scholarly journals Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Sensors ◽  
2017 ◽  
Vol 17 (3) ◽  
pp. 605 ◽  
Author(s):  
Dat Nguyen ◽  
Hyung Hong ◽  
Ki Kim ◽  
Kang Park
Keyword(s):  
Visible Light ◽  
Recognition System ◽  
Body Images ◽  
Person Recognition ◽  
Thermal Cameras

scholarly journals An Acoustic-Based Smart Home System for People Suffering from Dementia

Technologies ◽  
2019 ◽  
Vol 7 (1) ◽  
pp. 29 ◽  
Author(s):  
Eleni Boumpa ◽  
Anargyros Gkogkidis ◽  
Ioanna Charalampou ◽  
Argyro Ntaliani ◽  
Athanasios Kakarountas ◽  
...  
Keyword(s):  
Smart Home ◽  
Aging In Place ◽  
Recognition System ◽  
Smart Devices ◽  
Home Support ◽  
Person Recognition ◽  
Dementia Syndrome ◽  
Neurological Research ◽  
Familiar Person

Aging-in-place can reduce the progress of dementia syndrome and improve the quality of life of the sufferers and their families. Taking into consideration the fact that numerous neurological research results suggest the use of sound as a stimulus for empowering the memory of the sufferer, an innovative information home support system for people suffering from dementia is proposed. The innovation of the proposed system is found in its application, that is to integrate a home system for assisting with person recognition via a sound-based memory aid service. Furthermore, the system addresses the needs of people suffering from dementia to recognize their familiars and have better interaction and collaboration, without the need for training. The system offers a ubiquitous recognition system, using smart devices like smart-phones or smart-wristbands. When a familiar person is detected in the house, then a sound is reproduced on the smart speakers, in order to stimulate the sufferer’s memory. The system identified all users and reproduced the appropriate sound in 100% of the cases. To the best of the authors’ knowledge, this is the first system of its kind for assisting person recognition via sound ever reported in the literature.

Anti-Alteration Technology for License Plate Recognition System

2011 ◽  
Vol 211-212 ◽  
pp. 156-160
Author(s):  
Xing Yang ◽  
Yong Shun Ling ◽  
Xiao Li Hao ◽  
Hua Yang ◽  
Peng Ma
Keyword(s):  
Visible Light ◽  
Near Infrared ◽  
Imaging System ◽  
Recognition System ◽  
Infrared Range ◽  
License Plate ◽  
Uniform Field ◽  
License Plate Recognition ◽  
Infrared Images ◽  
Field Imaging

In order to realize anti-alteration function for License Plate Recognition System (LPRS), a uniform-field imaging system is designed and a corresponding anti-alteration algorithm is proposed. First, reflection characteristics of license plate and typical alteration material are measured. As a result, the two characteristics in near-infrared range fluctuate moderately and the former is notably lower than the latter. Then the uniform-field imaging system for visible-light and near-infrared is designed to capture the difference above effectively. Finally, the anti-alteration algorithm, composed of license plate location, character matching segmentation and alteration recognition, is introduced. Experimental results have indicated that visible-light and near-infrared images can be acquired stably by the proposed system under the condition of natural illumination and there are discriminable gray differences between license plate and alteration material in near-infrared images; and that success rate and average executive time of the algorithm are 86.5% and 157ms respectively.

Devising a novel visible light based low-cost ultra-low-power gesture recognition system

2017 ◽  
Author(s):  
Tusher Chakraborty ◽  
Md. Nasim ◽  
Sakib Md. Bin Malek ◽  
Md. Taksir Hasan Majumder ◽  
Md. Samiul Saeef ◽  
...  
Keyword(s):  
Low Power ◽  
Visible Light ◽  
Gesture Recognition ◽  
Low Cost ◽  
Recognition System ◽  
Ultra Low Power

scholarly journals Handwritten Character Recognition Using Neural Network

2021 ◽  
pp. 203-207
Author(s):  
Monika ◽  
Monika Ingole ◽  
Khemutai Tighare
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Execution Time ◽  
Character Recognition ◽  
Recognition System ◽  
Handwritten Character Recognition ◽  
Person Recognition ◽  
Community Approach ◽  
Artificial Neural

In this paper, an enterprise is made to perceive manually written characters for English letters so as. The precept point of this mission is to plan a master framework for, "HCR(English) utilizing neural community". That could viably understand a particular individual-of-kind layout making use of the artificial neural community approach. The manually written man or woman acknowledgment trouble has grown to be the maximum famous trouble in ai. Handwritten man or woman acknowledgment has been a difficult space of exam, with the execution of gadgets getting to know we suggest a neural network-based methodology. The development is based totally on neural network, that is a subject of look at in artificial intelligence. Distinct strategies and methods are used to broaden a handwriting person recognition system. Acknowledgment, precision fee, execution, and execution time are massive versions on the way to be met through the technique being applied. The purpose is to illustrate the effectiveness of neural networks for handwriting character recognition.

Priming Production of People's Names

1995 ◽  
Vol 48 (3) ◽  
pp. 513-535 ◽  
Author(s):  
Tim Valentine ◽  
Viv Moore ◽  
Serge Brédart
Keyword(s):  
Word Recognition ◽  
Naming Latency ◽  
Recognition System ◽  
Read Aloud ◽  
Information Processing Model ◽  
Test Task ◽  
Person Recognition ◽  
Prime Task ◽  
Time Required ◽  
The Relationship

Surnames of celebrities that are English words (e.g. “Wood”, “Bush”, “Sleep”) were used to explore the relationship between production of common names and proper names that share the same phonology. No effect of priming of face naming latency was found from a prime task in which a written common name was presented and was read aloud, even when subjects were informed the words that they would read aloud were surnames. Production of common names to complete a sentence did not prime famous-face naming. However, the reaction time required to name a famous face by articulating the surname only was primed by seeing the written full name of the celebrity, whether the surname was read aloud or an occupation decision or a familiarity decision was made. No effect of priming was found if the test task did not require name production. The results are interpreted in terms of the information-processing model of face, name, and word recognition proposed by Valentine, Brédart, Lawson, and Ward (1991). It is concluded that the effect of repetition reflects greater accessibility of lexical output codes resulting from an increase in the weight on links from person identity nodes to the output lexicon. Access to the output lexicon is assumed to be mandatory from written input. Common names access the output lexicon from the word recognition system rather than the person recognition system and therefore do not prime face naming latency.

scholarly journals Visible-Light Camera Sensor-Based Presentation Attack Detection for Face Recognition by Combining Spatial and Temporal Information

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 410 ◽  
Author(s):  
Dat Nguyen ◽  
Tuyen Pham ◽  
Min Lee ◽  
Kang Park
Keyword(s):  
Neural Network ◽  
Visible Light ◽  
Spatial Information ◽  
Recognition System ◽  
Image Features ◽  
Attack Detection ◽  
Temporal Information ◽  
Public Datasets ◽  
Presentation Attack Detection ◽  
Camera Sensor

Face-based biometric recognition systems that can recognize human faces are widely employed in places such as airports, immigration offices, and companies, and applications such as mobile phones. However, the security of this recognition method can be compromised by attackers (unauthorized persons), who might bypass the recognition system using artificial facial images. In addition, most previous studies on face presentation attack detection have only utilized spatial information. To address this problem, we propose a visible-light camera sensor-based presentation attack detection that is based on both spatial and temporal information, using the deep features extracted by a stacked convolutional neural network (CNN)-recurrent neural network (RNN) along with handcrafted features. Through experiments using two public datasets, we demonstrate that the temporal information is sufficient for detecting attacks using face images. In addition, it is established that the handcrafted image features efficiently enhance the detection performance of deep features, and the proposed method outperforms previous methods.

Sign in / Sign up

Export Citation Format

Share Document