2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)最新文献_第10页

A robust faint line detection and enhancement algorithm for mural images 一种鲁棒的壁画图像微弱线检测与增强算法

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776175

Mrinmoy Ghorai, B. Chanda

引用次数: 3

Improving video summarization based on user preferences 改进基于用户偏好的视频摘要

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776187

R. Kannan, G. Ghinea, Sridhar Swaminathan, Suresh Kannaiyan

引用次数: 6

Spatio-temporal feature based VLAD for efficient video retrieval 基于时空特征的VLAD高效视频检索

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776268

M. K. Reddy, Sahil Arora, R. Venkatesh Babu

引用次数: 6

Improvised eigenvector selection for spectral Clustering in image segmentation 基于特征向量选择的光谱聚类图像分割

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776233

Aditya Prakash, S. Balasubramanian, R. R. Sarma

引用次数: 1

Salient object detection in SfM point cloud SfM点云中的显著目标检测

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776194

Divyansh Agarwal, N. Soni, A. Namboodiri

引用次数: 0

Pan-sharpening based on Non-subsampled Contourlet Transform detail extraction 基于非下采样Contourlet变换细节提取的泛锐化

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776258

Kishor P. Upla, P. Gajjar, M. Joshi

{"title":"Pan-sharpening based on Non-subsampled Contourlet Transform detail extraction","authors":"Kishor P. Upla, P. Gajjar, M. Joshi","doi":"10.1109/NCVPRIPG.2013.6776258","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776258","url":null,"abstract":"In this paper, we propose a new pan-sharpening method using Non-subsampled Contourlet Transform. The panchromatic (Pan) and multi-spectral (MS) images provided by many satellites have high spatial and high spectral resolutions, respectively. The pan-sharpened image which has high spatial and spectral resolutions is obtained by using these images. Since the NSCT is shift invariant and it has better directional decomposition capability compared to contourlet transform, we use it to extract high frequency information from the available Pan image. First, two level NSCT decomposition is performed on the Pan image which has high spatial resolution. The required high frequency details are obtained by using the coarser subband available after the two level NSCT decomposition of the Pan image. The coarser sub-band is subtracted from the original Pan image to obtain these details. These extracted details are then added to MS image such that the original spectral signature is preserved in the final fused image. The experiments have been conducted on images captured from different satellite sensors such as IKonos-2, Worlview-2 and Quickbird. The traditional quantitative measures along with quality with no reference (QNR) index are evaluated to check the potential of the proposed method. The proposed approach performs better compared to the recently proposed state of the art methods such as additive wavelet luminance proportional (AWLP) method and context based decision (CBD) method.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

A learning based approach for dense stereo matching with IGMRF prior 基于学习的IGMRF先验密集立体匹配方法

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776264

S. Nahar, M. Joshi

{"title":"A learning based approach for dense stereo matching with IGMRF prior","authors":"S. Nahar, M. Joshi","doi":"10.1109/NCVPRIPG.2013.6776264","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776264","url":null,"abstract":"In this paper, we propose a learning based approach for solving the problem of dense stereo matching problem using edge preserving regularization prior. Given the test stereo pair and a training database consisting of disparity maps estimated using multiple views stereo images and their corresponding ground truths, we obtain the disparity map for the test set. We first obtain an initial disparity estimate by learning the disparities from the available database. A new learning based approach is proposed for obtaining the initial estimate that uses the estimated and the true disparities. Since the disparity estimation is an ill posed problem, we obtain the final disparity map using a regularization framework. The prior model for the disparity map is chosen as an Inhomogeneous Gaussian Markov Random Field (IGMRF). Assuming that the spatial variations among the disparity values captured in an initial estimate correspond to the variations in true disparities, we obtain the IGMRF parameters at every pixel location using the initial estimate. A graph cuts based method is used to optimize the energy function in order to obtain the global minimum. Experimental results on the standard dataset demonstrate the effectiveness of the proposed approach.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127834521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Enhancement of camera captured text images with specular reflection 通过镜面反射增强相机捕获的文本图像

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776189

A. Visvanathan, T. Chattopadhyay, U. Bhattacharya

{"title":"Enhancement of camera captured text images with specular reflection","authors":"A. Visvanathan, T. Chattopadhyay, U. Bhattacharya","doi":"10.1109/NCVPRIPG.2013.6776189","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776189","url":null,"abstract":"Specular reflection of light degrades the quality of scene images. Whenever specular reflection affects the text portion of such an image, its readability is reduced significantly. Consequently, it becomes difficult for an OCR software to detect and recognize similar texts. In the present work, we propose a novel but simple technique to enhance the region of the image with specular reflection. The pixels with specular reflection were identified in YUV color plane. In the next step, it enhances the region by interpolating possible pixel values in YUV space. The proposed method has been compared against a few existing general purpose image enhancement techniques which include (i) histogram equalization, (ii) gamma correction and (iii) Laplacian filter based enhancement method. The proposed approach has been tested on some images from ICDAR 2003 Robust Reading Competition image database. We computed a Mean Opinion Score based measure to show that the proposed method outperforms the existing enhancement techniques for enhancement of readability of texts in images affected by specular reflection.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116848309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Multi-resolution image fusion using multistage guided filter 基于多级引导滤波器的多分辨率图像融合

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776257

Sharad Joshi, Kishor P. Upla, M. Joshi

{"title":"Multi-resolution image fusion using multistage guided filter","authors":"Sharad Joshi, Kishor P. Upla, M. Joshi","doi":"10.1109/NCVPRIPG.2013.6776257","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776257","url":null,"abstract":"In this paper, we propose a multi-resolution image fusion approach based on multistage guided filter (MGF). Given the high spatial resolution panchromatic (Pan) and high spectral resolution multi-spectral (MS) images, the multi-resolution image fusion algorithm obtains a single fused image having both the high spectral and the high spatial resolutions. Here, we extract the missing high frequency details of MS image by using multistage guided filter. The detail extraction process exploits the relationship between the Pan and MS images by utilizing one of them as a guidance image and extracting details from the other. This way the spatial distortion of MS image is reduced by consistently combining the details obtained using both types of images. The final fused image is obtained by adding the extracted high frequency details to corresponding MS image. The results of the proposed algorithm are compared with the commonly used traditional methods as well as with a recently proposed method using Quickbird, Ikonos-2 and Worldview-2 satellite images. The quantitative assessment is evaluated using the conventional measures as well as using a relatively new index i.e., quality with no reference (QNR) which does not require a reference image. The results and measures clearly show that there is significant improvement in the quality of the fused image using the proposed approach.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129178476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Estimation of the orientation and distance of a mirror from Kinect depth data 根据Kinect深度数据估计镜子的方向和距离

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) Pub Date : 2013-12-01 DOI: 10.1109/NCVPRIPG.2013.6776248

Tanwi Mallick, P. Das, A. Majumdar

引用次数: 3