Search

The polarization phenomenon occurs when the sunlight is scattered by atmospheric molecules. As a result, there is a polarization pattern in the sky. An amount of research shows that many nature insects can derive orientation information from this pattern, such as bees and ants. The fundamental polarization pattern in the sky is presented. The characters and the orientation mechanism of the nature insects are discussed. The basic principle of designing the polarization skylight navigation sensor is explained. The domestic and foreign relevant researches and application situation of this new navigation method are summarized in details. In the end, the characters of application fields and its application prospect are previewed.

3D face sample is an important data platform for model training, algorithm design. Subject to the constraint of data acquisition equipment the size of current 3D face databases are relatively small and insufficient. To solve this problem, this paper presents a modeling way for generating 3D novel samples based on surface stitching. First we use morphable model to build a global model. Then, we replace each patch of the global model based on surface stitching. We demonstrate that with appropriate choice of local models it is possible to reliably generate new realistic face samples.

The traditional craniofacial reconstruction methods construct the face shape according to the soft tissue thickness measured at a sparse set of landmarks on the skull. But the landmarks are difficult to detect and generally need human interactive assistance. The quantity and position of the landmarks lack for uniform definition. We propose an automatic craniofacial reconstruction method based on a dense deformable model. To construct the model, hundreds of skull and face samples are acquired by CT scanner. A dense mesh registration algorithm is proposed to build the point-to-point correspondences of the samples. Based on the aligned samples, the deformable model is constructed. For a given skull, the reconstructed face is obtained by a model matching procedure. Experimental results indicate that the deformable model has good performance for craniofacial reconstruction.

This paper explores an image fusion algorithm based on self-adaptive fuzzy clustering algorithm. The clustering method combined nearest neighbor clustering method with k-means clustering method (NNKM) is adopted in pixel classification. The membership of every image pixel to each cluster center is introduced. And the fused image membership obtained by maximum rule is adopted as the weighting coefficient of the weighted mean strategy, which is used to obtain the fusion image. In this experiment, the fusion results of various Radiuses of Gauss function are compared with the results obtained by nearest neighbor clustering method. The experiment results show that the proposed method can achieve better performance of the fused image.

In this paper, Transiently Chaotic Neural Network (TCNN) is used in wavelet image fusion method. This paper adopts the weighted average strategy for the fusion of the wavelet transform coefficients. The TCNN outputs the weighting coefficient of every wavelet transform pixel when the energy function of the neural network has achieved the global minimum. At the same time, the average gradient value of the region around every wavelet transform pixel gets the global maximum according to the relationship between the average gradient and energy. The wavelet transform coefficients of the fused image are got by using the weighting coefficients. The advantage of the algorithm is that the weighting coefficient is obtained through the dynamic searching optimization of the average gradient. Experiments show that the average gradient values of the fusion images using the proposed method are greater than the results using the region energy method. The TCNN method improves the performance of the fusion image effectively.

Caused by light reflected off the subject's retina, red-eye is a troublesome problem in consumer photography. Although most of the cameras have the red-eye reduction mode, the result reality is that no on-camera system is completely effective. In this paper, we propose a fully automatic approach to detecting and correcting red-eyes in digital images. In order to detect red-eyes in a picture, a heuristic yet efficient algorithm is first adopted to detect a group of candidate red regions and then an eye classifier is utilized to confirm whether each candidate region is a human eye. Thereafter, for each detected redeye, we can correct it by the correction algorithm. In case that a red-eye cannot be detected automatically, another algorithm is also provided to detect red-eyes manually with the user's interaction by clicking on an eye. Experimental results on about 300 images with various red-eye appearances demonstrate that the proposed solution is robust and effective.

MiAlbum© (v1.0) is a system developed at Microsoft Research China for managing family photos with the help of a semi-automatic image annotation approach. It provides functionalities to import (from scanner, digital camera, disks, PC, CD, web, etc), label (keyword, name, place, etc.), categorize (by automatic classification into some predefined classes), manipulate (in some ways), and export (send or print) family photo images. In this demo, we show the efficiency of the semi-automatic image annotation method and its help in improving the image retrieval accuracy.