In this paper we propose to summarize videos based on key frames. We improve upon the histogram and pixel difference based approach with fuzzy rule based approach and also give a new approach which reduces the computa...
详细信息
ISBN:
(纸本)9781479915880
In this paper we propose to summarize videos based on key frames. We improve upon the histogram and pixel difference based approach with fuzzy rule based approach and also give a new approach which reduces the computation of framewise differences. We test our methods using fidelity ratio and compression ratio on videos of sports from YouTube and UCF sports dataset, videos of commercials and sitcoms. T he results of our methods are seen to be comparable to other state of the art approaches.
Mural images are noisy and consist of faint and broken lines. Here we propose a novel technique for straight and curve line detection and also an enhancement algorithm for deteriorated mural images. First we compute s...
详细信息
ISBN:
(纸本)9781479915880
Mural images are noisy and consist of faint and broken lines. Here we propose a novel technique for straight and curve line detection and also an enhancement algorithm for deteriorated mural images. First we compute some statistics on gray image using oriented templates. the outcome of the process are taken as a strength of the line at each pixel. As a result some unwanted lines are also detected in the texture region. Based on Gestalt law of continuity we propose an anisotropic refinement to strengthen the true lines and to suppress the unwanted ones. A modified bilateral filter is employed to remove the noises. Experimental result shows that the approach is robust to restore the lines in the mural images.
Scan time reduction in MRI can be achieved by partial k-space reconstruction. Truncation of the k-space results in generation of artifacts in the reconstructed image. A subspace projection algorithm is developed for a...
详细信息
ISBN:
(纸本)9781479915880
Scan time reduction in MRI can be achieved by partial k-space reconstruction. Truncation of the k-space results in generation of artifacts in the reconstructed image. A subspace projection algorithm is developed for artifact-free reconstruction of sparse MRI. the algorithm is applied to a frequency weighted k-space, which fits into a signal-space model for sparse MR images. the application is illustrated using Magnetic Resonance Angiogram (MRA).
this paper presents an implementation of an OCR system for the Meetei Mayek script. the script has been newly reintroduced and there is a growing set of documents currently available in this script. Our system accepts...
详细信息
ISBN:
(纸本)9781479915880
this paper presents an implementation of an OCR system for the Meetei Mayek script. the script has been newly reintroduced and there is a growing set of documents currently available in this script. Our system accepts an image of the textual portion of a page and outputs the text in the Unicode format. It incorporates preprocessing, segmentation and classification stages. However, no post-processing is done to the output. the system achieves an accuracy of about 96% on a moderate database.
We propose a scalable perception framework leveraging monocular security cameras in the infrastructure for localizing and tracking indoor autonomous mobile robots. We present a zero-shot pose estimation approach that ...
详细信息
ISBN:
(纸本)9798400710759
We propose a scalable perception framework leveraging monocular security cameras in the infrastructure for localizing and tracking indoor autonomous mobile robots. We present a zero-shot pose estimation approach that combines semantic and visual descriptors to identify reliable, repeatable and robust keypoints along with a quantification of its epistemic uncertainty via a mathematical covariance model of the external camera. these pose estimates are then fused withthe robot's on-board sensors to achieve high-accuracy localization. We also enhance an optimal camera placement algorithm by constraining it withthe external camera's covariance to simultaneously maximize total coverage and localization accuracy which is an integral aspect of multi-camera robot localization systems. We show through real-world experiments that fusing pose estimates from fixed monocular security cameras with an off-the shelf visual SLAM system results in a significant improvement in localization performance alongside eliminating the kidnapped robot problem.
In this paper, we address the problem of separating the diffuse and specular reflection components of complex textured surfaces from a single color image. Unlike most previous approaches that assume accurate knowledge...
详细信息
ISBN:
(纸本)9781479915880
In this paper, we address the problem of separating the diffuse and specular reflection components of complex textured surfaces from a single color image. Unlike most previous approaches that assume accurate knowledge of illumination source color for this task, we analyze errors in source color information to perform robust separation. the analysis leads to a simple, efficient and robust algorithm to estimate the diffuse and specular components using the estimated source color. the algorithm is completely automatic and does not need explicit color segmentation or color boundary detection as required by many existing methods. Results on complex textured images show the effectiveness of the proposed algorithm for robust reflection component separation.
Visual attention is an indispensable component of complex vision tasks. When looking at a complex scene, our ocular perception is confronted with a large amount of data that needs to be broken down for processing by o...
详细信息
ISBN:
(纸本)9781479915880
Visual attention is an indispensable component of complex vision tasks. When looking at a complex scene, our ocular perception is confronted with a large amount of data that needs to be broken down for processing by our psychovisual system. Selective visual attention provides a mechanism for serializing the visual data, allowing for sequential processing of the content of the scene. A Bottom-Up computational model is described that simulates the psycho-visual model of saliency based on features of intensity and color. the method gives sequential priorities to objects which other computational models cannot account for. the results demonstrate a fast execution time, full resolution maps and high detection accuracy. the model is applicable on both natural and artificial images.
A digital ecosystem contains many different services, including apps, physical objects, and a digital platform that provides these services to everyone. this complex structure is often hard to understand for people no...
详细信息
In this work we propose a new formulation for hyperspectral denoising based on the Blind Compressed Sensing (BCS) framework. BCS learns the sparsifying basis during signal recovery combining the advantages of standard...
详细信息
ISBN:
(纸本)9781467385640
In this work we propose a new formulation for hyperspectral denoising based on the Blind Compressed Sensing (BCS) framework. BCS learns the sparsifying basis during signal recovery combining the advantages of standard sparse recovery with dictionary learning. We show that our proposed formulation yields better results than a state-of-the-art technique hyperspectral denoising both in terms of PSNR (more than 1dB improvement) and visual quality.
this paper is aimed at exploring the potential of using discriminatory primitives containing words for the task of detecting skilled forgeries. We consider handwritten Devanagri documents for this work. We have obtain...
详细信息
ISBN:
(纸本)9781479915880
this paper is aimed at exploring the potential of using discriminatory primitives containing words for the task of detecting skilled forgeries. We consider handwritten Devanagri documents for this work. We have obtained experimental handwriting data from subjects who have contributed handwriting samples in their natural handwriting. Other authors are asked to imitate the writing style of the subjects to produce a skilled forgery sample. Most of the literature dealing with writer recognition focus on signatures and very few reports have addressed the problem of detecting forgeries for handwritten indian scripts. We also use multiple words based classification for the targeted task of forgery detection. Our experiments show encouraging results.
暂无评论