Image Recoloring with Valence‐Arousal Emotion Model

Kim, Hye-Rin; Kang, Hyung Seok; Lee, In-Kwon

doi:10.1111/cgf.13018

Cited by 16 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially in recent years, with the rapid development of economy, college students need to cultivate better ability to resist pressure, which requires excellent psychological quality. Psychological counseling service in Colleges and universities has developed rapidly in recent years, but there is still a big gap with the demand of college students for psychological counseling service [12][13].…”

Section: Psychological Counseling Servicementioning

confidence: 99%

Retracted: Psychological Counseling and Character Analysis Algorithm Based on Image Emotion

Cao

Zhang

2024

IEEE Access

View full text Add to dashboard Cite

The number of image video is increasing at an amazing speed because of its intuitive image and strong information integration. The semantic analysis of image emotion has a broad application prospect and practical value. The purpose of this study is to conduct psychological counseling and personality analysis on the emotion expressed by computer images. In this study, the sun database image database data set is selected to establish a mathematical model of the data, through linear combination of multiple indicators, and convert them into several unrelated indicators, but it can maintain the large amount of information contained in the original indicators, the emotional semantic data is analyzed by principal component analysis, and then combined with classification algorithm to analyze the image emotion character.The results show that the accuracy of character analysis of image emotion reaches 73.55% on average when the binary tree depth = 3. The recognition rate is the highest when the threshold value is 0.8, and the recognition accuracy is 77.33%. It is concluded that the classification algorithm in this study has good accuracy and accuracy for image emotion recognition, and can provide psychological counseling and personality analysis for the emotion contained in the image. It has contributed to the character analysis and mental health of network users.

show abstract

Section: Psychological Counseling Servicementioning

confidence: 99%

Retracted: Psychological Counseling and Character Analysis Algorithm Based on Image Emotion

Cao

Zhang

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“… used crowdsourcing only for the pilot study (e.g., [TGH12]); used crowdsourcing not for evaluation but for other purposes such as data collection (e.g., user generated layouts [KDMW16, KWD14, vHR08]); evaluated graphics but no information visualization (e.g., [BCER14,XADR13,KKL16]); evaluated user interfaces but no information visualization (e.g., [DCS*17,MBB*11,RYM*13]); evaluated human‐computer interaction but no information visualization (e.g., [MMS*08, KWS*14,DH08]); proposed a novel crowdsourcing platform (e.g., [TBRA17,EKR16]); used already available data maintained by a crowdsourcing platform without using crowdsourcing (e.g., [KHA16,DDW11]); discussed previous crowdsourcing studies without using crowdsourcing (e.g., [AJB16, ZGB*17,KH16]); mentioned the use of crowdsourcing for future evaluation (e.g., [HLS16]). …”

Section: Methodsmentioning

confidence: 99%

Information Visualization Evaluation Using Crowdsourcing

Borgo

Micallef

Bach

et al. 2018

Computer Graphics Forum

View full text Add to dashboard Cite

Visualization researchers have been increasingly leveraging crowdsourcing approaches to overcome a number of limitations of controlled laboratory experiments, including small participant sample sizes and narrow demographic backgrounds of study participants. However, as a community, we have little understanding on when, where, and how researchers use crowdsourcing approaches for visualization research. In this paper, we review the use of crowdsourcing for evaluation in visualization research. We analyzed 190 crowdsourcing experiments, reported in 82 papers that were published in major visualization conferences and journals between 2006 and 2017. We tagged each experiment along 36 dimensions that we identified for crowdsourcing experiments. We grouped our dimensions into six important aspects: study design & procedure, task type, participants, measures & metrics, quality assurance, and reproducibility. We report on the main findings of our review and discuss challenges and opportunities for improvements in conducting crowdsourcing studies for visualization research.

show abstract

“…Ali et al [1] have studied how high level concepts present in the images are related to the affect they induce. [7,17,18] have used the datasets to learn and/or transfer the emotion to the input image. Xue et al [18] model low-level color and tone features to represent different emotions of the movie clip clustered on the basis of genre and director of the film.…”

Section: Image Emotion Assignmentmentioning

confidence: 99%

“…Kim et al [7] instead of over-segmenting the input image use semantic segmentation. For each input-image-segment, semantically compatible segments are searched from the database while minimizing on position, scale, lightness of the segment and closeness of user supplied Valance Arousal (VA) score to VA score of the image to whom selected segment belongs to.…”

Section: Image Emotion Assignmentmentioning

confidence: 99%

“…In this paper, we present a framework for image transformation such that the transformed source image has the affect, as desired by the user. Unlike previous methods [7,12,17], in our algorithm user has to input only the source image and seven dimensional discrete probability distribution representing ratio of seven emotions (anger, disgust, fear, joy, sadness, surprise and neutral). We use features extracted from top layers of deep convolutional networks (that encapsulate both in-image-context and content information) to select target images that have similar content and spatial context as the source image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Image transformation for inducing affect

Ali¹,

Rafaqat²

2017

Procedings of the British Machine Vision Conference 2017

View full text Add to dashboard Cite

Current image transformation and recoloring algorithms try to introduce artistic effects in the photographed images, based on user input of target image(s) or selection of pre-designed filters. These manipulations, although intended to enhance the impact of an image on the viewer, do not include the option of image transformation by specifying the affect information. In this paper we present an automatic image-transformation method that transforms the source image such that it can induce an emotional affect on the viewer, as desired by the user. Our proposed novel image emotion transfer algorithm does not require a user-specified target image. The proposed algorithm uses features extracted from top layers of deep convolutional neural network and the user-specified emotion distribution to select multiple target images from an image database for color transformation, such that the resultant image has desired emotional impact. Our method can handle more diverse set of photographs than the previous methods. We conducted a detailed user study showing the effectiveness of our proposed method. A discussion and reasoning of failure cases has also been provided, indicating inherent limitation of color-transfer based methods in the use of emotion assignment.

show abstract

Image Recoloring with Valence‐Arousal Emotion Model

Cited by 16 publications

References 32 publications

Retracted: Psychological Counseling and Character Analysis Algorithm Based on Image Emotion

Retracted: Psychological Counseling and Character Analysis Algorithm Based on Image Emotion

Information Visualization Evaluation Using Crowdsourcing

Automatic Image transformation for inducing affect

Contact Info

Product

Resources

About