Research on Image Emotional Semantic Retrieval Mechanism Based on Cognitive Quantification Model

In the wake of the development of first-person engagement and crowdsourcing content creation, images are given abundant subjective dimensions of information, especially emotional ones. This research tried to purpose an approach for the image emotional semantic retrieval based on cognitive quantification model by using tags. In this research “Daqi”, a typical Chinese emotional experience, is taken as an example to construct an emotional quantification model of it through semantic association analysis and statistical data analysis. The results of verification experiments indicated that it is practical and effective to rank images and recommend tags in image emotional retrieval system based on cognitive model. It is foreseeable that the theory of this research can be applied to other social digital resources, like music or video.

[1]  Toru Fukumoto.  An analysis of image retrieval behavior for metadata type image database , 2006, Inf. Process. Manag..

[2]  Qiang Yang,et al.  A unified framework for semantics and feature based relevance feedback in image retrieval systems , 2000, ACM Multimedia.

[3]  Ying Liu,et al.  A survey of content-based image retrieval with high-level semantics , 2007, Pattern Recognit..

[4]  Emmanuel Dellandréa,et al.  Multimodal recognition of visual concepts using histograms of textual concepts and selective weighted late fusion scheme , 2013, Comput. Vis. Image Underst..

[5]  Allan Hanbury,et al.  A survey of methods for image annotation , 2008, J. Vis. Lang. Comput..

[6]  Lei Wu,et al.  Tag Completion for Image Retrieval , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Jorma Laaksonen,et al.  Analyzing Emotional Semantics of Abstract Art Using Low-Level Image Features , 2011, IDA.

[8]  Sourav S. Bhowmick,et al.  Tag-based social image retrieval: An empirical evaluation , 2011, J. Assoc. Inf. Sci. Technol..

[9]  J. Fernando Sánchez-Rada,et al.  Onyx: A Linked Data approach to emotion representation , 2016, Inf. Process. Manag..

[10]  Graeme Hirst,et al.  Evaluating WordNet-based Measures of Lexical Semantic Relatedness , 2006, CL.

[11]  Wolfgang G. Stock,et al.  Collective indexing of emotions in images. A study in emotional information retrieval , 2009 .

[12]  Qianhua He,et al.  A survey on emotional semantic image retrieval , 2008, 2008 15th IEEE International Conference on Image Processing.

[13]  Krystyna K. Matusiak.  Information Seeking Behavior in Digital Image Collections: A Cognitive Approach , 2006 .

[14]  Thierry Pun,et al.  Learning from User Behavior in Image Retrieval: Application of Market Basket Analysis , 2004, International Journal of Computer Vision.

[15]  Yu Ying-lin,et al.  Image Retrieval by Emotional Semantics: A Study of Emotional Space and Feature Extraction , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[16]  Erik Cambria,et al.  Sentic Computing: Exploitation of Common Sense for the Development of Emotion-Sensitive Systems , 2009, COST 2102 Training School.

[17]  Xue Li,et al.  Low-rank image tag completion with dual reconstruction structure preserved , 2016, Neurocomputing.

[18]  Marc Schröder,et al.  Representing Emotions and Related States in Technological Systems , 2011 .

[19]  Qi Tian,et al.  Interactive social group recommendation for Flickr photos , 2013, Neurocomputing.

[20]  K. Scherer.  What are emotions? And how can they be measured? , 2005 .

[21]  Mor Naaman,et al.  Why we tag: motivations for annotation in mobile and online media , 2007, CHI.

[22]  P. Zimmermann,et al.  Affective Computing—A Rationale for Measuring Mood With Mouse and Keyboard , 2003, International journal of occupational safety and ergonomics : JOSE.