An efficient and accurate approach of circular object detection in color images

• A fully automatic approach of color image edge detection is proposed.
• The edge detection algorithm is integrated with a novel circle detection algorithm efficiently.
• Three circle parameters are estimated with attractively low time complexity and memory requirement.
• Objects with incomplete or concentric circle boundary in real color images without any prior knowledge can be located.

Object detection is a critical step of many image recognition systems. In this paper, we discuss the problem of circular shape object detection in still color images. An isotropic edge detector merged with spatial information and region based analysis is employed to extract image edge and obtain accurate gradient information of edge pixels, which assures the high accuracy of the subsequent circle detection. Then three circle parameters are estimated efficiently with only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduces the storage requirements and time complexity of our approach. Experimental results show that our method is robust in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.