Development of framework for detecting smoking scene in video clips

Ghuli, Poonam; Shashank, B N; Rao, Athri G

doi:10.11591/ijeecs.v13.i1.pp22-26

Cited by 4 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We notice that the Resnet 18 neural network performs best for the face biometric system and the left and right palm print respectively. The resNet is successfully used in many fields and these results coincided with the literature [33], [34]. Apparently, ResNet 18 neural networks give the best accuracy rates for all three modalities.…”

Section: Training Cnns For Separate Modalitiessupporting

confidence: 80%

A deep learning-based multimodal biometric system using score fusion

Medjahed

Rahmoun

Charrier

et al. 2022

IJ-AI

View full text Add to dashboard Cite

Recent trends in artificial intelligence tools-based biometrics have overwhelming attention to security matters. The hybrid approaches are motivated by the fact that they combine mutual strengths and they overcome their limitations. Such approaches are being applied to the fields of biomedical engineering. A biometric system uses behavioural or physiological characteristics to identify an individual. The fusion of two or more of these biometric unique characteristics contributes to improving the security and overcomes the drawbacks of unimodal biometric-based security systems. This work proposes efficent multimodal biometric systems based on matching score concatenation fusion of face, left and right palm prints. Multimodal biometric identification systems using convolutional neural networks (CNN) and k-nearest neighbors (KNN) are proposed and trained to recognize and identify individuals using multi-modal biometrics scores. Some popular biometrics benchmarks such as FEI face dataset and IITD palm print database are used as raw data to train the biometric systems to design a strong and secure verification/identification system. Experiments are performed on noisy datasets to evaluate the performance of the proposed model in extreme scenarios. Computer simulation results show that the CNN and KNN multi-modal biometric system outperforms most of the most popular up to date biometric verification techniques.

show abstract

Section: Training Cnns For Separate Modalitiessupporting

confidence: 80%

A deep learning-based multimodal biometric system using score fusion

Medjahed

Rahmoun

Charrier

et al. 2022

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Therefore, isolating irrelevant information and extracting important information are essential [14], [15]. In addition, compared with manual detection, the advantage of using artificial intelligence (AI) to identify microexpressions is that as long as the camera objectively captures the identified object, the computer will have obtained the relevant data for processing [16]. In other words, by installing cameras, a certain level of recognition can be achieved [16], [17].…”

Section: Methodsmentioning

confidence: 99%

“…In addition, compared with manual detection, the advantage of using artificial intelligence (AI) to identify microexpressions is that as long as the camera objectively captures the identified object, the computer will have obtained the relevant data for processing [16]. In other words, by installing cameras, a certain level of recognition can be achieved [16], [17]. In this study, we used FaceReader, professional facial expression analysis software, for microexpression recognition.…”

Section: Methodsmentioning

confidence: 99%

Microexpression recognition robot

Wu¹,

Liu²,

Tsao³

et al. 2023

IJRA

View full text Add to dashboard Cite

Following the development of big data, the use of microexpression technology has become increasingly popular. The application of microexpressions has expanded beyond medical treatment to include scientific case investigations. Because microexpressions are characterized by short duration and low intensity, training humans to recognize their yields poor performance results. Automatically recognizing microexpressions by using machine learning techniques can provide more effective results and save time and resources. In the real world, to avoid judicial punishment, people lie and conceal the truth for a variety of reasons. In this study, our primary objective was to develop a system for real-time microexpression recognition. We used FaceReader as the retrieval system and integrated the data with an application programming interface to provide recognition results as objective references in real-time. Using an experimental analysis, we also attempted to determine the optimal system configuration conditions. In conclusion, the use of artificial intelligence is expected to enhance the efficiency of investigations.

show abstract

“…Nowadays, television offers internet television or online television services, allowing users to enjoy television programs through the internet (Mulej et al, 2020). Comedy shows on television essentially showcase characters capable of communicating their thoughts through verbal and nonverbal deviations to elicit amusement and laughter from the viewers of the show (Poonam et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

The content analyst of humor on NET TV and TVRI Television Stations

Islanmmudin,

Sari

2023

Sylection.

View full text Add to dashboard Cite

The discourse of humor in interpersonal interactions involves a complex mechanism. The creation of utterances containing humor in communication is not a simple phenomenon; it encompasses intricate mechanisms occurring between the speaker and the interlocutor. In addition to emerging in social interactions, humor can also be encountered in both print and electronic media. Among the electronic media, television is the most widely accessed by the public.Currently, television offers internet television services, or online television, allowing its programs to be enjoyed by internet users. This research delves into the forms, techniques, and themes of humor content in variety show programs broadcasted by NET TV and TVRI. The aim of this research is to describe patterns and purposes for delivering humor on both television stations. The method employed in this study is qualitative-descriptive, and data collection utilizes the Krippendorff technique.The findings of this research indicate distinctions between government-owned and privately-owned television stations, particularly in program packaging. Government-owned television stations package their programs with the cultural backdrop of a specific ethnic group in Indonesia and highlight stories from that group. Examples include programs like "Gangsa Ngetrend" and "Ludruk Kirun CS," which showcase Javanese culture, and the program "Ga'de Ga'de," which features stories from South Sulawesi culture. Government-owned television stations also address education by packaging it in the format of stand-up comedy and humor. Conversely, private-owned television stations package their programs primarily for entertainment purposes.

show abstract

Development of framework for detecting smoking scene in video clips

Cited by 4 publications

References 11 publications

A deep learning-based multimodal biometric system using score fusion

A deep learning-based multimodal biometric system using score fusion

Microexpression recognition robot

The content analyst of humor on NET TV and TVRI Television Stations

Contact Info

Product

Resources

About