Novel System for Color Logo Recognition Using Optimization and Learning Based Relevance Feedback Technique

Logorecognitionsystemdealswithmatchingoftheinputtrademarkorlogowithstoredtrademark imagesindatabase.Thisapplication,underCBIRumbrella,focusesonoptimizingsearchthrough database by extracting minimum features from set of the images and using relevance feedback mechanism to identify the relevant images.Obtaininghigheraccuracy in retrievalprocess is the mainchallengeofthework.TheretrievalresultsofCBIRsystemcanbeenhancedbyusingmachine learningmechanismswithrelevancefeedbackforShortTermLearning(STL)andLong-TermLearning (LTL).Thispaperproposestherelevancefeedbacksystemembeddedwithmachinelearningand optimizationtechniqueforlogorecognition.Relevancefeedbacktechniqueisusedasbaselinemodel forlogorecognition.Featuresetisoptimizedusingparticleswarmoptimization(PSO)andsearch processismadeintelligentbyincorporatingself-organizingmap(SOM).Thesetechniquesimprove thebasicmodelasdepictedintheresults. KeywORdS Content-Based Image Retrieval (CBIR), Feature, Logo, Particle Swarm Optimization, Relevance Feedback, Self-Organizing Map (SOM)

[1]  Erkki Oja,et al.  PicSOM - content-based image retrieval with self-organizing maps , 2000, Pattern Recognit. Lett..

[2]  Souvik Ghosh,et al.  Automated Color Logo Recognition System based on Shape and Color Features , 2015 .

[3]  James Ze Wang,et al.  Image retrieval: Ideas, influences, and trends of the new age , 2008, CSUR.

[4]  Josep Lladós,et al.  Interactive Trademark Image Retrieval by Fusing Semantic and Visual Content , 2011, ECIR.

[5]  Wei-Ying Ma,et al.  Learning a semantic space from user's relevance feedback for image retrieval , 2003, IEEE Trans. Circuits Syst. Video Technol..

[6]  John P. Eakins,et al.  Component-based visual clustering using the self-organizing map , 2007, Neural Networks.

[7]  Keisuke Kameyama,et al.  Optimal Parameter Selection in Image Similarity Evaluation Algorithms Using Particle Swarm Optimization , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[8]  Maisa Daoud,et al.  Content-Based Image Retrieval Using SOM and DWT , 2015 .

[9]  Forrest N. Iandola,et al.  DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer , 2015, ArXiv.

[10]  Ponnuthurai N. Suganthan.  Shape indexing using self-organizing maps , 2002, IEEE Trans. Neural Networks.

[11]  Philip S. Yu,et al.  Efficient Relevance Feedback for Content-Based Image Retrieval by Mining User Navigation Patterns , 2011, IEEE Transactions on Knowledge and Data Engineering.

[12]  Manisha Sharma,et al.  Comparative Evaluation of Image Retrieval Algorithms using Relevance Feedback and it's Applications , 2012 .

[13]  Zhenhai Wang,et al.  A Novel Approach for Trademark Image Retrieval by Combining Global Features and Local Features , 2012 .

[14]  Qiang Wu,et al.  LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks , 2015, ArXiv.

[15]  Sergio Escalera,et al.  Logo Recognition Based on the Dempster-Shafer Fusion of Multiple Classifiers , 2013, Canadian Conference on AI.

[16]  Jehad Alnihoud,et al.  Content-based image retrieval system based on self organizing map, fuzzy color histogram and subtractive fuzzy clustering , 2012, Int. Arab J. Inf. Technol..

[17]  Jing Li,et al.  Long-term learning in content-based image retrieval , 2008 .

[18]  Alireza Alaei,et al.  A Complete Logo Detection/Recognition System for Document Images , 2014, 2014 11th IAPR International Workshop on Document Analysis Systems.

[19]  Wan-Chi Siu,et al.  Multimedia Information Retrieval and Management , 2003 .

[20]  Michael R. Lyu,et al.  A novel log-based relevance feedback technique in content-based image retrieval , 2004, MULTIMEDIA '04.