Image Emotional Classification Based on Color Semantic Description

Wei, Kaiping; He, Bin; Zhang, Tao; He, Wei

doi:10.1007/978-3-540-88192-6_47

Cited by 17 publications

(23 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The principal strategy is based on faces detection, an emotion is then associated with facial features (such as eyebrows, lips). The other major approach is the detection of emotions from the characteristics of the image [1,4,5,7,12]. Considering these two approaches, it is interesting to compute the model on a part of images for many reasons.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Can Salient Interest Regions Resume Emotional Impact of an Image?

Gbèhounou

Lecellier

Fernández-Maloigne

et al. 2013

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. The salient regions of interest are supposed to contain the interesting keypoints for analysis and understanding. We studied in this paper the impact of image reduction to the region of interest on the emotion recognition. We chose a bottom-up visual attention model because we addressed emotions on a new low-semantic data set SENSE (Studies of Emotion on Natural image databaSE). We organized two experimentations. The first one has been conducted on the whole images called SENSE1 and the second on reduced images named SENSE2. These latter are obtained with a visual attention model and their size varies from 3% to 100% of the size of the original ones. The information collected during these evaluations are the nature and the power of emotions. For the nature observers have choice between "Negative", "Neutral" and "Positive" and the power varies from "Weak" to "Strong". On the both experimentations some images have ambiguous categorization. In fact, the participants were not able to decide on their emotional class (Negative, Neutral ans Positive). The evaluations on reduced images showed that average 79% of the uncategorised images during SENSE1 are categorized during SENSE2 in one of the both major classes. Reducing the size of the area to be observed leads to a better evaluation maybe because some semantic content are attenuated.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Several papers explore emotions extraction domain [4,5,7,8,12] and propose different approaches to extract emotion of the images. The principal strategy is based on faces detection, an emotion is then associated with facial features (such as eyebrows, lips).…”

Section: Introductionmentioning

confidence: 99%

Can Salient Interest Regions Resume Emotional Impact of an Image?

Gbèhounou

Lecellier

Fernández-Maloigne

et al. 2013

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…Thus, to distinguish them, it is important to predict affects from image. Due to this importance, the researches for human affects have been actively progressed [3][4][5][6][7][8][9][10][11][12]. Therefore, main goal of the current work is to develop a fully autonomous prediction system for various affects from visual features.…”

Section: Introductionmentioning

confidence: 99%

Affective prediction in photographic images using probabilistic affective model

Shin

Kim

2010

Proceedings of the ACM International Conference on Image and Video Retrieval

View full text Add to dashboard Cite

With increasing the importance of affective computing, it becomes necessary to retrieve and process images according to human affects or preference. However, judging such affective qualities of images is a highly subjective task. In spite of the lack of firm rules, certain features in images are believed to be more related than certain others. In this paper, we suggest predicting certain affective features include in an image using color composition that constitutes the scene. Using such a feature is inspired from Kobayashi's color scale that studies the relation between colors/color compositions and human's affects. Thus, we propose a Probabilistic Affective Model (PAM) to estimate the probabilities that an image is related to certain affective features. For this, we segment an image using mean-shift clustering algorithm, and extract more important regions, which are called seed regions, based on their properties. Thereafter, we find the dominant color compositions among those seed regions and their neighboring regions. Finally, from such color compositions, we infer the numerical ratings for some affective features. To assess the effectiveness of our PAM, we compared its results with 52 users' affective judgments. It was tested with online photo images, then the results show our PAM produced the recall of 85.22% and the precision of 78.16% on average. Potential applications include content-based image retrieval and design of web page interfaces.

show abstract

“…Certaines émotions peuvent être confondues (la peur et la colère par exemple) ou non représentées du tout (entre autre la surprise) dans un modèle bidimensionnel de type valence/éveil. Dans la littérature, beaucoup de travaux se basent sur une modélisation discrète des émotions par exemple ceux de Wei et al [20], Paleari et Huet [15], Kaya et Epps [6]. Plusieurs approches ont été développées pour l'extraction des émotions des images.…”

Section: Introductionunclassified

“…L'autre grande famille de travaux est celle de la détec-tion des émotions basée sur les caractéristiques de l'image [20,14,10 [2], évoquent l'idée selon laquelle des lignes obliques communiqueraient du dynamisme et de l'action alors que des lignes horizontales ou verticales du calme et de la relaxation. Au vu de la littérature, nous avons choisi de nous inscrire dans cette famille d'approches d'extraction de caractéristiques.…”

Section: Introductionunclassified

Extraction et analyse de l’impact émotionnel des images

Gbèhounou¹,

Lecellier²,

Fernández-Maloigne³

2012

Traitement du signal

View full text Add to dashboard Cite

RésuméCet article propose une méthode d'extraction de l'impact émotionnel des images à partir de descripteurs récents. Très souvent, on associe les émotions à l'expression du visage, mais nous avons décidé de ne pas faire de cette information la principale information émotionnelle des images naturelles, qui en général ne contiennent pas de visages. Nous avons ainsi effectué nos tests sur une base diversifiée, construite à partir d'images à faible contenu sémantique. La complexité des émotions a été prise en compte en inté-grant, au processus de classification, les résultats de tests psycho-visuels que nous avons mis en place. Vingt cinq observateurs ont participé aux tests. Ils ont évalué la nature et la puissance des émotions ressenties. Nous avons choisi un réseau de neurones multicouches pour la classification. Le taux de réussite moyen obtenu lors de la classification est de 56,15% ; ce qui est encourageant au regard des résultats de la littérature. Mots Clef Émotions, réseaux de neurones, tests psycho-visuels, couleurs AbstractThis paper proposes a method to extract the emotional impact of images. Emotions are often associated with facial expressions, but we decided not to consider this feature as first emotional characteristic of natural images, which, in general, does not contain faces. Using this statement, our tests have been done on a new image database composed of low semantic diversified images. The complexity of emotion modeling was considered in classification process through psycho-visual tests. The twenty five observers assessed the nature and the power of emotions felt. We used an artificial neural network for classification. The average success rate is 56,15% ; that is really relevant regarding the equivalent results in the literrature.

show abstract

Image Emotional Classification Based on Color Semantic Description

Cited by 17 publications

References 3 publications

Can Salient Interest Regions Resume Emotional Impact of an Image?

Can Salient Interest Regions Resume Emotional Impact of an Image?

Affective prediction in photographic images using probabilistic affective model

Extraction et analyse de l’impact émotionnel des images

Contact Info

Product

Resources

About