Abstract
Color is a very important cue for object recognition, which can help increase the discriminative power of an object-recognition system and also make it more robust to variations in the lighting and imaging conditions. Nonetheless, even though most image acquisition devices provide color data, a lot of object-recognition systems rely solely on simple grayscale information. Part of the reason for this is that although color has advantages, it also introduces some complexities. In particular, the RGB values of a digital color image are only indirectly related to the surface “color” of an object, which depends not only on the object’s surface reflectance but also on such factors as the spectrum of the incident illumination, surface gloss, and the viewing angle. As a result, there has been a great deal of research into color invariants that encode color information but at the same time are insensitive to these other factors. This chapter describes these color invariants, their derivation, and their application to color-based object recognition in detail. Recognizing objects using a simple global image matching strategy is generally not very effective since usually an image will contain multiple objects, involve occlusions, or be captured from a different viewpoint or under different lighting conditions than the model image. As a result, most object-recognition systems describe the image content in terms of a set of local descriptors—SIFT, for example—that describe the regions around a set of detected keypoints. This chapter includes a discussion of the three color-related choices that need to be made when designing an object-recognition system for a particular application: Color-invariance, keypoint detection, and local description. Different object-recognition situations call for different classes of color invariants depending on the particular surface reflectance and lighting conditions that will be encountered. The choice of color invariants is important because there is a trade-off between invariance and discriminative power. All unnecessary invariance is likely to decrease the discriminative power of the system. Consequently, one part of this chapter describes the assumptions underlying the various color invariants, the invariants themselves, and their invariance properties. Then with these color invariants in hand, we turn to the ways in which they can be exploited to find more salient keypoints and to provide richer local region descriptors. Generally but not universally, color has been shown to improve the recognition rate of most object-recognition systems. One reason color improves the performance is that including it in keypoint detection increases the likelihood that the region surrounding the keypoint will contain useful information, so descriptors built around these keypoints tend to be more discriminative. Another reason is that color-invariant-based keypoint detection is more robust to variations in the illumination than grayscale-based keypoint detection. Yet another reason is that local region descriptors based on color invariants more richly characterize the regions, and are more stable relative to the imaging conditions, than their grayscale counterparts.
What is without form is without color
Jacques Ferron
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdel-Hakim A, Farag A (2006) Csift: A sift descriptor with color invariant characteristics. In: 2006 IEEE computer society conference on computer vision and pattern recognition, New York, USA, vol 2, pp 1978–1983
Alexe B, Deselaers T, Ferrari V (2010) What is an object? IEEE computer society conference on computer vision and pattern recognition 4:73–80
Ancuti C, Bekaert P (2007) Sift-cch: Increasing the sift distinctness by color co-occurrence histograms. In: Proceedings of the 5th international symposium on image and signal processing and analysis, Istambul, Turkey, pp 130–135
Arulampalam M, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking. IEEE Trans Signal Process 50(2):174–188
Barnard K, Martin L, Coath A, Funt B (2002) A comparison of computational color constancy algorithms. II. Experiments with image data. IEEE Trans Image Process 11(9):985–996
Base caltech. URL http://www.vision.caltech.edu/html-files/archive.html
Base graz02. URL http://www.emt.tugraz.at/~pinz/data/GRAZ_02/
Bay H, Ess A, Tuytelaars T, Gool LV (2008) Surf: Speeded up robust features. Comput Vis Image Understand 110:346–359
Beaudet PR (1978) Rotationally invariant image operators. In: Proceedings of the International Conference on Pattern Recognition, Kyoto, Japan, pp 579–583
Beckmann P, Spizzichino A (1987) The scattering of electromagnetic waves from rough surfaces, 2nd edn. Artech House Inc, Norwood, USA
Bosch A, Zisserman A, Munoz X (2006) Scene classification via plsa. In: Proceedings of the European conference on computer vision, Graz, Austria, pp 517–530
Burghouts G, Geusebroek JM (2009) Performance evaluation of local colour invariants. Comput Vis Image Understand 113(1):48–62
Canny J (1986) Computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698
Chang P, Krumm J (1999) Object recognition with color cooccurrence histograms. In: In IEEE conference on computer vision and pattern recognition (CVPR), vol 2, p 504
Chen X, Hu X, Shen X (2009) Spatial weighting for bag-of-visual-words and its application in content-based image retrieval. In: Advances in knowledge discovery and data mining, lecture notes in computer science, vol 5476, pp 867–874
Chu DM, Smeulders AWM (2010) Color invariant surf in discriminative object tracking. In: ECCV workshop on color and reflectance in imaging and computer vision, Heraklion, Crete, Greece
Ciocca G, Marini D, Rizzi A, Schettini R, Zuffi S (2001) On pre-filtering with retinex in color image retrieval. In: Proceedings of the SPIE Conference on Internet Imaging II, San Jos, California, USA, vol 4311, pp 140–147
Dahl A, Aanaes H (2008) Effective image database search via dimensionality reduction. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop, Anchorage, Alaska, pp 1–6
Dinet E, Kubicki E (2008) A selective attention model for predicting visual attractors. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing, États-Unis, pp 697–700
Elsayad I, Martinet J, Urruty T, Djeraba C (2010) A new spatial weighting scheme for bag-of-visual-words. In: Proceedings of the international workshop on content-based multimedia indexing (CBMI 2010), Grenoble, France, pp 1 –6
Farag A, Abdel-Hakim A (2004) Detection, categorization and recognition of road signs for autonomous navigation. In: Proceedings of Advanced Concepts in Intelligent Vision Systems, Brussel, Belgium, pp 125–130
Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59:167–181
Finlayson G, Hordley S (2001) Colour constancy at a pixel. J Opt Soc Am 18(2):253–264
Finlayson GD, Trezzi E (2004) Shades of gray and colour constancy. In: Proceeding color imaging conference, Scottsdale, Arizona, pp 37–41
Finlayson G, Drew M, Funt B (1994) Color constancy : generalized diagonal transforms suffice. J Opt Soc Am 11(A):3011–3020
Finlayson GD, Drew MS, Funt BV (1994b) Spectral sharpening : sensor transformations for improved color constancy. J Opt Soc Am 11(A):1553–1563
Finlayson G, Chatterjee S, Funt B (1995) Color angle invariants for object recognition. In: Proceedings of the 3rd IS&T/SID color imaging conference, Scottsdale, Arizona, pp 44–47
Finlayson G, Schiele B, Crowley J (1998) Comprehensive colour image normalization. Lecture notes in computer science 1406:475–490. URL citeseer.nj.nec.com/finlayson98comprehensive.html
Finlayson G, Hordley S, Hubel P (2001) Color by correlation: a simple, unifying framework for color constancy. IEEE Trans Pattern Anal Mach Intell 23(11):1209–1221
Finlayson G, Drew M, Lu C (2004) Intrinsic images by entropy minimization. In: Proceedings of the European conference on computer vision, Prague, Czech Republic, pp 582–595
Finlayson G, Hordley S, Schaefer G, Tian GY (2005) Illuminant and device invariant colour using histogram equalisation. Pattern Recogn 38:179–190
Forssén PE (2007) Maximally stable colour regions for recognition and matching. In: IEEE conference on computer vision and pattern recognition, IEEE computer society, IEEE, Minneapolis, USA
Forssén P, Moe A (2009) View matching with blob features. Image Vis Comput 27(1–2): 99–107
Frangi A, Niessen W, Vincken K, Viergever M (1998) Multiscale vessel enhancement filtering. In: Proceeding of the MICCAI98 lecture notes in computer science, Berlin, vol 1496, pp 130–137
Funt B, Finlayson G (1995) Color constant color indexing. IEEE Trans Pattern Anal Mach Intell 17(5):522–529
Funt B, Cardei VC, Barnard K (1999) Method of estimating chromaticity of illumination using neural networks. In: United States Patent, USA, vol 5,907,629
Gabriel P, Hayet JB, Piater J, Verly J (2005) Object tracking using color interest points. In: IEEE conference on advanced video and signal based surveillance, IEEE computer society, Los Alamitos, CA, USA, vol 0, pp 159–164
Gao K, Lin S, Zhang Y, Tang S, Ren H (2008) Attention model based sift keypoints filtration for image retrieval. In: Proceedings of seventh IEEE/ACIS international conference on computer and information science, Washington, DC, USA, pp 191–196
Geusebroek J (2000) Color and geometrical structure in images. PhD thesis, University of Amsterdam
Geusebroek J (2006) Compact object descriptors from local colour invariant histograms. In: British machine vision conference, vol 3, pp 1029–1038
Geusebroek JM, van den Boomgaard R, Smeulders AWM, Dev A (2000) Color and scale: the spatial structure of color images. In: Proceedings of the European conference on computer vision, Dublin, Ireland, pp 331–341
Geusebroek JM, van den Boomgaard R, Smeulders AWM, Geerts H (2001) Color invariance. IEEE Trans Pattern Anal Machine Intell 23(12):1338–1350
Gevers T, Smeulders A (1999) Color-based object recognition. Pattern Recogn 32:453–464
Gevers T, Stokman H (2004) Robust histogram construction from color invariants for object recognition. IEEE Trans Pattern Anal Mach Intell 23(11):113–118
Goedem T, Tuytelaars T, Gool LV (2005) Omnidirectional sparse visual path following with occlusion-robust feature tracking. In: 6th workshop on omnidirectional vision, camera networks and non-classical cameras, OMNIVIS05, in Conjunction with ICCV 2005, Beijing, China
Gouet V, Montesinos P, Deriche R, Pel D (2000) Evaluation de dtecteurs de points d’intrt pour la couleur. In: Proceeding congrs Francophone AFRIF-AFIA, Reconnaissance des Formes et Intelligence Artificielle, Paris, vol 2, pp 257–266
Hamilton Y, Gortler S, Zickler T (2008) A perception-based color space for illumination invariant image processing. In: Proceeding of the special interest group in GRAPHics (SIGGRAPH), Los Angeles, California, USA, vol 27, pp 1–7
Harris C, Stephens M (1988) A combined corner and edge detector. In: Proceedings of the 4th Alvey vision conference, Manchester, pp 147–151
Healey G, Slater D (1995) Global color contancy:recognition of objects by use of illumination invariant properties of color distributions. J Opt Soc Am 11(11):3003–3010
Hegazy D, Denzler J (2008) Boosting colored local features for generic object recognition. Pattern Recogn Image Anal 18(2):323–327
Heidemann G (2004) Focus-of-attention from local color symmetries. PAMI 26(7):817–830
Heitger F, Rosenthaler L, von der Heydt R, Peterhans E, Kubler O (1992) Simulation of neural contour mechanisms: from simple to end-stopped cells. Vis Res 32(5):963–981
Hou X, Zhang L (2007) Saliency detection: a spectral residual approach. IEEE computer society conference on computer vision and pattern recognition 0:1–8
Hu L, Jiang S, Huang Q, Gao W (2008) People re-detection using adaboost with sift and color correlogram. In: Proceedings of the IEEE international conference on image processing, San Diego, California, USA, pp 1348–1351
Huang J, Kumar SR, Mitra M, Zhu W, Zabih R (1997) Image indexing using color correlogram. IEEE conference on computer vision and pattern recognition pp 762–768
Inria database. URL http://lear.inrialpes.fr/data
Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254–1259
(ITU) IRCC (1990) Basic parameter values for the hdtv standard for the studio and for international programme exchange. Tech. Rep. 709-2, CCIR Recommendation
Jost T, Ouerhani N, von Wartburg R, Muri R, Hugli H (2005) Assessing the contribution of color in visual attention. Comput Vis Image Understand 100:107–123
Khan F, van de Weijer J, Vanrell M (2009) Top-down color attention for object recognition. In: Proceedings of the international conference on computer vision, Japan, pp 979–986
Klinker G, Shafer S, Kanade T (1991) A physical approach to color image understanding. Int J Comput Vis 4(1):7–38
von Kries J (1970) Influence of adaptation on the effects produced by luminous stimuli. In: MacAdam, D.L. (ed) Sources of color vision. MIT Press, Cambridge
Kubelka P (1948) New contribution to the optics of intensity light-scattering materials, part i. J Opt Soc Am A 38(5):448–457
Lambert JH (1760) Photometria sive de mensure de gratibus luminis, colorum umbrae. Eberhard Klett
Land E (1977) The retinex theory of color vision. Sci Am 237:108–129
Land E (1986) An alternative technique for the computation of the designator in the retinex theory of color vision. In: Proceedings of the national academy science of the United State of America, vol 83, pp 3078–3080
Lenz R, Tran L, Meer P (1999) Moment based normalization of color images. In: IEEE workshop on multimedia signal processing, Copenhagen, Denmark, pp 129–132
Li J, Allinson NM (2008) A comprehensive review of current local features for computer vision. Neurocomput 71(10-12):1771–1787. DOI http://dx.doi.org/10.1016/j.neucom. 2007.11.032
Lindeberg T (1994) Scale-space theory in computer vision. Springer, London, UK
Locher P, Nodine C (1987) Symmetry catches the eye. Eye Movements: from physiology to cognition, North-Holland Press, Amsterdam
Logvinenko AD (2009) An object-color space. J Vis 9:1–23
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Luke RH, Keller JM, Chamorro-Martinez J (2008) Extending the scale invariant feature transform descriptor into the color domain. Proc ICGST Int J Graph Vis Image Process, GVIP 08:35–43
Marques O, Mayron L, Borba G, Gamba H (2006) Using visual attention to extract regions of interest in the context of image retrieval. In: Proceedings of the 44th annual Southeast regional conference, ACM, ACM-SE 44, pp 638–643
Matas J, Chum O, Martin U, Pajdla T (2002) Robust wide baseline stereo from maximally stable extremal regions. In: Proceeding of the British machine vision conference, pp 384–393
Mikolajczyk K, Schmid C (2004) Scale & affine invariant interest point detectors. Int J Comput Vision 60:63–86
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27:1615–1630
Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Gool LV (2005) A comparison of affine region detectors. Int J Comput Vis 65(1/2):43–72. URL http://lear.inrialpes.fr/pubs/2005/MTSZMSKG05
Mindru F, Moons T, van Gool L (1999) Recognizing color patterns irrespective of viewpoints and illuminations. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 368–373
Mindru F, Tuytelaars T, Gool LV, Moons T (2004) Moment invariants for recognition under changing viewpoint and illumination. Comput Vis Image Understand 1(3):3–27
Ming A, Ma H (2007) A blob detector in color images. In: Proceedings of the 6th ACM international conference on image and video retrieval, ACM, New York, NY, USA, CIVR ’07, pp 364–370
Mollon J (2006) Monge: The verriest lecture, lyon, july 2005. Visual Neurosci 23:297–309
Montesinos P, Gouet V, Deriche R (1998) Differential invariants for color images. In: Proceedings of the international conference on pattern recognition, Brisbane (Australie), vol 1, pp 838–840
Montesinos P, Gouet V, Deriche R, Pel D (2000) Matching color uncalibrated images using differential invariants. Image Vis Comput 18(9):659–671
Moosmann F, Larlus D, Jurie F (2006) Learning Saliency Maps for Object Categorization. In: ECCV international workshop on the representation and use of prior knowledge in vision
Moravec H (1977) Towards automatic visual obstacle avoidance. In: Proceedings of the 5th international joint conference on artificial intelligence, p 584
Nilsback ME, Zisserman A (2008) Automated flower classification over a large number of classes. In: Proceedings of the indian conference on computer vision, graphics image processing, pp 722 –729
Poynton’s web page. URL http://www.poynton.com/notes/colour_and_gamma/GammaFAQ.html
Qiu G (2002) Indexing chromatic and achromatic patterns for content-based colour image retrieval. Pattern Recogn 35(8):1675–1686
Quelhas P, Odobez J (2006) Natural scene image modeling using color and texture visterms. In: Proceedings of conference on image and video retrieval, Phoenix, USA, pp 411–421
Recognition benchmark images. URL http://www.vis.uky.edu/stewe/ukbench/
Reisfeld D, Wolfson H, Yeshurun Y (1995) Context-free attentional operators: the generalized symmetry transform. Int J Comput Vis 14:119–130
Rosenberg C, Hebert M, Thrun S (2001) Color constancy using kl-divergence. In: IEEE international conference on computer vision, pp 239–246
Rutishauser U, Walther D, Koch C, Perona P (2004) Is bottom-up attention useful for object recognition? In: IEEE conference on computer vision and pattern recognition (CVPR), pp 37–44
van de Sande K, Gevers T, Snoek C (2010a) Evaluating color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Intell 32:1582–1596
van de Sande KE, Gevers T, Snoek CG (2010) Evaluating color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Intell 32:1582–1596
Schugerl P, Sorschag R, Bailer W, Thallinger G (2007) Object re-detection using sift and mpeg-7 color descriptors. In: Proceedings of the international workshop on multimedia content analysis and mining, pp 305–314
Sebe N, Gevers T, Dijkstra S, van de Weije J (2006a) Evaluation of intensity and color corner detectors for affine invariant salient regions. In: Proceedings of the 2006 conference on computer vision and pattern recognition workshop, IEEE computer society, Washington, DC, USA, CVPRW ’06, pp 18–25
Sebe N, Gevers T, van de Weijer J, Dijkstra S (2006) Corners detectors for affine invariant salient regions: is color important? In: Proceedings of conference on image and video retrieval, Phoenix, USA, pp 61–71
Shafer SA (1985) Using color to separate reflection components. Color Res Appl 10(4):210–218
Shi L, Funt B, Hamarneh G (2008) Quaternion color curvature. In: Proceeding IS&T sixteenth color imaging conference, Portland, pp 338–341
Sikora T (2001) The mpeg-7 visual standard for content description - an overview. IEEE Trans Circ Syst Video Technol 11:696–702
Song X, Muselet D, Tremeau A (2009) Local color descriptor for object recognition across illumination changes. In: Proceedings of the conference on advanced concepts for intelligent vision systems (ACIVS’09), Bordeaux (France), pp 598–605
Stentiford FWM (2003) An attention based similarity measure with application to content-based information retrieval. In: Proceedings of the storage and retrieval for media databases conference, SPIE electronic imaging
Stoettinger J, Hanbury A, Sebe N, Gevers T (2007) Do colour interest points improve image retrieval? In: Proceedings of the IEEE international conference on image processing, San Antonio (USA), vol 1, pp 169–172
Stokes M, Anderson M, Chandrasekar S, Motta R (1996) A standard default color space for the internet-srgb, Available from http://www.w3.org/Graphics/Color/sRGB.html
Tuytelaars T, Mikolajczyk K (2008) Local invariant feature detectors: a survey. Found Trends Comput Graph Vis 3(3):177–280
Vazquez E, Gevers T, Lucassen M, van de Weijer J, Baldrich R (2010) Saliency of color image derivatives: a comparison between computational models and human perception. J Opt Soc Am A 27(3):613–621
Vázquez-Martína R, Marfila R, nez PN, Bandera A, Sandoval F (2009) A novel approach for salient image regions detection and description. Pattern Recogn Lett 30:1464–1476
Vigo DAR, Khan FS, van de Weijer J, Gevers T (2010) The impact of color on bag-of-words based object recognition. In: International conference on pattern recognition, pp 1549–1553
Vogel J, Schiele B (2004) A semantic typicality measure for natural scene categorization. In: Rasmussen CE, Blthoff HH, Schlkopf B, Giese MA (eds) Pattern recognition, lecture notes in computer science, vol 3175, Springer Berlin/Heidelberg, pp 195–203
Walther D, Rutishauser U, Koch C, Perona P (2005) Selective visual attention enables learning and recognition of multiple objects in cluttered scenes. Comput Vis Image Understand 100:41–63
Wandell B (1987) The synthesis and analysis of color images. IEEE Trans Pattern Anal Mach Intell 9:2–13
van de Weijer J, Schmid C (2006) Coloring local feature extraction. In: Proceedings of the ninth European conference on computer vision, Graz, Austria, vol 3954, pp 334–348
van de Weijer J, Schmid C (2007) Applying color names to image description. In: Proceedings of the IEEE international conference on image processing, San Antonio (USA), vol 3, pp 493–496
van de Weijer J, Gevers T, Geusebroek JM (2005) Edge and corner detection by photometric quasi-invariants. IEEE Trans Pattern Anal Mach Intell 27(4):625–630
van de Weijer J, Gevers T, Bagdanov A (2006) Boosting color saliency in image feature detection. IEEE Trans Pattern Anal Mach Intell 28(1):150–156
van de Weijer J, Gevers T, Smeulders A (2006b) Robust photometric invariant features from the colour tensor. IEEE Trans Image Process 15(1):118–127
Wu P, Kong L, Li X, Fu K (2008a) A hybrid algorithm combined color feature and keypoints for object detection. In: Proceedings of the 3rd IEEE conference on industrial electronics and applications, Singapore, pp 1408–1412
Wu P, Kong L, Zhao F, Li X (2008) Particle filter tracking based on color and sift features. In: Proceedings of the international conference on audio, language and image processing, Shanghai
Wurtz R, Lourens T (2000) Corner detection in color images through a multiscale combination of end-stopped cortical cells. Image Vis Comput 18(6-7):531–541
Wyszecki G, Stiles WS (1982) Color science: concepts and methods, quantitative data and formulas, 2nd ed. Wiley, New York
Xiong W, Funt B (2006) Color constancy for multiple-illuminant scenes using retinex and svr. In: Proceeding of imaging science and technology fourteenth color imaging conference, pp 304–308
Zhang D, Wang W, Gao W, Jiang S (2007) An effective local invariant descriptor combining luminance and color information. In: Proceedings of IEEE international conference on multimedia and expo, Beijing (China), pp 1507–1510
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Muselet, D., Funt, B. (2013). Color Invariants for Object Recognition. In: Fernandez-Maloigne, C. (eds) Advanced Color Image Processing and Analysis. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-6190-7_10
Download citation
DOI: https://doi.org/10.1007/978-1-4419-6190-7_10
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-6189-1
Online ISBN: 978-1-4419-6190-7
eBook Packages: EngineeringEngineering (R0)