Patch-based face recognition using a hierarchical multi-label matcher

Zhang, Lingfeng; Dou, Pengfei; Kakadiaris, Ioannis A.

doi:10.1016/j.imavis.2018.03.004

Cited by 5 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Video manipulation methods and devices that support privacy protection aim at preventing privacy infiltration when the images recorded on multiple VSSs are required to be sent to outside entity/entities that are beyond the jurisdiction of the VSSs. In cases where the video images are requested by, for example, law enforcement agencies, masking will be carried out with a receiver of control signals activated ( Figure 3) [33]. When motion signals are received, the VSS will compare the operational status of the cameras against the regulatory information and check if they match.…”

Section: Video Manipulation Methods and Devices That Support Privacy mentioning

confidence: 99%

A Mechanism of Masking Identification Information regarding Moving Objects Recorded on Visual Surveillance Systems by Differentially Implementing Access Permission

Park

Kim

2019

Electronics

View full text Add to dashboard Cite

Video surveillance systems (VSS), used as a measure of security strengthening as well as investigation, are provided principally in heavily crowded public places. They record images of moving objects and transmit them to the control center. Typically, the recorded images are stored after being encrypted, or masked using visual obfuscations on a concerned image(s) in the identification-enabling data contained in the visual information. The stored footage is recovered to its original state by authorized users. However, the recovery entails the restoration of all information in the visual data, possibly infiltrating the privacy of the object(s) other than the one(s) whose images are requested. In particular, Artificial Intelligence Healthcare that checks the health status of an object through images has the same problem and must protect the patient's identification information. This study proposes a masking mechanism wherein the infiltration of visual data privacy on videos is minimized by limiting the objects whose images are recovered with differential use of access permission granted to the requesting users.

show abstract

Section: Video Manipulation Methods and Devices That Support Privacy mentioning

confidence: 99%

A Mechanism of Masking Identification Information regarding Moving Objects Recorded on Visual Surveillance Systems by Differentially Implementing Access Permission

Park

Kim

2019

Electronics

View full text Add to dashboard Cite

show abstract

“…Typically, blurring is achieved by using the gaussian function to set the sigma parameter. Once the visual data are subject to blurring, they cannot be recovered to their original state [36][37][38]. This blurring technique blurs the edges, creating a clump of photos, and generally is applied to personal information about the subjects taken from the images to prevent the identification of targets by arbitrarily crushing them [39][40][41][42].…”

Section: Blurringmentioning

confidence: 99%

A Face Image Virtualization Mechanism for Privacy Intrusion Prevention in Healthcare Video Surveillance Systems

Kim

Park

2020

Symmetry

View full text Add to dashboard Cite

Closed-circuit television (CCTV) and video surveillance systems (VSSs) are becoming increasingly more common each year to help prevent incidents/accidents and ensure the security of public places and facilities. The increased presence of VSS is also increasing the number of per capita exposures to CCTV cameras. To help protect the privacy of the exposed objects, attention is being drawn to technologies that utilize intelligent video surveillance systems (IVSSs). IVSSs execute a wide range of surveillance duties—from simple identification of objects in the recorded video data, to understanding and identifying the behavioral patterns of objects and the situations at the incident/accident scenes, as well as the processing of video information to protect the privacy of the recorded objects against leakage. Besides, the recorded privacy information is encrypted and recorded using blockchain technology to prevent forgery of the image. The technology herein proposed (the “proposed mechanism”) is implemented to a VSS, where the mechanism converts the original visual information recorded on a VSS into a similarly constructed image information, so that the original information can be protected against leakage. The face area extracted from the image information is recorded in a separate database, allowing the creation of a restored image that is in perfect symmetry with the original image for images with virtualized face areas. Specifically, the main section of this study proposes an image modification mechanism that inserts a virtual face image that closely matches a predetermined similarity and uses a blockchain as the storage area.

show abstract

“…The UR2D system is evaluated on two types of face recognition scenarios: constrained environment and unconstrained environment. The datasets used for evaluation are the UHDB31 dataset [50,54] and the IJB-A dataset [35]. The same setting is followed as [55] in the UHDB31 dataset.…”

Section: Ur2d Evaluationmentioning

confidence: 99%

A Hierarchical Matcher using Local Classifier Chains

Zhang,

Kakadiaris

2018

Preprint

View full text Add to dashboard Cite

This paper focuses on improving the performance of current convolutional neural networks in visual recognition without changing the network architecture. A hierarchical matcher is proposed that builds chains of local binary neural networks after one global neural network over all the class labels, named as Local Classifier Chains based Convolutional Neural Network (LCC-CNN). The signature of each sample as two components: global component based on the global network; local component based on local binary networks. The local networks are built based on label pairs created by a similarity matrix and confusion matrix. During matching, each sample travels through one global network and a chain of local networks to obtain its final matching to avoid error propagation. The proposed matcher has been evaluated with image recognition, character recognition and face recognition datasets. The experimental results indicate that the proposed matcher achieves better performance when compared with methods using only a global deep network. Compared with the UR2D system, the accuracy is improved significantly by 1% and 0.17% on the UHDB31 dataset and the IJB-A dataset, respectively.

show abstract

Patch-based face recognition using a hierarchical multi-label matcher

Cited by 5 publications

References 58 publications

A Mechanism of Masking Identification Information regarding Moving Objects Recorded on Visual Surveillance Systems by Differentially Implementing Access Permission

A Mechanism of Masking Identification Information regarding Moving Objects Recorded on Visual Surveillance Systems by Differentially Implementing Access Permission

A Face Image Virtualization Mechanism for Privacy Intrusion Prevention in Healthcare Video Surveillance Systems

A Hierarchical Matcher using Local Classifier Chains

Contact Info

Product

Resources

About