Comparative study of histogram distance measures for re-identification
This is an incremental study that helps researchers and practitioners in computer vision and surveillance by identifying optimal distance measures and color spaces for re-identification tasks.
The paper compared various histogram distance measures across different color spaces for color-based re-identification, finding that certain combinations performed best as indicated by area under the CMC metrics in experiments on multiple image databases.
Color based re-identification methods usually rely on a distance function to measure the similarity between individuals. In this paper we study the behavior of several histogram distance measures in different color spaces. We wonder whether there is a particular histogram distance measure better than others, likewise also, if there is a color space that present better discrimination features. Several experiments are designed and evaluated in several images to obtain measures against various color spaces. We test in several image databases. A measure ranking is generated to calculate the area under the CMC, this area is the indicator used to evaluate which distance measure and color space present the best performance for the considered databases. Also, other parameters such as the image division in horizontal stripes and number of histogram bins, have been studied.