Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  Mustapha OUJAOURA.  Combining Generative And Discriminative Classifiers For Semantic Automatic Image Annotation , 2014 .

[3]  Ling Guan,et al.  Multi-feature pLSA for combining visual features in image annotation , 2011, ACM Multimedia.

[4]  Philippe Leray,et al.  Réseaux bayésiens : Apprentissage et diagnostic de systemes complexes , 2006 .

[5]  Zhihua Chen,et al.  Multilabel Image Annotation Based on Double-Layer PLSA Model , 2014, TheScientificWorldJournal.

[6]  Yong Yang,et al.  Evaluating Feature Combination in Object Classification , 2011, ISVC.

[7]  Cong Jin,et al.  Automatic image annotation using feature selection based on improving quantum particle swarm optimization , 2015, Signal Process..

[8]  Luciano Serafini,et al.  Mixing Low-Level and Semantic Features for Image Interpretation - A Framework and a Simple Case Study , 2014, ECCV Workshops.

[9]  Ajimi Ameer,et al.  Efficient Automatic Image Annotation using Weighted Feature Fusion and its Optimization using Genetic Algorithm , 2015 .

[10]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[11]  Sabine Barrat,et al.  Modèles graphiques probabilistes pour la reconnaissance de formes. (Probabilistic graphical models for shape recognition) , 2009 .

[12]  Dong ping Tian,et al.  A Review on Image Feature Extraction and Representation Techniques , 2013 .

[13]  Tom. Mitchell.  GENERATIVE AND DISCRIMINATIVE CLASSIFIERS: NAIVE BAYES AND LOGISTIC REGRESSION Machine Learning , 2005 .

[14]  Chee-Way Chong,et al.  Translation and scale invariants of Legendre moments , 2004, Pattern Recognit..

[15]  Marc Sebban,et al.  Discriminative feature fusion for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Yong Wang,et al.  Combining global, regional and contextual features for automatic image annotation , 2009, Pattern Recognit..

[17]  Hengame Deljooi,et al.  A Novel Semantic Statistical Model for Automatic Image Annotation Using the Relationship between the Regions Based on Multi-Criteria Decision Making , 2014 .

[18]  Yafei Lu,et al.  Image Annotation Based on Joint Feature Selection with Sparsity , 2014 .

[19]  Judea Pearl,et al.  Bayesian Networks , 1998, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[20]  Frank Y. Shih,et al.  Automatic seeded region growing for color image segmentation , 2005, Image Vis. Comput..