A Colour Object Search Algorithm

Abstract

In this paper a colour object search algorithm is presented. Given an image, areas of interest are generated (for each database model) by isolating regions whose colours are similar to model colours. Since the model may exist at one or more of these region locations, each is examined individually. At each region location the object size is estimated and a growing process initiated to include all pixels with model colours. Growing is terminated when a match measure (based on object size and the number of pixels with each model colour) is maximised; if it exceeds a predefined threshold then the object is assumed to be present. Several experiments are presented which demonstrate the algorithm's robustness to scale, affine object distortion, varying illumination, image clutter and occlusion.

A novel color based object detection and localization algorithm

“…If we extend this conclusion to the whole image, in the corresponding backprojected image, the values of the object areas are greater than that of the background regions, and the object area is always local maxima. According to the normalized histogram of the template in equation 8, we can get another probabilistic image with the equation (9). It can overcome the drawbacks of the histogram backprojected algorithm.…”

“…Matas et al [8] used a color adjacency graph (whose nodes represent model colors and edges encode information about the adjacency of colors and their reflectance ratios) to identify object hypotheses and the color region adjacency graph for object match verification, Matas et al's graph search process is computationally expensive, but it can represent 3-dimensional deformable objects with perspective distortions. Paul A. Walcott and Tim J. Ellis [9] proposed a color object search algorithm, which included three stages: cue generation, region growing and hypotheses ranking, and this algorithm depended on its color image segmented section and had expensive computation. Many chosen parameters influenced its flexibility.…”