gold ribbon—which contribute to a sense of nostalgia and make the book [End Page 179] resemble a mysterious photographic album. Through an insertion of other migrants' narratives into the main account, this wordless "photo album" serves as a repository for memories, visually representing the traumatic past and vulnerability of immigrants from distinct backgrounds. Nabizadeh also shows how iconic elements such as origami and gestures buttress the representation of the immigration experience. Chapter 2 continues the theme of immigration with Gene Luen Yang's American Born Chinese (2006) and Pat Grant's Blue (2012) but from a different angle, that of cultural identity and exclusion, as well as the ways in which the two authors strive to dismantle the stereotypes that the hegemonic "us" imposed on the "other." In her historical and cultural unpacking of American Born Chinese, Nabizadeh demonstrates how notoriously negative cartoon images of Chinese people give birth to the stereotype Cousin Chin-Kee that the protagonist is desperate to break away from. The deliberate placement of Chin-Kee in sitcom context self-reflexively manifests the flatness of both the medium and the image of the Chinese in the West. The book interweaves three story lines, which "mimics the compartmentalisation that can take place with regards to difficult memories" (66), as in the protagonist's "cultural amnesia" (71). If American Born Chinese reflects on the internal apprehension of "otherness," Blue, dealing with the...

A Study of Culture Metaphor and Conceptual Metaphor in the Film “Zootopia”

Metaphor is a figure of speech. In order to achieve rhetorical effect, it directly uses one thing to describe another thing. It may provide (or blur) clarity or identify hidden similarities between two things. “Zootopia”, an animated film produced by Disney, has swept around the world since its release. From this story, the children enjoyed the lovely cartoon image and the power of justice. Teenagers felt the efforts for the pursuits. However in adult perspective, there are metaphors everywhere in the city of wild animals. The application of metaphors in this film will bring strong astonishment and inspiration.

Bilateral Filtering Based Image Cartoon Stylization Design

With the rapid development of multimedia technology and rising demand for entertainment, comic-styled images are increasingly becoming a necessity of life. Cartoonists can produce comic stylized works by making comic-style modifications to real images, but this is laborious and time-consuming. By extracting the features of comic style paintings, we can analyze the differences of comics relative to real images in terms of contrast, presentation, and color, and thus write computer programs to perform comic stylized processing of images. In this paper, we extract the features of comics and use MATLAB tool to write the corresponding feature transformation program to get the comic stylized images step by step, so as to achieve the effect of fast comic stylization of images. Then the images are selected to validate the program, and the analysis concludes that the program has advantages such as fast and good effect, and also has shortcomings such as elimination of details and single style.

Responses to e-cigarette health messages among young adult sexual minoritized women and nonbinary people assigned female at birth: Assessing the influence of message theme and format

BackgroundYoung adult sexual minority women (YSMW) report disproportionate e-cigarette (EC) use and low EC harm perceptions. Health messages that effectively communicate EC harms to YSMW are needed. We tested the effect of culturally targeted EC health messages with varying themes and image formats on attitudes and intentions to use ECs in this population. MethodsN = 501 YSMW and nonbinary people assigned female at birth (AFAB) aged 18–30 years-old completed an online experiment. Participants were randomized into a control or one of nine experimental conditions in a 3 (theme: harms, wellness, pride) by 3 (image format: individual, couple, cartoon) study design. We modeled associations between message condition and message effectiveness, discouragement from vaping, change in feelings toward vaping, perceived threat, and intentions to abstain from vaping. ResultsAmong YSMW and nonbinary people AFAB, harm and wellness themes discouraged vaping more than pride-themed messages (p’s < 0.001). Harms messages resulted in worse feelings about vaping than wellness and pride messages (p’s < 0.02). Images of couples were perceived as more effective than cartoon images (p = .008). Among current EC users, viewing images of individuals resulted in greater readiness to avoid ECs and higher intentions to abstain than the couple or cartoon conditions (p’s < 0.001). ConclusionsMessage theme and image format were associated with YSMW and nonbinary people AFAB’s EC attitudes and behavioral intentions. Future studies should evaluate how to optimize harms messages; including if wellness or pride messages can be re-framed to better affect EC use in this population.

Research on the Style Characteristics of Network Hosts

There is a distinct difference between the network host style and the traditional host style. Wang Nima, as the "most positive host of three views of speech", is very successful in thinking from the perspective of social psychology. Wang Nima has become one of the symbols of the violent image subculture group through the styles of hiding identity, symbolized cartoon image, symbolized audio language and paralanguage expression, phonetic vocabulary grammar deviation and so on. The use of Wang Nima's image can better stimulate the audience to communicate and deliver the program. At the same time, the youth subculture audience speaks and spits with "opinion leaders" such as Wang Nima, and "opinion leaders" such as Wang Nima become spokespersons with obvious group characteristics. However, its disadvantage is that it can influence the public opinion trend of news on the Internet, and further interfere with the consciousness of individual thinking in the group.

Image Sketch Based Criminal Face Recognition Using Content Based Image Retrieval

Purpose: Face recognition is a geometric space recording activity that allows it to be used to distinguish the features of a face. Therefore, facial recognition can be used to identify ID cards, ATM card PINs, search for one’s committed crimes, terrorists, and other criminals whose faces were not caught by Close-Circuit Television (CCTV). Based on the face image database and by applying the Content-Base Image Retrieval method (CBIR), committed crimes can be recognized on his face. Moreover, the image segmentation technique was carried out before CBIR was applied. This work tried to recognize an individual who committed crimes based on his or her face by using sketch facial images as a query. Methods: We used an image sketch as a querybecause CCTV could not have caught the face image. The research used no less than 1,000 facial images were carried out, both normal as well asabnormal faces (with obstacles). Findings:Experiments demonstrated good enough in terms of precision and recall, which are 0,8 and 0,3 respectively, which is better than at least two previous works.The work demonstrates a precision of 80% which means retrieval of effectiveness is good enough. The 75 queries were carried out in this work to compute the precision and recall of image retrieval. Novelty: Most face recognition researchers using CBIR employed an image as a query. Furthermore, previous work still rarely applied image segmentation as well as CBIR.

Generating faces From the Sketch Using GAN

Abstract: In most cases, sketch images simply show basic profile details and do not include facial detail. As a result, precisely generating facial features is difficult. Using the created adversarial network and attributes, we propose an image translation network. A feature extracting network and a down-sampling up-sampling network make up the generator network. There is a generator and a discriminator in GANs. The Generator creates fake data samples (images, audio, etc.) in intended to mislead the Discriminator. On the other hand, the Discriminator attempts to distinguish between the real and fake sample Keywords: Deep Learning, Generative Adversarial Networks, Image Translation, face generation, skip-connection.

Reference-guided structure-aware deep sketch colorization for cartoons

Digital cartoon production requires extensive manual labor to colorize sketches with visually pleasant color composition and color shading. During colorization, the artist usually takes an existing cartoon image as color guidance, particularly when colorizing related characters or an animation sequence. Reference-guided colorization is more intuitive than colorization with other hints, such as color points or scribbles, or text-based hints. Unfortunately, reference-guided colorization is challenging since the style of the colorized image should match the style of the reference image in terms of both global color composition and local color shading. In this paper, we propose a novel learning-based framework which colorizes a sketch based on a color style feature extracted from a reference color image. Our framework contains a color style extractor to extract the color feature from a color image, a colorization network to generate multi-scale output images by combining a sketch and a color feature, and a multi-scale discriminator to improve the reality of the output image. Extensive qualitative and quantitative evaluations show that our method outperforms existing methods, providing both superior visual quality and style reference consistency in the task of reference-based colorization.

Printing Infidelity: Watson Heston and the Making of the Impressionable Freethinking Subject, 1873–1900

Nineteenth-century print media provided a set of metaphors with which American unbelievers began to articulate an understanding of religious infidelity as something permanent. Ink, paper, pencil, and mechanical printing technologies served as symbols for articulating disbelief as something imprinted indelibly on the mind of the reading or viewing subject. Thus, over the course of the nineteenth century, American nonbelievers began discussing infidelity less in terms of something rationally subscribed to and more in terms of something non-rationally imprinted at a young age. At the same time, the late nineteenth century witnessed an increasing emphasis on a militaristic understanding of missionary activity incumbent upon American infidels—a tendency partially enabled by understandings of the cartoon image as a tool suited to the defeat of believers and the creation of young unbelievers.

Cartoon Image of the Mother, Its Perception by Elementary School Students and Correction in the Process of Media Education

This article presents a psychological study of the mother image projected in cartoons and its perception by elementary school students. The research provides evidence for the importance of an integral approach to the analysis of media texts addressed to children, as well as for the necessity of considering their narrative, verbal, and descriptive components. A psychological analysis was conducted on the material of three cartoons: “Chunya” (USSR), “Barboskiny” [The Barkers] (Russia), and “Peppa Pig” (UK). Hypotheses were formulated about the potential influence of the cartoons on the younger audience. 70 elementary school students (ꭓ̅ = 9.5 years old) took part in the study. The research was conducted using the method of semantic differential; the data obtained were processed using factor analysis. The results show that the categorization of images follows the factors of “education”, “love”, “patience”, and “respect”. Differences in the semantic assessment of the cartoons under study are presented. Children perceive the events taking place in a cartoon directly, without reflection. Artistic mediation—polysemy, metaphors, and the category of the comic—does not evoke an aesthetic reaction in children, as assumed by the authors. It was found that the semantic assessment of the word “mother” by elementary school students did not agree with the traditional cultural status of a mother. Thus, the respondents ranked such indicators as “understanding” and “prestige” at a low level. A developmental experiment was conducted to correct the mother image as perceived by elementary school students. During the experimental program (8 lessons in total), the schoolchildren watched and discussed the cartoons together with a psychologist. At the end of the experiment, the semantic assessment of the verbal stimulus “mom” by the respondents showed a statistically significantly increase (р≤0.05) in the indicators of “understanding” and “prestige”.

Application of Deep Learning Algorithms to Visual Communication Courses.

There are rare studies on the combination of visual communication courses and image style transfer. Nevertheless, such a combination can make students understand the difference in perception brought by image styles more vividly. Therefore, a collaborative application is reported here combining visual communication courses and image style transfer. First, the visual communication courses are sorted out to obtain the relationship between them and image style transfer. Then, a style transfer method based on deep learning is designed, and a fast transfer network is introduced. Moreover, the image rendering is accelerated by separating training and execution. Besides, a fast style conversion network is constructed based on TensorFlow, and a style model is obtained after training. Finally, six types of images are selected from the Google Gallery for the conversion of image style, including landscape images, architectural images, character images, animal images, cartoon images, and hand-painted images. The style transfer method achieves excellent effects on the whole image besides the part hard to be rendered. Furthermore, the increase in iterations of the image style transfer network alleviates lack of image content and image style. The image style transfer method reported here can quickly transmit image style in less than 1 s and realize real-time image style transmission. Besides, this method effectively improves the stylization effect and image quality during the image style conversion. The proposed style transfer system can increase students’ understanding of different artistic styles in visual communication courses, thereby improving the learning efficiency of students.