IHBM: Integrated Histogram Bin Matching For Similarity Measures of Color Image Retrieval

The selection of “proper similarity measure” of color histograms is an essential consideration for the success of many methods. The Histogram Quadratic Distance Measure (HQDM) is a metric distance. Till today, this method is supposed to be the better choice, But it holds a disadvantage that it can compute the cross similarity between all elements of histograms. Therefore, computationally it is more expensive. This paper proposes a method that is known as Integrated Histogram Bin Matching (IHBM) which is also a metric method, and overcomes the disadvantages of the HQDM. The proposed IHBM first matches the closest Histogram Bin Pair according to the distance matrix determined from color histograms, which satisfies the Monge condition. After matching histogram bins, the similarity measure is computed as a weighed sum of the similarity between histogram bin pairs, with weights determined by the matching scheme. The proposed IHBM is experimented on 1000 color images and results are compared with the existing methods.