scholarly journals Smart Security System Using Image Recognition

2021 ◽  
Vol 9 (VII) ◽  
pp. 1936-1939
Author(s):  
Arpita Prakash Hegde
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Good Accuracy ◽  
Family Members ◽  
Security System ◽  
Home Based ◽  
The Family

The Smart Security System using Image Recognition uses Deep Learning and Computer Vision approach.In real time it would help the home based security system to track the persons coming into the house and unlocking the door, hereby the system would be accessed by using the image recognition service in which the images are trained in different classes labeled with the names of the family members and not only them they can train the images of their relatives which provides the access to unlock their door. By using this model one can secure the home premises from the invaders and also capture the suspected people who are not authorized to move inside the house. By using “dlib one short learning”, all the faces for permission would be trained and the model is given to the security system where it can secure the premises with good accuracy through trained images.

Smart teaching mode based on particle swarm image recognition and human-computer interaction deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao
Keyword(s):  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Particle Swarm ◽  
Learning Technology ◽  
Search Performance ◽  
Swarm Optimization ◽  
Teaching Mode

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.

Real-time Drowsiness and Distraction Detection using Computer Vision and Deep Learning

2020 ◽  
Author(s):  
Phakawat Pattarapongsin ◽  
Bipul Neupane ◽  
Jirayus Vorawan ◽  
Harit Sutthikulsombat ◽  
Teerayut Horanont
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Real Time

scholarly journals Computer vision based obstacle detection and target tracking for autonomous vehicles

2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Target Tracking ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Obstacle Detection ◽  
Pid Algorithm ◽  
Deep Learning Neural Network

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

scholarly journals Human-Like Sketch Object Recognition via Analogical Learning

2019 ◽  
Vol 33 ◽  
pp. 1336-1343
Author(s):  
Kezhen Chen ◽  
Irina Rabkina ◽  
Matthew D. McLure ◽  
Kenneth D. Forbus
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Recognition ◽  
Image Recognition ◽  
Visual Representations ◽  
Learning Systems ◽  
Training Data ◽  
Adversarial Examples ◽  
Analogical Learning

Deep learning systems can perform well on some image recognition tasks. However, they have serious limitations, including requiring far more training data than humans do and being fooled by adversarial examples. By contrast, analogical learning over relational representations tends to be far more data-efficient, requiring only human-like amounts of training data. This paper introduces an approach that combines automatically constructed qualitative visual representations with analogical learning to tackle a hard computer vision problem, object recognition from sketches. Results from the MNIST dataset and a novel dataset, the Coloring Book Objects dataset, are provided. Comparison to existing approaches indicates that analogical generalization can be used to identify sketched objects from these datasets with several orders of magnitude fewer examples than deep learning systems require.

Fluorescent PCR Based Gene Dose Assessment for Detection of Deletion Mutations in the FIX Gene Among Carriers of Hemophilia B.

Blood ◽  
2009 ◽  
Vol 114 (22) ◽  
pp. 3486-3486
Author(s):  
Eunice Sindhuvi Edison ◽  
G. Sankari Devi ◽  
G. Jayandharan ◽  
Shaji R Velayudhan ◽  
Auro Viswabandya ◽  
...  
Keyword(s):  
Linkage Analysis ◽  
Real Time ◽  
Real Time Pcr ◽  
Gene Dosage ◽  
Family Members ◽  
Peak Height ◽  
Hemophilia B ◽  
Carrier Status ◽  
Fluorescent Pcr ◽  
The Family

Abstract Abstract 3486 Poster Board III-423 Haemophilia B (HB), an X linked inherited disorder is caused by heterogeneous mutations in the F9 gene. Approximately 3% of hemophilia B patients have major deletions in the F9 gene. Gross and small deletions in the F9 gene in HB affected males are easily detected by PCR but detecting the carrier state of females in the family is challenging due to the presence of the normal allele. Different methods like linkage analysis, real time PCR and MLPA have been used to assess the carrier status in this situation. Linkage analysis is limited by the availability of informative markers and adequate number of family members. Real time PCR involves standardisation and preparation of calibration curves for each run. Although MLPA is a better alternative, it can be time consuming and involves multiple steps. We have therefore developed a fluorescent PCR based gene dosage approach which is simple, rapid and cost-effective for determining the carrier status of females in families with deletions in the F9 gene. 200ng of DNA extracted by standard protocols was used for amplification with primers designed to amplify a 160bp product from exon h in the F9 gene. One of the primers was fluorescently labelled. Amplification was carried out using these primers for 20 cycles only and the amplified product was subjected to capillary electrophoresis on an ABI 310 genetic analyser. A 230 bp fragment in the albumin gene was used as the control. Analysis was done using Genescan and Genotyper software. The ratio between the peak heights of the exon h in the F9 and control genes in the patient samples were normalised to a normal control. Five families with deletional HB were analysed (in toto deletion-1; Ex g-h – 1; Ex g-poly A-1; Ex h-poly A-2). The ratios in the probands and the family members are presented in the table. Out of eight females analysed, 6 were carriers and 2 were normal. The mean ratio in the carriers was 0.49±0.08 and 0.75±0.05 in the normal. Deletions are not uncommon in HB and deletions involving the exon g and h constitute a major group. Among 212 families with HB assessed at our centre, we have identified large deletions in 8 families (3.7%). It is interesting to note that all except one of these deletional mutations involved exon h. This method confirmed the presence of these deletions in the males and helped us to identify the carrier status of the females in the family. Identification of carrier status of females with deletions in F9 gene by gene dosage Subject ID Peak height of Exh in F9 Peak height of albumin Normalised Ratio Interpretation HB5 284 442 0.59 Carrier HB6 305 489 0.57 Carrier HB22 188 372 0.47 Carrier HB63 85 165 0.48 Carrier HB129 247 295 0.78 Normal HB238 94 326 0.4 Carrier HB280 372 679 0.77 Normal HB384 202 670 0.4 Carrier Disclosures: No relevant conflicts of interest to declare.

scholarly journals Deep Learning-Based Computer Vision for Real-Time Intravenous Drip Infusion Monitoring

2020 ◽  
pp. 1-1
Author(s):  
Nicola Giaquinto ◽  
Marco Scarpetta ◽  
Maurizio Spadavecchia ◽  
Gregorio Andria
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Real Time ◽  
Drip Infusion ◽  
Intravenous Drip
Sign in / Sign up

Export Citation Format

Share Document