Skip to main content
SpringerLink
Log in

Composite description based on color vector quantization and visual primary features for CBIR tasks

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

This paper presents a novel method for content-based color image retrieval that combines color vector quantization and visual primary features into a compact feature representation. Color vector quantization is proposed to describe the image in a compressed stream by preserving the contrast of an image and produce two color quantizers which are processed by vector quantization to preserve the content of a color image. Loosely inspired by human visual system and its mechanism in effectively recognizing objects in an image by its edges and color distribution, we propose extraction of visual primary features based on edge texture orientation and color moments features. The representation of the proposed method utilizes histogram-based features which are populated by color quantization and visual primary features that are used to measure the similarity between the two color images by a specific distance metric computation. The proposed method proves to be efficient and adaptive to the particulars of image retrieval, while it does not require any training information, making it suitable for real time color CBIR applications.The smaller feature size is an additional benefit of the proposed methodology which makes it ideal to use for embedded computing, mobile computing, energy efficient computing and high-throughput systems. An extensive experimental evaluation conducted on four publicly available datasets namely Wang, Vistex-640, Corel-5k and Corel-10k datasets against well-known fusion based, non-fusion based, and deep learning methods highlights the effectiveness and efficiency of the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Alzu-bi A, Amira A, Ramzan N (2015) Semantic content-based image retrieval: A comprehensive study. J Vis Commun Image Represent 32:20–54

    Article  Google Scholar 

  2. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput Vis Image Underst 110(3):346–359

    Article  Google Scholar 

  3. Beecks C, Kirchhoff S, Seidl T (2014) On stability of signature-based similarity measures for content-based image retrieval. Multimed Tools Appl 71(1):349–362

    Article  Google Scholar 

  4. Beecks C, Uysal MS, Seidl T (2010) A comparative study of similarity measures for content-based multimedia retrieval. In: 2010 IEEE International Conference on Multimedia and Expo. IEEE, pp 1552–1557

  5. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255

  6. Deselaers T, Keysers D, Ney H (2008) Features for image retrieval: an experimental comparison. Inf Retrieval 11(2):77–107

    Article  Google Scholar 

  7. 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

    Article  MathSciNet  Google Scholar 

  8. Gonzalez RC, Woods RE (2007) Digital image processing, 3rd edition. Prentice Hall

  9. Guo JM (2010) High efficiency ordered dither block truncation coding with dither array lut and its scalable coding application. Digital Signal Process 20(1):97–110

    Article  Google Scholar 

  10. Guo JM, Liu YF (2013) Improved block truncation coding using optimized dot diffusion. IEEE Trans Image Process 23(3):1269–1275

    Article  MathSciNet  Google Scholar 

  11. Guo JM, Prasetyo H, Chen JH (2014) Content-based image retrieval using error diffusion block truncation coding features. IEEE Trans Circuits Syst Video Technol 25(3):466–481

    Google Scholar 

  12. Guo JM, Prasetyo H, Su HS (2013) Image indexing using the color and bit pattern feature fusion. J Vis Commun Image Represent 24(8):1360–1379

    Article  Google Scholar 

  13. Guo JM, Prasetyo H, Wang NJ (2015) Effective image retrieval system using dot-diffused block truncation coding features. IEEE Trans Multimedia 17(9):1576–1590

    Article  Google Scholar 

  14. Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: A review. Neurocomputing 187:27–48

    Article  Google Scholar 

  15. Guo Y, Zhao G, PietikäInen M (2012) Discriminative features for texture description. Pattern Recogn 45(10):3834–3843

    Article  Google Scholar 

  16. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  17. Howarth P, Rüger S (2004) Evaluation of texture features for content-based image retrieval. In: International conference on image and video retrieval. Springer, pp 326–334

  18. Koch C, Ullman S (1987) Shifts in selective visual attention: towards the underlying neural circuitry. In: Matters of intelligence. Springer, pp 115–141

  19. Lee SH, Choi JY, Ro YM, Plataniotis KN (2011) Local color vector binary patterns from multichannel face images for face recognition. IEEE Trans Image Process 21(4):2347–2353

    Article  MathSciNet  Google Scholar 

  20. Li J, Sang N, Gao C (2016) Completed local similarity pattern for color image recognition. Neurocomputing 182:111–117

    Article  Google Scholar 

  21. Lin K, Lu J, Chen CS, Zhou J (2016) Learning compact binary descriptors with unsupervised deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1183–1192

  22. Linde Y, Buzo A, Gray R (1980) An algorithm for vector quantizer design. IEEE Trans Commun 28(1):84–95

    Article  Google Scholar 

  23. Liu GH, Li ZY, Zhang L, Xu Y (2011) Image retrieval based on micro-structure descriptor. Pattern Recogn 44(9):2123–2133

    Article  Google Scholar 

  24. Liu GH, Yang JY, Li Z (2015) Content-based image retrieval using computational visual attention model. Pattern Recogn 48(8):2554–2566

    Article  Google Scholar 

  25. Liu P, Guo JM, Chamnongthai K, Prasetyo H (2017) Fusion of color histogram and lbp-based features for texture image retrieval and classification. Inf Sci 390:95–111

    Article  Google Scholar 

  26. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91–110

    Article  Google Scholar 

  27. Maenpaa T, Pietikainen M, Viertola J (2002) Separating color and pattern information for color texture discrimination. In: Object recognition supported by user interaction for service robots, vol 1. IEEE, pp 668–671

  28. Manjunath BS, Ohm JR, Vasudevan VV, Yamada A (2001) Color and texture descriptors. IEEE Trans Circuits Syst Video Technol 11(6):703–715

    Article  Google Scholar 

  29. Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987

    Article  Google Scholar 

  30. Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1717–1724

  31. Patel JM, Gamit NC (2016) A review on feature extraction techniques in content based image retrieval. In: 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). IEEE, pp 2259–2263

  32. Penatti OA, Valle E, Torres RDS (2012) Comparative study of global color and texture descriptors for web image retrieval. J Vis Commun Image Represent 23(2):359–380

    Article  Google Scholar 

  33. Picard R, Graczyk C, Mann S, Wachman J, Picard L, Campbell L, Negroponte N (1995) Vision texture database. The Media Laboratory, MIT, Cambridge, Massachusetts

  34. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 4510–4520

  35. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

  36. Singh C, Walia E, Kaur KP (2018) Color texture description with novel local binary patterns for effective image retrieval. Pattern Recogn 76:50–68

    Article  Google Scholar 

  37. Subrahmanyam M, Wu QJ, Maheshwari R, Balasubramanian R (2013) Modified color motif co-occurrence matrix for image indexing and retrieval. Comput Electr Eng 39(3):762–774

    Article  Google Scholar 

  38. Tan M, Le QV (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946

  39. Tola E, Lepetit V, Fua P (2009) Daisy: An efficient dense descriptor applied to wide-baseline stereo. IEEE Trans Pattern Anal Mach Intell 32(5):815–830

    Article  Google Scholar 

  40. Tzelepi M, Tefas A (2018) Deep convolutional learning for content based image retrieval. Neurocomputing 275:2467–2478

    Article  Google Scholar 

  41. Vassou SA, Anagnostopoulos N, Amanatiadis A, Christodoulou K, Chatzichristofis SA (2017) Como: a compact composite moment-based descriptor for image retrieval. In: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing. pp 1–5

  42. Wan J, Wang D, Hoi SCH, Wu P, Zhu J, Zhang Y, Li J (2014) Deep learning for content-based image retrieval: A comprehensive study. In: Proceedings of the 22nd ACM international conference on Multimedia. pp 157–166

  43. Wang JZ, Li J, Wiederhold G (2001) Simplicity: Semantics-sensitive integrated matching for picture libraries. IEEE Trans Pattern Anal Mach Intell 23(9):947–963

    Article  Google Scholar 

  44. Wu YG, Tai SC (1998) An efficient btc image compression technique. IEEE Trans Consum Electron 44(2):317–325

    Article  Google Scholar 

  45. Xia R, Pan Y, Lai H, Liu C, Yan S (2014) Supervised hashing for image retrieval via image representation learning. In: Twenty-Eighth AAAI Conference on Artificial Intelligence

  46. Zhang B, Gao Y, Zhao S, Liu J (2009) Local derivative pattern versus local binary pattern: face recognition with high-order local pattern descriptor. IEEE Trans Image Process 19(2):533–544

    Article  MathSciNet  Google Scholar 

  47. Zhu C, Bichot CE, Chen L (2013) Image region description using orthogonal combination of local binary patterns enhanced with color information. Pattern Recogn 46(7):1949–1963

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Engineering, Griffith University, Griffith, Australia

    M. Daud Abdullah Asif & Yongsheng Gao

  2. School of Information and Communication Technology, Griffith University, Griffith, Australia

    Jing Wang & Jun Zhou

Authors
  1. M. Daud Abdullah Asif
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yongsheng Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Daud Abdullah Asif.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• A robust content-based color image retrieval method is proposed, which integrates color vector quantization and visual primary features into a compact representation with high precision.

• The proposed color quantization process generates two color quantizers to preserve the content and contrast of an image.

• Inspired by human visual system, two-fold representation is proposed to capture texture orientation and color distribution among the images.

• The smaller feature size is an additional benefit of the proposed methodology which makes it ideal to use for embedded computing, mobile computing, energy efficient computing and high-throughput systems.

• Experimental results on four publicly available texture image datasets consistently demonstrate the effectiveness and superiority of the proposed approach.

• Experimental analysis with state-of-the-art deep learning convolutional neural networks exhibits the potential of proposed method for many real-time applications.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Asif, M.D.A., Wang, J., Gao, Y. et al. Composite description based on color vector quantization and visual primary features for CBIR tasks. Multimed Tools Appl 80, 33409–33427 (2021). https://doi.org/10.1007/s11042-021-11353-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11353-6

Keywords

Search

Navigation