Quantization Selection of Colour Histogram Bins to Categorize the Colour Appearance of Landscape Paintings for Image Retrieval

In the world of today, most images are digitized and kept in digital libraries for better organization and management. With the growth of information and communication technology, collection holders such as museums or cultural institutions have been increasingly interested in making their collections available anytime and anywhere for any Image Retrieval (IR) activities such as browsing and searching. In a colour image retrieval application, images retrieved by users are accomplished according to their specifications on what they want or acquire, which could be based upon so many concepts. We suggest an  approach to categorize the colour appearances of whole scene landscape painting images based on human colour perception. The colour features in the image are represented using a colour histogram. We then find  the suitable quantization bins that can be used to generate optimum colour histograms for all categories of colour appearances, which is selected based on theHarmonic Mean of the precision and recall,  also known as F-Score percentage higher saturated value. Colour appearance attributes in the CIELab colour model (L-Lightness, a and b are colour-opponent dimension) are used to generate colour appearance feature vectors namely the saturation metric, lightness metric and multicoloured metric. For the categorizations, we use the Nearest Neighbour (NN) method to detect the classes by using the predefined colour appearance descriptor measures and the pre-set thresholds.  The experimental results show that the quantization of CIELab colour model into 11 uniformly bins for each component had achieved the optimum result for all colour appearances categories.

[1]  Steffen Beich,et al.  Digital Video And Hdtv Algorithms And Interfaces , 2016 .

[2]  E. Soljanin,et al.  Quantization of color spaces by Fibonacci lattices , 2001, Proceedings. 2001 IEEE International Symposium on Information Theory (IEEE Cat. No.01CH37252).

[3]  Ali Borji,et al.  Salient Object Detection: A Benchmark , 2015, IEEE Transactions on Image Processing.

[4]  Tasneem Mirza,et al.  Content based Image Retrieval using Color and Texture , 2016 .

[5]  J. Keilwagen,et al.  Area under Precision-Recall Curves for Weighted and Unweighted Data , 2014, PloS one.

[6]  Yoo-Joo Choi,et al.  Deciding the Number of Color Histogram Bins for Vehicle Color Recognition , 2008, 2008 IEEE Asia-Pacific Services Computing Conference.

[7]  H. B. Kekre,et al.  COLOR FEATURE EXTRACTION FOR CBIR , 2011 .

[8]  Moacir Ponti,et al.  Image quantization as a dimensionality reduction procedure in color and texture feature extraction , 2016, Neurocomputing.

[9]  A. Ciobanu,et al.  Color feature vectors based on optimal LAB histogram bins , 2014, 2014 International Conference on Development and Application Systems (DAS).

[10]  Joon Hee Han,et al.  Image indexing using weighted color histogram , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[11]  Mohammad Atique,et al.  A Novel Localized Entropy-based Medical Image Retrieval , 2016 .

[12]  Baharum Baharudin,et al.  Analysis of distance metrics in content-based image retrieval using statistical quantized histogram texture features in the DCT domain , 2013, J. King Saud Univ. Comput. Inf. Sci..

[13]  Chuanbo Yan,et al.  Feature extraction and analysis on Xinjiang uygur medicine image by using color histogram , 2013, 2013 IEEE International Conference on Medical Imaging Physics and Engineering.

[14]  Pratap Singh Patwal,et al.  A Content-Based Indexing System for Image Retrieval , 2012 .

[15]  Samia Boucherkha,et al.  Color quantization and its impact on color histogram based image retrieval accuracy , 2009, 2009 First International Conference on Networked Digital Technologies.

[16]  Kien A. Hua,et al.  Exploit Every Bit: Effective Caching for High-Dimensional Nearest Neighbor Search , 2016, IEEE Transactions on Knowledge and Data Engineering.

[17]  Minetada Osano,et al.  Cross-Language Similarity between Perceptual and Semantic Structures of Color Tones , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[18]  Jing-Yu Yang,et al.  Content-based image retrieval using computational visual attention model , 2015, Pattern Recognit..

[19]  A. Vadivel,et al.  Smooth Weighted Approach for Colour Histogram Construction using Human Colour Perception for CBIR Applications , 2012 .

[20]  Michael J. Swain,et al.  The capacity of color histogram indexing , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Francisco Herrera,et al.  IFROWANN: Imbalanced Fuzzy-Rough Ordered Weighted Average Nearest Neighbor Classification , 2015, IEEE Transactions on Fuzzy Systems.

[22]  Hassan Farsi,et al.  Colour and texture feature-based image retrieval by using hadamard matrix in discrete wavelet transform , 2013, IET Image Process..

[23]  Jing-Yu Yang,et al.  Content-based image retrieval using color difference histogram , 2013, Pattern Recognit..

[24]  Ioannis Pitas,et al.  Color-based descriptors for image fingerprinting , 2006, IEEE Transactions on Multimedia.

[25]  Nurul Malim,et al.  New strategy for Turbo Similarity Searching: Implementation and testing , 2013, 2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[26]  Sang Uk Lee,et al.  Color-Based Image Retrieval Using Perceptually Modified Hausdorff Distance , 2008, EURASIP J. Image Video Process..

[27]  Kirk Martinez,et al.  Colour appearance descriptors for image browsing and retrieval , 2008, Electronic Imaging.

[28]  Peter Willett,et al.  Comparison of chemical similarity measures using different numbers of query structures , 2013, J. Inf. Sci..

[29]  Charles L. A. Clarke,et al.  Information Retrieval - Implementing and Evaluating Search Engines , 2010 .