Color indexing

Abstract

Computer vision is embracing a new research focus in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, realistic environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determining the location of a known object. Color can be successfully used for both tasks.This article demonstrates that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and image histograms and a fast incremental version of Histogram Intersection, which allows real-time indexing into a large database of stored models. For solving the location problem it introduces an algorithm called Histogram Backprojection, which performs this task efficiently in crowded scenes.

Local grayvalue invariants for image retrieval

“…The idea is not to impose what has to be seen in the image (points, lines º) but rather to use what is really seen in the image to characterize an object. The first idea was to use color histograms [8]. Several authors have improved the performance of the original color histogram matching technique by introducing measures which are less sensitive to illumination changes [9], [10], [11], [12].…”

Diagnostic Colors Mediate Scene Recognition

“…It is not derived from the identity of the objects (textural information, detailed contours, and cast shadows are not well represented on coarser scales). The role of coarse scene backgrounds in object identification clearly deserves further exploration because the identification of the former could facilitate the processing of the latter, both in humans and machines (e.g., Oliva, Torralba, Guerin-Dugue, & Herault, 1999;Swain, & Ballard, 1991;Vailaya, Jain, & Zhang, 1998).…”

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

“…To measure the similarity between consecutive frames, we use the histogram intersection [58] as: 1] is, the more similar b i−1 and b i are. Then, the dissimilarity is defined as:…”