Multimedia Tools and Applications

, Volume 75, Issue 17, pp 10175–10199 | Cite as

Region-based image retrieval in the compressed domain using shape-adaptive DCT

Article
First Online:
Received:
Revised:
Accepted:

Abstract

Content-based image retrieval (CBIR) has drawn substantial research and many traditional CBIR systems search digital images in a large database based on features, such as color, texture and shape of a given query image. A majority of images are stored in compressed format and most of compression technologies adopt different kinds of transforms to achieve compression. Therefore, features can be extracted directly from images in compressed format by using, for example, discrete cosine transform (DCT) for JPEG compressed images. Region-based image retrieval (RBIR) is an image retrieval approach which focuses on contents from regions of images, instead of the content from the entire image in early CBIR. Although RBIR approaches attempt to solve the semantic gap problem existed in global low-level features in CBIR by using local low-level features based on regions of images. This paper proposes a new RBIR approach using Shape adaptive discrete cosine transform (SA-DCT). At a bottom level, local features are constructed from the coefficients of quantized block transforms (low-level features) for each region. Quantization acts for the concentration of block-wise information in a more condense way, which is highly desirable for the retrieval tasks. At an intermediate level, histograms of local image features are used as descriptors of statistical information. Finally, at the top level, the combination of histograms from different image regions (objects) is defined as a way to incorporate high-level semantic information. In this retrieval system, an image has a prior segmentation alpha plane, which is defined exactly as in MPEG-4. Therefore, an image is represented by segmented regions, each of which is associated with a feature vector derived from DCT and SA-DCT coefficients. Users can select any region as the main theme of the query image. The similarity between a query image and any database image is ranked according to a same similarity measure computed from the selected regions between two images. For those images without distinctive objects and scenes, users can still select the whole image as the query condition. The experimental results show that the proposed approach is able to identify main objects and reduce the influence of background in the image, and thus improve the performance of image retrieval in comparison with a conventional CBIR based on DCT.

Keywords

Content-based image retrieval (CBIR) DCT Segmentation Region-based image retrieval (RBIR) Semantic image retrieval SA-DCT 

References

  1. 1.
    Agarwal M, Maheshwari R (2012) A trous gradient structure descriptor for content based image retrieval. Int J Multimedia Inf Retr 1(2):129–138CrossRefGoogle Scholar
  2. 2.
    Bai C, Kpalma K, Ronsin J (2012) Color textured image retrieval by combining texture and color features. In: Proceedings EUSIPCO’12 (European Signal Processing Conference), pp 170–174Google Scholar
  3. 3.
    Bai C, Kpalma K, Ronsin J (2012) A new descriptor based on 2d dct for image retrieval. In: Proceedings VISAPP’12 (International Conference on Computer Vision Theory and Applications), pp 714–717Google Scholar
  4. 4.
    Bai C, Zhang J, Liu Z, Zhao WL (2014) K-means based histogram using multiresolution feature vectors for color texture database retrieval. Multimed Tools Appl 69(5):1–20Google Scholar
  5. 5.
    Belloulata K, Belalia A, Zhu S (2014) Object-based stereo video compression using fractals and shape-adaptive dct. AEU Int J Electron Commun 68(7):687–697CrossRefGoogle Scholar
  6. 6.
    Belloulata K, Belhallouche L, Belalia A, Kpalma K (2014) Region based image retrieval using shape-adaptive dct. In: Proceedings ChinaSIP-14 (2nd IEEE China Summit and International Conference on Signal and Information Processing), pp 470–474Google Scholar
  7. 7.
    Belloulata K, Konrad J (2002) Fractal image compression with region-based functionality. IEEE Trans Image Process 11(4):351–362CrossRefGoogle Scholar
  8. 8.
    Bolle RM, Pankanti S, Ratha NK (2000) Evaluation techniques for biometrics-based authentication systems (frr). In: Proceedings ICPR’00 (International Conference on Pattern Recognition), vol II, pp 831–837Google Scholar
  9. 9.
    Bresson X, Esedoglu S, Vandergheynst P, Thiran J, Osher S (2007) Fast global minimization of the active contour/snake model. J Math Imaging and Vision 28(2):151–167MathSciNetCrossRefGoogle Scholar
  10. 10.
    Carson C, Belongie S, Greenspan H, Malik J (2002) Blobworld: Image segmentation using expectation-maximization and its application to image querying. IEEE Trans Pattern Anal Mach Intell 24(8):1026–1038CrossRefGoogle Scholar
  11. 11.
    Chang C, Chuang J, Hu Y (2004) Retrieving digital images from a jpeg compressed image database. Image Vis Comput 22(6):471–484CrossRefGoogle Scholar
  12. 12.
    Chen H, Civanlar M, Haskell B (1994) A block transform coder for arbitrarily-shaped image segments. In: Proceedings ICIP-94 (IEEE International Conference on Image Processing), pp 85–89Google Scholar
  13. 13.
    Cheng K, Law N, Siu W (2010) Fast extraction of wavelet-based features from jpeg images for joint retrieval with jpeg2000 images. Pattern Recogn 43:3314–3323CrossRefMATHGoogle Scholar
  14. 14.
    Climer S, Bhatia SK (2002) Image database indexing using jpeg coefficients. Pattern Recogn 35(11):2479–2488CrossRefMATHGoogle Scholar
  15. 15.
    Dabbaghchian S, Ghaemmaghami M, Aghagolzadeh A (2010) Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology. Pattern Recogn 43:1431–1440CrossRefMATHGoogle Scholar
  16. 16.
    Datta R, Joshi D, Li J, Wang JZ (2008) Image retrieval: Ideas, influences, and trends of the new age. ACM Comput Surv 140(2)5:1–60Google Scholar
  17. 17.
    Edmundson D, Schaefer G (2012) Fast jpeg image retrieval using optimised huffman tables. In: Proceedings ICPR’12 (International Conference on Pattern Recognition), vol IV, pp 3188–3191Google Scholar
  18. 18.
    Edmundson D, Schaefer G, Celebi M (2012) Robust texture retrieval of compressed images. In: Proceedings ICIP-12 (IEEE International Conference on Image Processing), vol IV, pp 2421–2424Google Scholar
  19. 19.
    Eickeler S, Muller S, Rigoll G (2000) Recognition of jpeg compressed face images based on statistical methods. Image Vis Comput 18(4):279–287CrossRefGoogle Scholar
  20. 20.
    Feng G, Jiang J (2003) Jpeg compressed image retrieval via statistical features. Pattern Recogn 36(4):977–985CrossRefGoogle Scholar
  21. 21.
    Ferman A, Tekalp M, Mehrotra R (2002) Robust color histogram descriptors for video segment retrieval and identification. IEEE Trans Circuits Syst Video Technol 11(5):497–508Google Scholar
  22. 22.
    Gilge M, Engelhardt T, Mehlan R (1989) Coding of arbitrarily shaped image segments based on a generalized orthogonal transform. Signal Process Image Commun 1(2):153–180CrossRefGoogle Scholar
  23. 23.
    Griffin G, Holub A, Perona P (2007) Caltech-256 object category datasetGoogle Scholar
  24. 24.
    Hsu H, Lee K, Chang N, Chang T (2008) Architecture design of shape-adaptive discrete cosine transform and its inverse for mpeg-4 video coding. IEEE Trans Circuits Syst Video Technol 18(3):375–386CrossRefGoogle Scholar
  25. 25.
    http://wang.ist.psu.edu/jwang/test1.tar. Last accessed- jan. 2013
  26. 26.
  27. 27.
    http://www.anefian.com/research/face-reco.htm. georgia tech, gtf database., Last accessed mars 2012
  28. 28.
    Information Technology - Coding of Audio-Visual Objects-Part2: Visual (14496-2), ISO/IEC JTC1/SC29/WG11, MPEG-4 Version 3 Visual Working Draft Revision 3.0 (2004)Google Scholar
  29. 29.
    Jiang J, Amstrong A, Feng G (2002) Direct content access and extraction from jpeg compressed images. Pattern Recogn 35(11):2511–2519CrossRefMATHGoogle Scholar
  30. 30.
    Jiang J, Feng G (2002) The spatial relationship of dct coefficients between a block and its sub-blocks. IEEE Trans. Signal Process. 5(11):1160–1169CrossRefGoogle Scholar
  31. 31.
    Jing F, Li M, Zhang H, Zhang B (2004) An efficient and effective region-based image retrieval framework. IEEE Trans Image Process 13(5):699–709CrossRefGoogle Scholar
  32. 32.
    Kauff P, Schüür K (1998) Shape-adaptive DCT with block-based DC separation and ΔDC correction. IEEE Trans Circuits Syst Video Technol 8(3):237–242CrossRefGoogle Scholar
  33. 33.
    Liu Y, Chen X, Zhang C, Sprague A (2009) Semantic clustering for region-based image retrieval. J Vis Commun Image Represent 20:157–166CrossRefGoogle Scholar
  34. 34.
    Liu Y, Zhang DS, Lu G, Ma WY (2006) Study on texture feature extraction in region-based image retrieval system. In: Proceedings MMM’06 (Iternational Multimedia Modeling Conference), pp 264–271Google Scholar
  35. 35.
    Liu Y, Zhang DS, Lu G, Ma WY (2007) A survey of content-based image retrieval with high-level semantics. Pattern Recogn 40(1):262–282CrossRefMATHGoogle Scholar
  36. 36.
    Liu Y, Zhang DS, Lu G (2008) Region-based image retrieval with high-level semantics using decision tree learning. Pattern Recogn 41(1):2554–2570CrossRefMATHGoogle Scholar
  37. 37.
    Liu Y, Zhou X, Ma WY (2004) Extraction of texture features from arbitrary-shaped regions for image retrieval. In: Proceedings ICME’04 (Iternational Conference on Multimedia and Expo), pp 1891–1894Google Scholar
  38. 38.
    Manipoonchelvi P, Muneeswaran K (2014) Significant region-based image retrieval. SIViP 6:1–8. SpringerMATHGoogle Scholar
  39. 39.
    Murala S, Maheshwari RP, Balasubramanian R (2012) Directional local extrema patterns: a new descriptor for content based image retrieval. Int J Multimedia Inf Retr 1(3):191–203CrossRefGoogle Scholar
  40. 40.
    Murala S, Wu QM (2014) Expert content-based image retrieval system using robust local patterns. J Vis Commun Image Represent 25:1324–1334CrossRefGoogle Scholar
  41. 41.
    Ngo C, Pong T, Chin R (2001) Exploiting image indexing techniques in dct domain. Pattern Recogn 34(9):1841–1845CrossRefMATHGoogle Scholar
  42. 42.
    Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vis 40:99–121CrossRefMATHGoogle Scholar
  43. 43.
    Rui Y, Huang T, Chang SF (1999) Image retrieval: Current technique, promising directions and open issues. J Vis Commun Image Represent 10:39–62CrossRefGoogle Scholar
  44. 44.
    Schneier M, Abdel-Mottaleb M (1996) Exploiting the jpeg compression scheme for image retrieval. IEEE Trans Pattern Anal Mach Intell 18(8):849–853CrossRefGoogle Scholar
  45. 45.
    Shokoufandeh A, Keselman Y, Demirci MF, Macrini D, Dickinson S (2012) Many-to-many feature matching in object recognition: a review of three approaches. IET Comput Vis 6(6):500–513CrossRefGoogle Scholar
  46. 46.
    Sikora T (1995) Low complexity shape-adaptive DCT for coding of arbitrarily shaped image segments. Signal Process Image Commun 17(4–6):381–395CrossRefGoogle Scholar
  47. 47.
    Sikora T, Makai B (1995) Shape-adaptive DCT for generic coding of video. IEEE Trans Circuits Syst Video Technol 5(1):59–62CrossRefGoogle Scholar
  48. 48.
    Smeulders AWM, Worring M, Santini S (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349–1380CrossRefGoogle Scholar
  49. 49.
    Stasinski R, Konrad J (1999) A new class of fast shape-adaptive orthogonal transforms and their application to region-based image compression. IEEE Trans Circuits Syst Video Technol 9(1):16–34CrossRefGoogle Scholar
  50. 50.
    Sun Y, Ozawa S (2005) Hirbir: A hierarchical approach to region-based image retrieval. Multimedia Systems 10(6):559–569CrossRefGoogle Scholar
  51. 51.
    Wang JZ, Li J, Wiederhold G (2001) Simplicity: Semantics-sensitive integrated matching for picture libraries. IEEE Trans Pattern Anal Mach Intell 23(9):947–963CrossRefGoogle Scholar
  52. 52.
    Wang XY, Zhang BB, Yang HY (2014) Content-based image retrieval by integrating color and texture features. Multimed Tools Appl 68(4):545–569CrossRefGoogle Scholar
  53. 53.
    Yang X, Cai L (2014) Adaptive region matching for region-based image retrieval by constructing region importance index. IET Comput Vis 8(2):141–151CrossRefGoogle Scholar
  54. 54.
    Yanping D, Wang JZ (2001) A scalable integrated region-based image retrieval system. In: Proceedings ICIP-01 (IEEE International Conference on Image Processing), vol I, pp 22–25Google Scholar
  55. 55.
    Zhang D, Islam M, Lu G, Sumana I (2012) Rotation invariant curvelet features for region based image retrieval. Int J Comput Vis 98(2):187–201MathSciNetCrossRefGoogle Scholar
  56. 56.
    Zhong D, Defee I (2005) Dct histogram optimization for image database retrieval. Pattern Recogn Lett 26(14):2272–2281CrossRefGoogle Scholar
  57. 57.
    Zhong D, Defee I (2007) Performance of similarity measures based on histograms of local image feature vectors. Pattern Recogn Lett 28(15):2003–2010CrossRefGoogle Scholar
  58. 58.
    Zhong D, Defee I (2008) Face retrieval based on robust local features and statistical-structural learning approach. EURASIP J Adv Signal Process 2008:12. ID 631297CrossRefMATHGoogle Scholar
  59. 59.
    Zou W, Kpalma K, Ronsin J (2012) Semantic image segmentation using region bank. In: Proceedings ICPR’12 (International Conference on Pattern Recognition), pp 922–925Google Scholar
  60. 60.
    Zou W, Kpalma K, Ronsin J (2012) Semantic segmentation via sparse coding over hierarchical regions. In: Proceedings ICIP-12 (IEEE International Conference on Image Processing), pp 2577–2580Google Scholar
  61. 61.
    Zou W, Kpalma K, Ronsin J (2013) Automatic foreground extraction via joint crf and online learning. Electron Lett 49(18):1140–1142CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Electronics Department, Faculty of EngineeringUniversity of Djillali LiabesSidibel AbbesAlgeria
  2. 2.UEB INSA, UMR 6164IETRRennesFrance

Personalised recommendations