A Sketch Classifier Technique with Deep Learning Models Realized in an Embedded System

Tsai, Tsung‐Han; Chi, Po-Ting; Cheng, Kuo-Hsing

doi:10.1109/ddecs.2019.8724656

Cited by 6 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This accuracy is satisfactory with lightweight CNN architecture and fast response for authentication operation. The previous research by T.Tsai [45] who used Google Quick Draw dataset achieves is 85% accuracy.…”

Section: ) Second Stage: Authentication Keys Extractionmentioning

confidence: 92%

On-Air Hand-Drawn Doodles for IoT Devices Authentication During COVID-19

Elshenaway

Guirguis

2021

IEEE Access

View full text Add to dashboard Cite

In this paper, a new natural human interaction authentication method has been proposed for the Internet of Things (IoT) devices. In this method the user draws doodles on-air for authentication. On-air drawing, refers to virtually drawing free hand-drawn doodles passwords through hand gestures on the air without touching anything which is recommended during COVID-19. This work uses Google Quick Draw doodles dataset for password doodles. The proposed method is based on a usual video camera, two lightweight Convolutional Neural Networks (CNN) and Kalman filter. The first CNN for hand gestures classification to overcome dynamic hand gestures challenges on the air. The second CNN for authentication verification. Kalman filter is used to correct and smooth the drawn line path on the air. To accept the new authentication method, it must achieve two main goals security and usability. The evaluation of the usability was based on ISO 9241-11:2018 standards usability model. The results revealed that the accuracy of the proposed authentication method is 95% and, the efficiency is 94% and user satisfaction is accepted. The evaluation of the security was based on two threats related to IoT devices which are guessing and physical observation. The results showed that the password strength of the proposed authentication method is stronger than the traditional 4-digits PIN password. The proposed authentication method is also resistant to physical observation threats.

show abstract

Section: ) Second Stage: Authentication Keys Extractionmentioning

confidence: 92%

On-Air Hand-Drawn Doodles for IoT Devices Authentication During COVID-19

Elshenaway

Guirguis

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recently, with the rapid development of deep learning, the educational, experiential, and auxiliary situations in which various deep learning technologies are applied have increased [ 1 , 2 , 3 , 4 ]. In particular, in terms of edutainment, various recognition technologies based on deep learning are being developed to recognize interactions such as speech, gestures, eye and head tracking, and even physical objects.…”

Section: Introductionmentioning

confidence: 99%

Noise-Robust Multimodal Audio-Visual Speech Recognition System for Speech-Based Interaction Applications

Jeon

Kim

2022

Sensors

View full text Add to dashboard Cite

Speech is a commonly used interaction-recognition technique in edutainment-based systems and is a key technology for smooth educational learning and user–system interaction. However, its application to real environments is limited owing to the various noise disruptions in real environments. In this study, an audio and visual information-based multimode interaction system is proposed that enables virtual aquarium systems that use speech to interact to be robust to ambient noise. For audio-based speech recognition, a list of words recognized by a speech API is expressed as word vectors using a pretrained model. Meanwhile, vision-based speech recognition uses a composite end-to-end deep neural network. Subsequently, the vectors derived from the API and vision are classified after concatenation. The signal-to-noise ratio of the proposed system was determined based on data from four types of noise environments. Furthermore, it was tested for accuracy and efficiency against existing single-mode strategies for extracting visual features and audio speech recognition. Its average recognition rate was 91.42% when only speech was used, and improved by 6.7% to 98.12% when audio and visual information were combined. This method can be helpful in various real-world settings where speech recognition is regularly utilized, such as cafés, museums, music halls, and kiosks.

show abstract