Personal identification by extracting SIFT features from laser speckle patterns

This paper presents a novel personal identification method by extracting unique object features from optical speckle patterns using the SIFT (Scale Invariant Feature Transform) algorithm. Accurate identification is achieved by developing an invariant speckle capturing device and recognition criteria. Experimental results show that optical speckle pattern of a given material is invariant after slight movement and the patterns captured from different areas of the same material are distinct. Therefore, this merit can be adopted for security applications by using the surface of specific object as the personal identification card and extracting speckle patterns from this surface to recognize the identity of certain subject.