We present a novel depth image enhancement approach for RGB-D cameras such as the Kinect. Our approach employs optical flow of color images for refining the quality of corresponding depth images. We track every depth pixel over a sequence of frames in the temporal domain and use valid depth values of the same point for recovering missing and inaccurate information. We conduct experiments on dif...

Frequently, images of rare documents must be taken under strict time constraints, when a chance opportunity arises, and with equipment that is less than ideally suited for precise digitization. This can often result in uncalibrated images whose contents are nonetheless qualitatively useful. Due to the logistics of document imaging, perspective distortion is a common artifact which can manifest ...

In this paper, we propose a new method for correcting distorted document images using a stereo camera pair. Geometric and photometric distortions may occur in document images of thick book pages because of its curved surfaces. The proposed method acquires document shape by stereo measurement to correct geometric distortions in images. By considering normal vectors of document surfaces, optimum-...

We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into a space where they cluster according to their partial-match feature correspondences. After efficiently computing the pairwise affinities between the input images in this space, a spectral clustering technique is used ...

We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into a space where they cluster according to their partial-match feature correspondences. After efficiently computing the pairwise affinities between the input images in this space, a spectral clustering technique is used ...

optimum error correcting code for a WSN where both, the performance and energy consumption are taken into So to help the scholars in finding Optimization metric used to compare the performance of message passing algorithm (MPA) and sum-product (1) Chong C.Y. and Kumar S.P. Sensor networks: Evolution. proposed a Continuous Genetic Algorithm (CGA) to achieve the best subset of hyperspectral image...

People often encounter situations where they need to recall past experiences from their daily life. In this paper, we aim construct a question answering system that enables human query over personal knowledge base. Previous works on base focus finding answers for answerable questions. the real world applications, however, people muddle up facts and ask those questions cannot be answered with Th...

We report the design of a mirror correcting system used at the Large Helical Device (LHD) to convert the output radiation of the CPI 84 GHz gyrotron into the HE11 mode of a corrugated waveguide transmission line. The radiation pattern of the gyrotron is measured using an IR camera at LHD. The measured data is analyzed at MIT to retrieve the phase distribution of the radiation. The moments of th...

use of auxiliary elements in refining and betterment of engineering properties of soil have gained attention since a long time ago. nowadays the effectiveness and capability of the soil reinforcing technique for giving proper practical solutions in various projects have resulted in this technique quickly gaining a place in geotechnical engineering. in this paper, the results of laboratory studi...

This chapter describes a method of segmenting MR images into different tissue classes, using a modified Gaussian Mixture Model. By knowing the prior spatial probability of each voxel being grey matter, white matter or cerebro-spinal fluid, it is possible to obtain a more robust classification. In addition, a step for correcting intensity non-uniformity is also included, which makes the method m...