Abstract. The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image.A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.
ABSTRACT:We studied the interactions of nylon-6 with water by following the Fourier transform infrared spectra of a hydrated thin film during dehydration. Very small changes in the spectra caused by the interactions were clearly revealed by the application of spectral subtraction. The water was found to interact with amide groups to form hydrogen bonds with non-hydrogen-bonded or free C¢O and NH groups in the amorphous portion in the first hydration sphere. This was deduced from an analysis of minus and plus peaks appearing around the absorptions of the NH stretching, amide I band, and amide II bands in the difference spectra between the spectra during dehydration and the one at the most dehydration. The interactions of the amide groups with water were significantly stronger than the hydrogen bond between CO and NH in the crystalline portion, according to the magnitude of the frequency shift of relevant bands. Water, as the interacting counterpart, showed a distorted OH stretching absorption with two close peaks at about 3450 cm Ϫ1 .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.