检索结果-内蒙古大学图书馆

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Srimanta Mandal Kuldeep Purohit A. N. Rajagopalan DA-IICT Gandhinagar Gujarat IIT Madras Chennai Tamil Nadu

ISBN: (纸本)9781450366151

In practice, images can contain different amounts of noise for different color channels, which is not acknowledged by existing super-resolution approaches. In this paper, we propose to super-resolve noisy color images by considering the color channels jointly. Noise statistics are blindly estimated from the input low-resolution image and are used to assign different weights to different color channels in the data cost. Implicit low-rank structure of visual data is enforced via nuclear norm minimization in association with adaptive weights, which is added as a regularization term to the cost. Additionally, multi-scale details of the image are added to the model through another regularization term that involves projection onto PCA basis, which is constructed using similar patches extracted across different scales of the input image. The results demonstrate the super-resolving capability of the approach in real scenarios.

关键词： Noise

来源：评论

学校读者我要写书评

暂无评论

A Fast Method for Very Low Bit-Rate Coding of Hyperspectral images 2018

A Fast Method for Very Low Bit-Rate Coding of Hyperspectral ...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Saurabh Kumar Subhasis Chaudhuri Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9781450366151

In this work, we propose a computationally efficient compressive sensing based approach for very low bit rate lossy coding of hyperspectral (HS) image data by exploiting the redundancy inherent in this imaging modality. We divide the HS datacube into subsets of adjacent bands, each of which is encoded into a coded snapshot using a random code matrix. These coded snapshot images are encoded using the wavelet-based SPIHT compression technique. The decompression from the coded snapshots at the receiver is done using the orthogonal matching pursuit with the help of an overcomplete dictionary learned on a general purpose training dataset. We provide ample experimental results and performance comparisons to substantiate the usefulness of the proposed method. In the proposed technique the encoder is free from any decoder and it offers a significant saving in computation and yet yields a much higher compression quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEDNet: Deep Network for Single image Haze Removal 2018

LEDNet: Deep Network for Single Image Haze Removal

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Akshay Dudhane Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar India Learning Affect and Semantic Image Analysis Group Indian Institute of Technology Ropar India

ISBN: (纸本)9781450366151

Haze during the bad weather, degrades the visibility of the scene drastically. Degradation of scene visibility varies with respect to the transmission coefficient/map (Tc) of the scene. Estimation of accurate Tc is key step to reconstruct the haze free scene. Previously, local as well as global priors were proposed to estimate the Tc. We, on the other hand, propose integration of local and global approaches to learn both point level and object level Tc. The proposed local encoder decoder network (LEDNet) estimates the scene transmission map in two stages. During first stage, network estimates the point level Tc using parallel convolutional filters and spatial invariance filtering. The second stage comprises of a two level encoder-decoder architecture which anticipates the object level Tc. We also propose, local air-light estimation (LAE) algorithm, which is able to obtain the air-light component of the outdoor scene. Combination of LEDNet and LAE improves the accuracy of haze model to recover the scene radiance. Structural similarity index, mean square error and peak signal to noise ratio are used to evaluate the performance of the proposed approach for single image haze removal. Experiments on benchmark datasets show that LEDNet outperforms the existing state-of-the-art methods for single image haze removal.

关键词： Haze removal transmission map CNN

来源：评论

学校读者我要写书评

暂无评论

SegFast: A Faster SqueezeNet based Semantic image Segmentation Technique using Depth-wise Separable Convolutions 18

SegFast: A Faster SqueezeNet based Semantic Image Segmentati...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Anisha Pal Shourya Jaiswal Swarnendu Ghosh Nibaran Das Mita Nasipuri Dept. of Information and Communication Technology Manipal Institute of Technology Manipal Karnataka Dept. of Electronics and Communication Engineering Manipal Institute of Technology Manipal Karnataka Dept. of Computer Science and Engineering Jadavpur University Kolkata West Bengal

ISBN: (纸本)9781450366151

Recent trends in image segmentation algorithms have shown various large scale networks with impressive performance for natural scene images. However most of the networks come with costly overheads such has large memory requirements or dependence on huge number of parallel processing units. In most cases costly graphics processing units or GPUs are used to boost computational capability. However for creating products in the real world we need to consider speed, performance as well as cost of deployment. We propose a novel "spark" module which is a combination of the "fire" module of SqueezeNet and depth-wise separable convolutions. Along with this modified SqueezeNet as an encoder we also propose the use of depth-wise separable transposed convolution for a decoder. The resultant encoder-decoder network has approximately 49 times lesser number of parameters than SegNet and almost 223 times lesser number of parameters than fully convolutional networks(FCN). Even in a CPU the network completes a forward pass for a single sample in approximately 0.39 seconds which is almost 5.1 times faster as compared to SegNet and almost 8.7 times faster compared to FCN.

关键词： Deep Learning

来源：评论

学校读者我要写书评

暂无评论

VidSeg-GAN: Generative Adversarial Network for Video Object Segmentation Tasks 2018

VidSeg-GAN: Generative Adversarial Network for Video Object ...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Saptakatha Adak Sukhendu Das Indian Institute of Technology Madras Chennai India

ISBN: (纸本)9781450366151

Video object segmentation aims to segment objects in a video sequence, given some user annotation which indicates the object of interest. Although Convolutional Neural Networks (CNNs) have been used in the recent past for the purpose of foreground segmentation in videos, adversarial training methods have not been used effectively to solve this problem, in spite of its extensive use for solving many other problems in computer vision. Earlier, flow features and motion trajectories have been extensively used to capture the temporal consistency between subsequent frames to segment moving objects in videos. However, we show that our proposed framework of processing the video frames independently using a deep generative adversarial network (GAN), is able to maintain the temporal coherency across frames without the use of any explicit trajectory based information, to provide superior results. Our main contribution lies in introducing a GAN based framework along with the incorporation of an Intersection-over-Union score based novel cost function for training the model, to solve the problem of foreground object segmentation in videos. The proposed method, when evaluated on popular real-world video segmentation datasets viz. DAVIS, SegTrack-v2 and YouTube-Objects, exhibits substantial performance gain over the recent state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perfectly Secure Shamir's Secret Sharing Scheme for Privacy Preserving image processing Over Cloud 2018

Perfectly Secure Shamir's Secret Sharing Scheme for Privacy ...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Debanjan Sadhya Akshay Agarwal Balasubramanian Raman Indian Institute of Technology Roorkee Roorkee India Manipal Institute of Technology Manipal India

ISBN: (纸本)9781450366151

Cloud computing is a highly prospective paradigm in which computational resources from third parties are used for processing outsourced data. Nonetheless, the distributed architecture of this concept poses many security and privacy threats for the data owners. Shamir's secret sharing is an effective technique for distributing and processing secret images over the encrypted domain. However, it has got some critical limitations primarily due to the presence of correlated information between the image pixels. Our study addresses this problem by proposing a perfectly secure Shamir's secret sharing scheme for images. Our work builds upon the formal notion of perfect secrecy for encoding the Shamir's shares in a particular manner such that they (i.e. encoded shares) do not reveal any additional information about the original image. Importantly, we have provided both theoretical and empirical validation of our proposed approach. We have also performed several image filtering operations on the stored shares and found the resulting PSNR and NCC values to be similar in the plain and encrypted domains. Hence our work provides a privacy-preserving and secure framework for working with images over a cloud-based architecture.

关键词： Perfect Secrecy Encrypted Domain Cloud Computing Shamir's Secret Sharing

来源：评论

学校读者我要写书评

暂无评论

CACAI: Comparative analysis of crypto apps in India

引用

AIP conference proceedings 2023年第1期2916卷

作者： Rahul Johari Anuj Talwar Suhas Harbola Jyotsna Yadav Himesh Nayak Deo Prakash Vidyarthi SWINGER: Security Wireless IoT Network Group of Engineering and Research University School of Information Communication and Technology (USICT) Guru Gobind Singh Indraprastha University Sector-16C Dwarka Delhi India Computer vision and Image processing lab University School of Information Communication and Technology (USICT) Guru Gobind Singh Indraprastha University Sector-16C Dwarka Delhi India School of Computer and Systems Sciences Parallel and Distributed Systems Lab JNU Delhi India

Crypto-currency is a decentralized digital currency which can be used as a medium of exchange. As it does not have any central authority, it is unregulated and a volatile asset. Globally the crypto market is worth a few trillion dollars. The indian crypto market suffered a lot due to a ban imposed by the Reserve Bank of India (RBI), an indian regulatory agency, which lasted for around two years. Even after the ban and cautions issued by the RBI, the crypto market in India touched a billion dollar mark in no time. Currently, the crypto market has more than 10 million indian investors which is growing fast as the number of exchange apps in the indian market increase with the ease of trading in crypto. In the current research work Comparative Analysis of Crypto App in India (CACAI) has been performed and results exceed the expectations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BatchOut: Batch-level feature augmentation to improve robustness to adversarial examples 18

BatchOut: Batch-level feature augmentation to improve robust...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Akshayvarun Subramanya Konda Reddy Mopuri R. Venkatesh Babu Video Analytics Lab Indian Institute of Science Bangalore India

ISBN: (纸本)9781450366151

Machine Learning models are known to be susceptible to small but structured changes to their inputs that can result in wrong inferences. It has been shown that such samples, called adversarial samples, can be created rather easily for standard neural network architectures. These adversarial samples pose a serious threat for deploying state-of-the-art deep neural network models in the real world. We propose a feature augmentation technique called BatchOut to learn robust models towards such examples. The proposed approach is a generic feature augmentation technique that is not specific to any adversary and handles multiple attacks. We evaluate our algorithm on benchmark datasets and architectures to show that models trained using our method are less susceptible to adversaries created using multiple methods.

关键词： Adversarial examples

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Neural Network for Classification in Esophageal Cancer Histopathological images (CNN plus LSTM) 10

An Efficient Deep Neural Network for Classification in Esoph...

引用

10th International conference on graphics and image processing (ICGIP)

作者： Ge, Jing Ying, Xie Wang, Di Qilu Univ Technol Shandong Acad Sci Key Lab Med Artificial Intelligence Shandong Comp Sci CtrNatl Supercomp Ctr Jinan Jinan 250014 Shandong Peoples R China

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

Esophageal cancer is one of the leading causes of mortality worldwide. Early diagnostics are imperative of improving the chances of correct treatment and survival. Pathology examination requires time consuming scanning while often leads to a disagreement among pathologists. The computer-aided diagnosis systems are critical to improve the diagnostic efficiency and reduce the subjectivity and error of human. In this paper, a deep learning-based approach is proposed to classify the H&E stained histopathological images of esophageal cancer. The histopathological images are firstly normalized to correct the color variations during slide preparation. Then one image patch is cut into five pieces and gets five corresponded features via convolutional neural networks (CNNs). Subsequently, the five features of one image patch are fed into the Long Short-Term Memory (LSTM) model for further feature extraction and integrated as one for the last classification. The experiment results have demonstrated the proposed approach is effective to classify the esophageal histopathological images with the accuracy of 84.5% which outperforming 10 percent than GoogLeNet.

关键词： Histopathological image classification convolutional neural network long short-term memory esophageal cancer

来源：评论

学校读者我要写书评

暂无评论

Temporal Modeling of EEG Signals using Block Sparse Variational Bayes Framework 18

Temporal Modeling of EEG Signals using Block Sparse Variatio...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Shruti Sharma Santanu Chaudhury Jayadeva Jayadeva Indian Institute of Technology Delhi

ISBN: (纸本)9781450366151

Compressed Sensing (CS) has emerged as an alternate method to acquire high dimensional signals effectively by exploiting the sparsity assumption. However, owing to non-sparse and non-stationary nature, it is extremely difficult to process Electroencephalograph (EEG) signals using CS paradigm. The success of Bayesian algorithms in recovering non-sparse signals has triggered the research in CS based models for neurophysiological signal processing. In this paper, we address the problem of Temporal Modeling of EEG Signals using Block Sparse Variational Bayes (SVB) Framework. Temporal correlation of EEG signals is modeled blockwise using normal variance scale mixtures parameterized via some random and deterministic parameters. Variational inference is exploited to infer the random parameters and Expectation Maximization (EM) is used to obtain the estimate of deterministic parameters. To validate the framework, we present experimental results for benchmark State Visual Evoked Potential (SSVEP) dataset with 40-target Brain-computer Interface (BCI) speller using two frequency recognition algorithms viz. Canonical Correlation Analysis (CCA) and L1-regularized Multiway CCA. Results show that the proposed temporal model is highly useful in processing SSVEP-EEG signals irrespective of the recognition algorithms used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：