Proc. SPIE. 8919, MIPPR 2013: Pattern Recognition and Computer Vision
KEYWORDS: Visual process modeling, Detection and tracking algorithms, Data modeling, Visualization, Image segmentation, Diffusion, Computer vision technology, Machine vision, Algorithm development, RGB color model
Visual saliency has recently attracted lots of research interest in the computer vision community. In this paper, we
propose a novel computational model for bottom-up saliency detection based on manifold learning. A typical graphbased
manifold learning algorithm, namely the diffusion map, is adopted for establishing our saliency model. In the
proposed method, firstly, a graph is constructed using low-level image features. Then, the diffusion map algorithm is
performed to learn the diffusion distances, which are utilized to derive the saliency measure. Compared to existing
saliency models, our method has the advantage of being able to capture the intrinsic nonlinear structures in the original
feature space. Moreover, due to the inherent characteristics of the diffusion map algorithm, our method can deal with the
multi-scale issue effectively, which is crucial to any saliency model. Experimental results on publicly available data
demonstrate that our method outperforms the state-of-the-art saliency models, both qualitatively and quantitatively.
Small angle measurement has been widely use for the alignment or error compensation of a mechanical system. In this paper a small angle dynamic measurement device based on laser interference technique is introduced, which consists of a reference module and a measuring module. The measuring module is fixed on the measured object. With the variation of the small tilt angle of the measured object, the phase difference between the two beams from prism1 and prism2 changes according to it. By analyzing the interference patterns, the variation of the small tilt angle can be obtained dynamically. Experimental setup has been established and the results show that the measurement range is 15' with the resolution of 0.08", the measurement error is less than 8″.