Human emotion recognition and behavioral analysis have become important research areas in Artificial Intelligence, Computer Vision, and Human-Computer Interaction. Recent advancements in facial landmark detection, machine learning, and deep learning have enabled real-time analysis of emotions, attention levels, fatigue, and user engagement through webcams and mobile cameras. This review paper examines existing approaches used for facial emotion recognition, gaze tracking, blink detection, head pose estimation, and behavioral analytics. Various methodologies including Media Pipe Face Mesh, Convolution Neural Networks (CNNs), Facial Action Coding System (FACS), and machine learning-based inference models are analyzed. The paper highlights current limitations and identifies opportunities for developing lightweight, real-time behavioral tracking systems. This paper proposes a real-time face emotion detection and behavior analysis system based on YOLO11, Media Pipe Face Mesh, and Convolution Neural Networks (CNN). The proposed framework performs high speed face detection using YOLO11 and extracts detailed facial landmarks through Media Pipe Face Mesh. A CNN-based emotion classifier is trained to recognize seven primary human emotions: angry, disgust, fear, happy, neutral, sad, and surprise. In addition to emotion recognition, the proposed system performs behavioral analysis including blink detection, gaze tracking, eyebrow movement analysis, mouth state detection, head pose estimation, yawn detection, and attention score calculation

The project Emotion Detection Using Deep Learning‖ successfully integrates advanced artificial intelligence techniques to recognize human emotional states and generate appropriate system responses. Through the use of convolution neural networks (CNN), LSTM units, and transformer-based architectures, the system demonstrates reliable accuracy in classifying emotions such as happiness, sadness, anger, fear, surprise, and neutrality. This not only improves human–computer interaction but also provides valuable support in domains such as mental health monitoring, smart education, security surveillance, and personalized user experiences. The experiments show that deep learning–based models outperform traditional machine learning approaches and are capable of functioning effectively in real-time environments with proper preprocessing and dataset balancing. The project establishes a solid foundation for future work involving multimodal emotion recognition, context-aware actions, IoT integration, and deployment on mobile and embedded platforms. In this work, we survey computational models for the recognition of the following positive emotions: admiration, amusement, awe, compassion, contentment, elation, enthusiasm, excitement, gratitude, pride, relief, and sympathy. The choice is inspired by the previous works exploring the differences between positive emotions, especially. Further, we conduct preliminary queries to main databases of research papers to gain a better understanding of the variety of papers addressing classification, detection, and recognition of these emotions. More specifically, the labels are selected based on how reflective and inclusive they are of the current literature, while also taking practical concerns into account. After preliminary queries, some labels are excluded due to their ambiguous nature both in theory and in the contexts in which the research was conducted. We intentionally excluded generic descriptions of positive state, such as joy, happiness, and their synonyms such as enjoyment. This decision is made since our aim is to survey specific, well-defined emotional states, as well as the contexts in which they appear.

[1]R.W.Picard, AffectiveComputing. Cambridge, MA, USA: MITPress, 1997. [2]P. Ekman and W. V. Friesen, Facial Action Coding System: A Technique for the MeasurementofFacialMovement.PaloAlto, CA, USA: ConsultingPsychologistsPress, 1978. [3]J.Redmon,S.Divvala,R.Girshick,andA.Farhadi,”YouOnlyLookOnce:Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779-788. [4]Ultralytics, “YOLO11 Architecture and Real-Time Object Detection Engine OptimizationDocumentation,”UltralyticsDeepLearningRepository, 2024.[Online]. Available: https://github.com/ultralytics/ultralytics [5]P. Viola and M. Jones, “Rapid Object Detection using Boosted Cascade of Simple Features,”inProceedingsofthe2001IEEEComputerSocietyConferenceonComputer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, 2001, pp. I-511–I-518. [6]M.Abadietal.”TensorFlow:e-ScaleMachineLearningonHeterogeneous Distributed Systems,”arXiv preprint arXiv:1603.04467, 2016. [7]D. P. Kingman and J. Ba, “Adam: A Method for Stochastic Optimization,” in Proceedingsofthe3rdInternationalConferenceonLearningRepresentations (ICLR), San Diego, CA, USA, 2015. [8]C.Lugaresietal.”MediaPipe: AFrameworkforBuildingPerceptionPipelines,”arXiv preprint arXiv: 1906.08172, 2019. [9]T. Soukupova and J. Cech, “Real-Time Eye Blink Detection Using Facial Landmarks,”inProceedingsofthe21stComputerVisionWinterWorkshop (CVWW), Rimske Toplice, Slovenia, 2016, pp. 1-8. [10]G.Bradski,”TheOpenCV Library,”Dr.Dobb’sJournalofSoftwareTools,vol.25, Pp.120-123,2000. [11]I.J.Goodfellow, Y.Bengio, andA.Courville, DeepLearning.Cambridge, MA, USA: MIT Press, 2016. [12]Z.Zheng,P.Wang,W.Liu,J.Li,R.Ye,andD.Ren,”Distance-IoULoss:Faster and Better Learning for Bounding Box Regression,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12565-12572, 2020. [13]J. Redmon et al., “YOLO: Real-Time Object Detection,” IEEE Conference on Computer Vision and Pattern Recognition. [14]F. Larradet, R. Niewiadomski, G. Barresi, D. G. Caldwell, and L. S. Mattos, ‗‗Toward emotion recognition from physiological signals in the wild: Approaching the methodological issues in real-life data collection,‘‘ Frontiers Psychol., vol. 11, p. 1111, Jul. 2020. [15]Dahl R.E., Harvey A.G. Sleep in children and adolescents with behavioral and emotional disorders https://www.sciencedirect.com/science/article/pii/S1556407X07000513 [16]Wilson G.F., Russell C.A. Real-time assessment of mental workload using psychophysiological measures and artificial neural networks Hum. Factors, 45 (4) (2003), pp. 635-644 Google Scholar [17]Kang S., Park C.Y., Kim A., Cha N., Lee U.Understanding emotion changes in mobile experience CHI ’22, Association for Computing Machinery, New York, NY, USA (2022), 10.1145/3491102.3501944 V.Lepetit,F.Moreno-Noguer,andP.Fua,”EPnP:AnAccurateO(n)Solutiontothe PnP Problem, “International Journal of Computer Vision, vol. 81, no. 2, pp. 155-166, 20

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close