Abstract
Internet applications stores vast quantity of images into databases of server and also several quantities of images are also retrieved from databases. This phenomenon projects the CBIR system as a vital need. The Content based Image Retrieval (CBIR) is an image retrieval system that is mostly demanded by the fields such as agriculture object recognition, biomedical, etc. The CBIR method that is imparted in this paper is Enhanced Hybrid CBIR based on Multichannel LBP oriented color descriptor and HSV color statistical feature(CBIR_MCLBP_HSV). This method employs the Hybrid feature sets which are generated by histogram oriented features and statistical features. The main contribution of this method is the new color-image-descriptor which is entitled as Multichannel LBP Oriented Color image descriptor (MCLBP). To strengthen this CBIR system, the HSV color space oriented statistical features such as Mean and Standard deviation are included in this new framework. The reduced feature sets from MCLP and the usage of HSV color space results in fast and higher retrieval rate. This excellent method is fit for large size online image retrieval. The proposed methodology is experimentally analyzed and compared with the existing recent CBIR algorithms with the help of three standard databases (DB_Corel1k, DB_USPTex and KTH-TIPS2a) and a user contributed database named DB_VEG.
Similar content being viewed by others
References
Abbadeni N (2011) Computational PerceptualFeatures for Texture Representation and Retrieval. IEEETrans. Image Process 20(1):236–246
Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041
AmitSatpathy XJ, Eng H-L (2014) LBP-based edge-texture features for object recognition. IEEE Trans Image Process 23(5):1953–1964
Chih-Chih (2011) ‘A User-Oriented Image Retrieval SystemBased on Interactive Genetic Algorithm’. IEEE Trans Instrument Measur. 60 (10): 3318–3325
ColorSpace: http://www.Compression.ru/download/articles/Color-space/ch03.pdf
Corel Database :http://wang.ist.psu.edu/docs/realted/.
Dubey SR, Singh SK, Singh RK (2016) Multichannel decoded local binary patterns for content-based image retrieval. IEEE Trans Image Process 25(9):4018–4032
Gonzalez RC & Woods RE 2014, ‘Digital image processing’, Tata McGraw Hill Education Private Limited, New Delhi.
Gonzalez RC, Woods RE & Eddins SL 2016, ‘ Digital image processing using Matlab’, Tata McGraw Hill Education Private Limited, New Delhi.
Hadid A, Zhao G (2011) Computer vision using local binary patterns, vol 40. Springer
HSV Color Space: http://en.wikipedia.org/wiki/List-of-Color-space-and–their-uses-HSV-and-HSL.
Jain AK 2017, ‘Fundamentals of digital image processing’, Pearson India Education Service Pvt Ltd, India.
Kong F-H (2009) Image retrieval using both color and texture features. IEEE Int Conf Mach Learn Cybernetics 4:2228–2232
KTH-TIPS texture image database: https://www.csc.kth.se/cvap/databases/kth-ips/download.html.
Kwitt R, Meerwald P (Jul. 2011) Andreas Uhi: ‘efficient texture image retrieval using copulas BayesianFramework’. IEEE Trans Image Process 20(7):2063–2077
Lai C-C, Chen Y-C (2011) A User-Oriented Image Retrieval System Based on Interactive Genetic Algorithm’. IEEE Trans Instrument Measurement 60(10):3318–3325
Latecki L, Lakamper R, Eckhardt U (2000) Shape descriptors for non-rigid shapes with a single closed contour. IEEE Conf on Computer Vision and Pattern Recognition 1:424–429
Latecki LE (2000) ‘Shape descriptors forNon- rigid shapes with a single closed contour’, IEEEConf. on Computer Vision and Pattern Recognition, , vol. 1, pp. 424–429.
Li W, Duan L, Xu D, Tsang IW-H (2011) Text-based image retrieval using progressive multi-instance learning. Int Conf Comput Vision 58(11):2049–2055
MIT Vision and Modeling Group, Cambridge : http://vismod.media.mit.edu/pub/.
Ojala P (2002) Maenpaa: ‘multi resolution gray-scaleand rotation invariant texture classification with localbinary patterns’, IEEE trans. Pattern anal. Mach. Intell 24(7):971–987
Ojala T, Pietikäinen, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recogn 29(1):51–59
Persoon E, Fu K (1997) Shape discrimination using Fourierdescriptors. IEEE Trans Syst Man Cybern 7(3):170–179
Sajjanhar A, Lu G, Zhang D, Zhou W & Phoebe Chen Y-P (2008) ‘Image retrieval based on semantics of intra-region color properties’, 8th IEEE International Conference on Computer and Information Technology, pp. 338–343.
Sikora T (2001) The MPEG-7 Visual Standard for Content Description—An Overview. IEEE Trans Circ Syst Video Technol 11(6):696–702
Sujatha, Vijayakumar H: ‘A new logical compactLBP co-occurrence matrix for texture analysis’Int J Sci. Eng Res 2012, vol. 3, no. 2, pp. 1–5
USPTex database:http://fractal.ifsc.usp.br/dataset/USPtex.php.
Yang J, Jiang B, Li B, Tian K, Zhihan LV (2017) A fast image retrieval method designed for network big data. IEEE Trans Industrial Inform 13(5):2350–2359
Zhang C, Chai JY, Jin R (2005) User term feedback in interactive text based image retrieval. Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, Brazil, pp 51–58
Zhang D, Lu G (2003) Evaluation of MPEG-7 shape descriptors against other shape descriptors. Multimedia Syst 9(1):15–30
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Latha, D., Sheela, C.J.J. Enhanced hybrid CBIR based on multichannel LBP oriented color descriptor and HSV color statistical feature. Multimed Tools Appl 81, 23801–23818 (2022). https://doi.org/10.1007/s11042-022-12568-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12568-x