Automatic Color Image Segmentation Based on Illumination Invariant and Superpixelization

Superpixel and invariant methods for color images are becoming increasingly popular in many applications of computer vision and image analysis. This paper presents an automatic segmentation based on illumination invariant and superpixelization methods. We develop an automatic superpixel generation method by automatically modifying the quick-shift parameters based on invariant images. The proposed method segments a color image into homogeneous regions by applying quick-shift method with initial parameters, and then automatically get the final segmented image by calculating the best similarity between the output image and the invariant image by changing the quick-shift parameters values. To reduce the number of colors in image that will be used in comparison, a quantization process is applied to the original invariant image. Changing parameters values in iterations instead of using a specific value made the proposed algorithm flexible and robust against different image characteristics. The effectiveness of the proposed method for a variety of images including different objects of metals and dielectrics are examined in experiments.

[1]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[3]  Katsushi Ikeuchi,et al.  Separating Reflection Components of Textured Surfaces Using a Single Image , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Arnold W. M. Smeulders,et al.  Color Invariance , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  S. Athi Narayanan,et al.  A Hybrid Method for Image Quantization , 2009 .

[6]  Nasser Kehtarnavaz,et al.  DWT-based scene-adaptive color quantization , 2005, Real Time Imaging.

[7]  Umar Mohammed,et al.  Superpixel lattices , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Sing Bing Kang,et al.  Stereo for Image-Based Rendering using Image Over-Segmentation , 2007, International Journal of Computer Vision.

[9]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Takahiko Horiuchi.  Similarity measure of labelled images , 2004, ICPR 2004.

[11]  Stefano Soatto,et al.  Motion segmentation with occlusions on the superpixel graph , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[12]  David J. Kriegman,et al.  Beyond Lambert: reconstructing specular surfaces using color , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Stefano Soatto,et al.  Class segmentation and object localization with superpixel neighborhoods , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[14]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Stefano Soatto,et al.  Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[16]  S. Avidan,et al.  Seam carving for content-aware image resizing , 2007, SIGGRAPH 2007.

[17]  Sven J. Dickinson,et al.  TurboPixels: Fast Superpixels Using Geometric Flows , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Arnold W. M. Smeulders,et al.  Color-based object recognition , 1997, Pattern Recognit..

[19]  Takahiko Horiuchi,et al.  Illumination-invariant representation for natural color images and its application , 2012, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation.

[20]  Takahiko Horiuchi,et al.  Invariant representation for spectral reflectance images and its application , 2011, EURASIP J. Image Video Process..

[21]  Jianbo Shi,et al.  Spectral segmentation with multiscale graph decomposition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[22]  Ian Reid,et al.  gSLIC: a real-time implementation of SLIC superpixel segmentation , 2011 .

[23]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..