Advertisement

Color image segmentation using saturated RGB colors and decoupling the intensity from the hue

  • Farid García-LamontEmail author
  • Jair Cervantes
  • Asdrúbal López-Chau
  • Sergio Ruiz-Castilla
Article
  • 64 Downloads

Abstract

Although the RGB space is accepted to represent colors, it is not adequate for color processing. In related works the colors are usually mapped to other color spaces more suitable for color processing, but it may imply an important computational load because of the non-linear operations involved to map the colors between spaces; nevertheless, it is common to find in the state-of-the-art works using the RGB space. In this paper we introduce an approach for color image segmentation, using the RGB space to represent and process colors; where the chromaticity and the intensity are processed separately, mimicking the human perception of color, reducing the underlying sensitiveness to intensity of the RGB space. We show the hue of colors can be processed by training a self-organizing map with chromaticity samples of the most saturated colors, where the training set is small but very representative; once the neural network is trained it can be employed to process any given image without training it again. We create an intensity channel by extracting the magnitudes of the color vectors; by using the Otsu method, we compute the threshold values to divide the intensity range in three classes. We perform experiments with the Berkeley segmentation database; in order to show the benefits of our proposal, we perform experiments with a neural network trained with different colors by subsampling the RGB space, where the chromaticity and the intensity are processed jointly. We evaluate and compare quantitatively the segmented images obtained with both approaches. We claim to obtain competitive results with respect to related works.

Keywords

RGB space Color image segmentation Self-organizing maps Otsu method 

Notes

References

  1. 1.
    Bayá AE, Larese MG, Namías R (2017) Clustering stability for automated color image segmentation. Expert Syst Appl 86:258–273CrossRefGoogle Scholar
  2. 2.
    Behroozi-Khazaei N, Reza-Maleki M (2017) A robust algorithm based on color features for grape clusters segmentation. Comput Electron Agric 142:41–49CrossRefGoogle Scholar
  3. 3.
    Bhavana N, Sanjay K (2013) Impact of algorithms on green computing. IJCA proceedings on international conference on green computing and technology, pp 15–17Google Scholar
  4. 4.
    Chakraborty BK, Bhuyan MK, Kumar S (2017) Combining image and global pixel distribution model for skin colour segmentation. Pattern Recogn Lett 88:33–40CrossRefGoogle Scholar
  5. 5.
    Chang D, Zhao Y, Liu L, Zheng C (2016) A dynamic niching clustering algorithm based on individual-connectedness and its application to color image segmentation. Pattern Recogn 60:334–347CrossRefGoogle Scholar
  6. 6.
    Chang X, Feiping N, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-k projections for bilinear analysis. IEEE Trans Neural Netw Learn Syst 27(7):1502–1513MathSciNetCrossRefGoogle Scholar
  7. 7.
    Chen X, Yang SX (2013) A practical solution for ripe tomato recognition and localization. J Real-Time Image Process 8:35–51CrossRefGoogle Scholar
  8. 8.
    Chen W, Wang K, Jiang H, Li M (2016) Skin color modeling for face detection and segmentation: a review and a new approach. Multimed Tool Appl 75:839–862CrossRefGoogle Scholar
  9. 9.
    De-Thu H, Min C, Trong-Thua H, Chu HH (2019) Energy consumption optimization for green device-to-device multimedia communications. Future Gener Comput Syst 92:1131–1141CrossRefGoogle Scholar
  10. 10.
    Dubey SR, Jalal AS (2016) Apple disease classification using color, texture and shape features from images. Signal Image Video Process 10:819–826CrossRefGoogle Scholar
  11. 11.
    Garcia-Lamont F, Cervantes J, Lopez A, Rodriguez L (2018) Segmentation of images by color features: a survey. Neurocomputing 292:1–27CrossRefGoogle Scholar
  12. 12.
    Garcia-Zapirain B, Shalaby A, El-Baz A, Elmaghraby A (2017) Automated framework for accurate segmentation of pressure ulcer images. Comput Biol Med 90:137–145CrossRefGoogle Scholar
  13. 13.
    Gharieb RR, Gendy G, Abdelfattah A (2017) C-means clustering fuzzified by two membership relative entropy functions approach incorporating local data information for noisy image segmentation. Signal Image Video Process 11:541–548CrossRefGoogle Scholar
  14. 14.
    Girshick R, Donahue F, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142–158CrossRefGoogle Scholar
  15. 15.
    Gonzalez RC, Woods RE (2002) Digital image processing. Prentice Hall, Upper Saddle RiverGoogle Scholar
  16. 16.
    Hassan G, Hassanien AE (2018) Retinal fundus vasculature multilevel segmentation using whale optimization algorithm. Signal Image Video Process 12:263–270CrossRefGoogle Scholar
  17. 17.
    Heidary K, Caulfield HJ (2014) Color classification using margin-setting with ellipsoids. Signal Image Video Process 8:1245–1262CrossRefGoogle Scholar
  18. 18.
    Hettiarachchi R, Peters JF (2017) Voronoï region-based adaptive unsupervised color image segmentation. Pattern Recogn 65:119–135CrossRefGoogle Scholar
  19. 19.
    Joumani SE, Mechkouri SE, Zennouhi R, Kadmiri OW, Masmoudi L (2017) Segmentation method based on multiobjective optimization for very high spatial resolution satellite images. EURASIP J Image Video Process 2017:26CrossRefGoogle Scholar
  20. 20.
    Kermani S, Samadzadehaghdam N, EtehadTavakol M (2015) Automatic color segmentation of breast infrared images using a Gaussian mixture model. Optik 126:3288–3294CrossRefGoogle Scholar
  21. 21.
    Khan A, Jaffar MA (2015) Genetic algorithm and self organizing map based fuzzy hybrid intelligent method for color image segmentation. Appl Soft Comput 32:300–310CrossRefGoogle Scholar
  22. 22.
    Khan A, Ullah J, Jaffar MA, Choir TS (2014) Color image segmentation: a novel spatial fuzzy genetic algorithm. Signal Image Video Process 8:1233–1243CrossRefGoogle Scholar
  23. 23.
    Khelifi L, Mignotte M (2017) EFA-BMFM: a multi-criteria framework for the fusion of colour image segmentation. Inf Fusion 38:104–121CrossRefGoogle Scholar
  24. 24.
    Kohonen T (1990) The self-organizing map. Proc IEEE 78:1464–1480CrossRefGoogle Scholar
  25. 25.
    Lezoray O, Charrier C (2009) Color image segmentation using morphological clustering and fusion with automatic scale selection. Pattern Recogn Lett 30:397–406CrossRefGoogle Scholar
  26. 26.
    Li Z, Wu ZM, Chang SF (2012) Segmentation using superpixels: a bipartite graph partitioning approach. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 789–796Google Scholar
  27. 27.
    Li K, Tao W, Liu X, Liu L (2018) Iterative image segmentation with feature driven heuristic four-color labeling. Pattern Recogn 76:69–79CrossRefGoogle Scholar
  28. 28.
    Liang B, Zhang J (2014) Algorithm based on k-means clustering and graph cut. Math Probl Eng.  https://doi.org/10.1155/2014/464875 Google Scholar
  29. 29.
    Liang L, Zhang ZM (2017) Structure-aware enhancement of imaging mass spectrometry data for semantic segmentation. Chemom Intell Lab Syst 171:259–265CrossRefGoogle Scholar
  30. 30.
    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. IEEE conference on computer vision and pattern recognition, pp 3431–3440Google Scholar
  31. 31.
    López-Rubio FL, Domínguez E, Palomo EJ, López-Rubio E, Luque-Baena RM (2016) Selecting the color space for self-organizing map based foreground detection in video. Neural Process Lett 43:345–361CrossRefGoogle Scholar
  32. 32.
    Medeiros R, Scharcanski J, Wong A (2013) Natural scene segmentation based on a stochastic texture region merging approach. In: 2013 IEEE International conference on acoustics, speech, and signal processing. IEEE, pp 1464–1467Google Scholar
  33. 33.
    Mignotte M (2014) A non-stationary mrf for image segmentation from a soft boundary map. Pattern Anal Appl 17:129–139MathSciNetCrossRefGoogle Scholar
  34. 34.
    Mohd Safuan SN, Md Tomari MR, Wan Zakaria WN (2018) White blood cell (WBC) counting analysis in blood smear images using various color segmentation methods. Meas 116:543–555CrossRefGoogle Scholar
  35. 35.
    Ong SH, Yeo NC, Lee KH, Venkatesh YV, Cao DM (2002) Segmentation of color images using a two-stage self-organizing network. Image Vis Comput 20:279–289CrossRefGoogle Scholar
  36. 36.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern SMC-9:62–66CrossRefGoogle Scholar
  37. 37.
    Qinkun X, Ren S (2018) Action recognition based on hierarchical dynamic Bayesian network. Multimed Tool Appl 77(6):6955–6968CrossRefGoogle Scholar
  38. 38.
    Rajaby E, Ahadi SM, Aghaeinia H (2016) Robust color image segmentation using fuzzy c-means with weighted hue and intensity. Digit Signal Process 51:170–183CrossRefGoogle Scholar
  39. 39.
    Rajinikanth V, Couceiro MS (2015) RGB histogram based color image segmentation using firefly algorithm. Procedia Comput Sci 46:1449–1457CrossRefGoogle Scholar
  40. 40.
    Schu G, Scharcanski J (2018) A new method for building adaptive Bayesian tress and its application in color image segmentation. Expert Syst Appl 98:57–71CrossRefGoogle Scholar
  41. 41.
    Schu G, Scharcanski J (2018) A new method for building adaptive Bayesian trees and its application in color image segmentation. Expert Syst Appl 98:57–71CrossRefGoogle Scholar
  42. 42.
    Siang Tan K, Mat Isa NA (2011) Color image segmentation using histogram thresholding – fuzzy c-means hybrid approach. Pattern Recogn 44:1–15zbMATHCrossRefGoogle Scholar
  43. 43.
    Siang Tan K, Mat Isa NA, Hong Lim W (2013) Color image segmentation using adaptive unsupervised clustering approach. Appl Soft Comput 13:2017–2036CrossRefGoogle Scholar
  44. 44.
    Sridevi M, Mala C (2017) Self-organizing neural networks for image segmentation based on multiphase active contour. Neural Comput Appl.  https://doi.org/10.1007/s00521-017-3045-1 CrossRefGoogle Scholar
  45. 45.
    Wang J, Jiang H, Jia Y, Hua XS, Zhang C, Quan L (2014) Regularized tree partitioning and its application to unsupervised image segmentation. IEEE Trans Image Process 23:1909–1922MathSciNetzbMATHCrossRefGoogle Scholar
  46. 46.
    Wang X, Tang Y, Masnou S, Chen L (2015) A global/local affinity graph for image segmentation. IEEE Trans Image Process 24:1399–1411MathSciNetzbMATHCrossRefGoogle Scholar
  47. 47.
    Wang Y, Liu C, Zhu F, Boushey CJ, Delp EJ (2016) Efficient superpixel based segmentation for food analysis. In: 2016 IEEE International Conference on Image Processing (ICIP). IEEE, pp 2544–2548Google Scholar
  48. 48.
    Xiao Q, Wang H, Li F, Gao Y (2011) 3D object retrieval based on a graph model descriptor. Neurocomputing 74(17):3486–3493CrossRefGoogle Scholar
  49. 49.
    Xiao Q, Yichuang L, Wang H (2014) Motion retrieval based on switching Kalman filters model. Multimed Tool Appl 72(1):951–966CrossRefGoogle Scholar
  50. 50.
    Xiao Q, Yi Q, Wang H (2015) Motion retrieval using weighted graph matching. Soft Comput 19(1):133–144CrossRefGoogle Scholar
  51. 51.
    Yin S, Qian Y, Gong M (2017) Unsupervised hierarchical image segmentation through fuzzy entropy maximization. Pattern Recogn 68:245–259CrossRefGoogle Scholar
  52. 52.
    You X, Peng Q, Yuan Y, Cheung YM, Lei J (2011) Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern Recogn 44(10-11):2314–2324CrossRefGoogle Scholar
  53. 53.
    Zhang L, Verma B (2017) Superpixel-based class-semantic texton occurrences for natural roadside vegetation segmentation. Mach Vis Appl 28:293–311CrossRefGoogle Scholar
  54. 54.
    Zhang S, You Z, Wu Z (2017) Plant disease leaf image segmentation based on superpixel clustering and EM algorithm. Neural Comput Appl.  https://doi.org/10.1007/s00521-017-3067-8 CrossRefGoogle Scholar
  55. 55.
    Zhou Z, Zhao X, Zhu S (2018) K-harmonic means clustering algorithm using feature weighting for color image segmentation. Multimed Tool Appl 77:15139–15160CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Farid García-Lamont
    • 1
    Email author
  • Jair Cervantes
    • 1
  • Asdrúbal López-Chau
    • 2
  • Sergio Ruiz-Castilla
    • 1
  1. 1.Universidad Autónoma del Estado de México, Centro Universitario UAEM TexcocoTexcocoMexico
  2. 2.Universidad Autónoma del Estado de México, Centro Universitario UAEM ZumpangoZumpangoMexico

Personalised recommendations