Combining Geometric Invariants With Fuzzy Clustering For Object Recognition

Object recognition is the process of identifying the types and locations of objects in the image. Earlier work has shown the desirability of using fuzzy compatibility for local feature correspondence and fuzzy clustering for pose estimation of two-dimensional objects. This paper extends the methodology to images of three dimensional objects by applying geometric invariants, specifically the cross ratio of four collinear points. The recognition process is divided into three subtasks: local feature correspondence, object identification, and pose determination. Algorithms are described for each subtask.