scholarly journals CNN Feature-Based Image Copy Detection with Contextual Hash Embedding

Mathematics ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. 1172
Author(s):  
Zhili Zhou ◽  
Meimin Wang ◽  
Yi Cao ◽  
Yuecheng Su
Keyword(s):  
Detection Method ◽  
Superior Performance ◽  
Detection Methods ◽  
Copy Detection ◽  
Visual Words ◽  
The Past ◽  
Index File ◽  
Image Copy Detection ◽  
Feature Based ◽  
Deep Learning Features

As one of the important techniques for protecting the copyrights of digital images, content-based image copy detection has attracted a lot of attention in the past few decades. The traditional content-based copy detection methods usually extract local hand-crafted features and then quantize these features to visual words by the bag-of-visual-words (BOW) model to build an inverted index file for rapid image matching. Recently, deep learning features, such as the features derived from convolutional neural networks (CNN), have been proven to outperform the hand-crafted features in many applications of computer vision. However, it is not feasible to directly apply the existing global CNN features for copy detection, since they are usually sensitive to partial content-discarded attacks, such as copping and occlusion. Thus, we propose a local CNN feature-based image copy detection method with contextual hash embedding. We first extract the local CNN features from images and then quantize them to visual words to construct an index file. Then, as the BOW quantization process decreases the discriminability of these features to some extent, a contextual hash sequence is captured from a relatively large region surrounding each CNN feature and then is embedded into the index file to improve the feature’s discriminability. Extensive experimental results demonstrate that the proposed method achieves a superior performance compared to the related works in the copy detection task.

scholarly journals A Multi-Floor Indoor Pedestrian Localization Method Using Landmarks Detection for Different Holding Styles

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Khanh Nguyen-Huu ◽  
Seon-Woo Lee
Keyword(s):  
Detection Method ◽  
Dead Reckoning ◽  
Superior Performance ◽  
Detection Methods ◽  
Portable Devices ◽  
Indoor Environments ◽  
Fusion Method ◽  
Localization Method ◽  
Pedestrian Dead Reckoning ◽  
Over Time

The pedestrian dead reckoning (PDR) technique is widely used due to its ease of implementation on portable devices such as smartphones. However, the position error that accumulates over time is the main drawback of this technology. In this paper, we propose a fusion method combining a PDR technique and the landmark recognition methods for multi-floor indoor environments using a smartphone in different holding styles. The proposed method attempts to calibrate the position of a pedestrian by detecting whether the pedestrian passes by specific locations called landmarks. Three kinds of landmarks are defined, which are the WiFi, the turning, and the stairs landmarks, and the detection methods for each landmark are proposed. Besides, an adaptive floor detection method using a barometer and a WiFi fingerprinting technique is suggested for tracking a pedestrian in a multi-floor building. The developed system can track the pedestrian holding a smartphone in four styles. The results of the experiment conducted by three subjects changing the holding style in a three-floor building show the superior performance of the proposed method. It reduces the error rate of positioning results to less than 57.51% compared with the improved PDR alone system.

scholarly journals Cloud detection for MIPAS using singular vector decomposition

2009 ◽  
Vol 2 (2) ◽  
pp. 1185-1219
Author(s):  
J. Hurley ◽  
A. Dudhia ◽  
R. G. Grainger
Keyword(s):  
Climate Models ◽  
Singular Vector ◽  
Detection Method ◽  
Michelson Interferometer ◽  
Detection Methods ◽  
Cloud Detection ◽  
Radiative Balance ◽  
The Past ◽  
Vector Decomposition ◽  
Atmospheric Sounding

Abstract. Clouds are increasingly recognised for their influence on the radiative balance of the Earth and the implications that they have on possible climate change, as well as in air pollution and acid-rain production. However, clouds remain a major source of uncertainty in climate models. Satellite-borne high-resolution limb sounders, such as the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) onboard ENVISAT, provide information on clouds, especially optically thin clouds, which have been difficult to observe in the past. The aim of this work is to develop, implement and test a reliable cloud detection method for infrared spectra measured by MIPAS. Current MIPAS cloud detection methods used operationally have been developed to detect thick cloud filling more than 30% of the measurement field-of-view (FOV). In order to resolve thin clouds, a new detection method using Singular Vector Decomposition (SVD) is formulated and tested. A rigorous comparison of the current operational and newly-developed detection methods for MIPAS is carried out – and the new SVD detection method has been proven to be much more reliable than the current operational method, and very sensitive even to thin clouds only marginally filling the MIPAS FOV.

scholarly journals An Unsupervised Approach for Detecting Group Shilling Attacks in Recommender Systems Based on Topological Potential and Group Behaviour Features

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Hongyun Cai ◽  
Fuzhi Zhang
Keyword(s):  
Recommender Systems ◽  
Detection Method ◽  
Potential Method ◽  
Detection Methods ◽  
Clustering Method ◽  
Group Behaviour ◽  
The Past ◽  
Group Members ◽  
Unsupervised Approach ◽  
Individual Features

To protect recommender systems against shilling attacks, a variety of detection methods have been proposed over the past decade. However, these methods focus mainly on individual features and rarely consider the lockstep behaviours among attack users, which suffer from low precision in detecting group shilling attacks. In this work, we propose a three-stage detection method based on strong lockstep behaviours among group members and group behaviour features for detecting group shilling attacks. First, we construct a weighted user relationship graph by combining direct and indirect collusive degrees between users. Second, we find all dense subgraphs in the user relationship graph to generate a set of suspicious groups by introducing a topological potential method. Finally, we use a clustering method to detect shilling groups by extracting group behaviour features. Extensive experiments on the Netflix and sampled Amazon review datasets show that the proposed approach is effective for detecting group shilling attacks in recommender systems, and the F1-measure on two datasets can reach over 99 percent and 76 percent, respectively.

scholarly journals A Survey Of Sign Based Image Copy Detection Methods

2014 ◽  
Vol 16 (3) ◽  
pp. 73-77
Author(s):  
Ms. Payal R. Shete ◽  
◽  
Mrs. Girija G. Chiddarwar
Keyword(s):  
Detection Methods ◽  
Copy Detection ◽  
Image Copy Detection

scholarly journals Cloud detection for MIPAS using singular vector decomposition

2009 ◽  
Vol 2 (2) ◽  
pp. 533-547 ◽  
Author(s):  
J. Hurley ◽  
A. Dudhia ◽  
R. G. Grainger
Keyword(s):  
Singular Vector ◽  
Detection Method ◽  
Michelson Interferometer ◽  
High Spectral Resolution ◽  
Detection Methods ◽  
Cloud Detection ◽  
The Past ◽  
Vector Decomposition ◽  
Atmospheric Sounding ◽  
Thin Cloud

Abstract. Satellite-borne high-spectral-resolution limb sounders, such as the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) onboard ENVISAT, provide information on clouds, especially optically thin clouds, which have been difficult to observe in the past. The aim of this work is to develop, implement and test a reliable cloud detection method for infrared spectra measured by MIPAS. Current MIPAS cloud detection methods used operationally have been developed to detect cloud effective filling more than 30% of the measurement field-of-view (FOV), under geometric and optical considerations – and hence are limited to detecting fairly thick cloud, or large physical extents of thin cloud. In order to resolve thin clouds, a new detection method using Singular Vector Decomposition (SVD) is formulated and tested. This new SVD detection method has been applied to a year's worth of MIPAS data, and qualitatively appears to be more sensitive to thin cloud than the current operational method.

scholarly journals Content-Based Image Copy Detection Using Convolutional Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2029
Author(s):  
Xiaolong Liu ◽  
Jinchao Liang ◽  
Zi-Yi Wang ◽  
Yi-Te Tsai ◽  
Chia-Chen Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Digital Images ◽  
Rapid Development ◽  
Network Technology ◽  
Copy Detection ◽  
Detection Scheme ◽  
The Past ◽  
Image Copy Detection ◽  
Feature Values

With the rapid development of network technology, concerns pertaining to the enhancement of security and protection against violations of digital images have become critical over the past decade. In this paper, an image copy detection scheme based on the Inception convolutional neural network (CNN) model in deep learning is proposed. The image dataset is transferred by a number of image processing manipulations and the feature values in images are automatically extracted for learning and detecting the suspected unauthorized digital images. The experimental results show that the proposed scheme takes on an extraordinary role in the process of detecting duplicated images with rotation, scaling, and other content manipulations. Moreover, the mechanism of detecting duplicate images via a convolutional neural network model with different combinations of original images and manipulated images can improve the accuracy and efficiency of image copy detection compared with existing schemes.

Fast image copy detection approach based on local fingerprint defined visual words

2013 ◽  
Vol 93 (8) ◽  
pp. 2328-2338 ◽  
Author(s):  
Hefei Ling ◽  
Lingyu Yan ◽  
Fuhao Zou ◽  
Cong Liu ◽  
Hui Feng
Keyword(s):  
Copy Detection ◽  
Visual Words ◽  
Image Copy Detection ◽  
Detection Approach

Video Copy Detection Based on Fusion of Spatio-Temporal Features

2013 ◽  
Vol 347-350 ◽  
pp. 3653-3661
Author(s):  
Wei Bao ◽  
Li Xin Ji ◽  
Shi Lin Gao ◽  
Xing Li ◽  
Li Xiong Liu
Keyword(s):  
Detection Method ◽  
Temporal Behavior ◽  
Bag Of Visual Words ◽  
Video Copy Detection ◽  
Copy Detection ◽  
Visual Words ◽  
Temporal Features ◽  
Surf Features ◽  
Spatio Temporal ◽  
Frequency Vectors

A video copy detection method based on fusion of spatio-temporal features is proposed in this paper. Firstly, trajectories are built and lens boundaries are detected by SURF features analyzing, then normalized histogram is used to describe spatio-temporal behavior of trajectories, the bag of visual words is constructed by trajectories behavior clustering, word frequency vectors and SURF features with behavior labels are extracted to express spatio-temporal content of lens, finally, duplicates are detected efficiently based on grade-match. The experimental results show the performance of this method is improved greatly compared with other similar methods.

Automated Detection of Pin Defects on Counterfeit Microelectronics

2018 ◽  
Author(s):  
Pallabi Ghosh ◽  
Domenic Forte ◽  
Damon L. Woodard ◽  
Rajat Subhra Chakraborty
Keyword(s):  
Integrated Circuits ◽  
Depth Map ◽  
Optical Microscope ◽  
Automated Detection ◽  
Detection Methods ◽  
Global Supply Chains ◽  
Subject Matter Experts ◽  
Security Breaches ◽  
The Past ◽  
Skilled Subject

Abstract Counterfeit electronics constitute a fast-growing threat to global supply chains as well as national security. With rapid globalization, the supply chain is growing more and more complex with components coming from a diverse set of suppliers. Counterfeiters are taking advantage of this complexity and replacing original parts with fake ones. Moreover, counterfeit integrated circuits (ICs) may contain circuit modifications that cause security breaches. Out of all types of counterfeit ICs, recycled and remarked ICs are the most common. Over the past few years, a plethora of counterfeit IC detection methods have been created; however, most of these methods are manual and require highly-skilled subject matter experts (SME). In this paper, an automated bent and corroded pin detection methodology using image processing is proposed to identify recycled ICs. Here, depth map of images acquired using an optical microscope are used to detect bent pins, and segmented side view pin images are used to detect corroded pins.

Sign in / Sign up

Export Citation Format

Share Document