Journal of Soft Computing and Information Technology

Journal of Soft Computing and Information Technology

Improving Facial Emotional Expression Recognition for Individuals with Visual Agnosia Based on Early Biological Inspired Features Model

Document Type : Persian Original Article

Author
Department of Computer Engineering, FSh.C., Islamic Azad University, Fouman, Iran.
Abstract
Agnosia is a neurological condition that results in the inability to recognize and extract meaning from the visual and auditory environment. Individuals with visual agnosia have difficulty in the communication between the mind and the brain and, as a result, in perceiving the images seen. In this paper, a model based on the visual pathway is proposed that will help these individuals with image and face recognition using fuzzy perceptual mapping. Also, an early biologically inspired feature model will be used to identify facial emotional expressions. First, appropriate features are extracted and then, using fuzzy perceptual mapping, the concept of the seen image is perceived. If the detected image is a face, the early biologically inspired model will be used to extract effective facial features and finally, the facial emotional states are recognized with a support vector machine. The results obtained show that the proposed model performs well with an accuracy of 98.1% in object recognition and an average accuracy of 99.01% in facial emotional states recognition.
Keywords

[1] M. J. Yang, T. J. Nail, and J. Winer, "Left parietal tumors presenting with smartphone icon visual agnosia: Two cases of a modern presentation of Gerstmann syndrome," World Neurosurgery, vol. 142, pp. 233–238, 2020.
[2] N. Seijdel, H. S. Scholte, and E. H. F. de Haan, "Visual features drive the category-specific impairments on categorization tasks in a patient with object agnosia," Neuropsychologia, vol. 161, 2021.
[3] C. Gerlach and R. Robotham, "Chapter 9 - Object recognition and visual object agnosia," in Handbook of Clinical Neurology, Elsevier, vol. 178, pp. 155–173, 2021.
[4] H. J. Peel and P. A. Chouinard, "A review of the impairments, preserved visual functions, and neuropathology in 21 patients with visual form agnosia – A unique defect with line drawings," Neuropsychologia, vol. 190, 2023.
[5] J. H. Missimer, E. Abela, M. Pastore-Wapp, R. Wiest, and B. J. Weder, "Distinguishing transient from persistent tactile agnosia after partial anterior circulation infarcts—Behavioral and neuroimaging evidence for white matter disconnection," NeuroImage: Clinical, vol. 36, 2022.
[6] R. Ptak, F. Turri, and N. Doganci, "Object recognition and visual agnosia," in Encyclopedia of Behavioral Neuroscience, 2nd ed., pp. 587–596, 2022.
[7] B. Fernández, A. Moreira, H. Gomes, J. M. Justo, and V. Pimenta, "Mirror self-image agnosia: A case report," Journal of the Neurological Sciences, vol. 455, 2023.
[8] L. Iterson, L. T. L. Sie, P. B. Augustijn, A. C. S. Rooze, and F. E. Jansen, "Acquired visual agnosia as an uncommon presentation of epileptic encephalopathy in a 6-year-old boy with CSWS," Epilepsy & Behavior Reports, vol. 16, 2021.
[9] O. Martinaud, "Visual agnosia and focal brain injury," Revue Neurologique, vol. 173, no. 7–8, pp. 451–460, 2017.
[10] X. Duanmu, "Image retrieval using color moment invariant," in Seventh International Conference on Information Technology, pp. 200–203, 2010.
[11] R. Ptak and F. Lazeyras, "Functional connectivity and the failure to retrieve meaning from shape in visual object agnosia," Brain and Cognition, vol. 131, pp. 94–101, 2019.
[12] O. Martinaud, "Visual agnosia and focal brain injury," Revue Neurologique, vol. 173, no. 7–8, pp. 451–460, 2017.
[13] F. Yaghouti and S. Motamed, "Recognition of facial expression of emotions based on brain emotional learning (BEL) model," Advances in Cognitive Science, vol. 20, no. 4, pp. 46–61, 2019.
[14] J. Morén, Emotion and learning—a computational model of the amygdala, Ph.D. dissertation, Lund University, Lund, Sweden, 2002.
[15] E. Lotfi, "Mathematical modeling of emotional brain for classification problems," in Proceedings of IAM, vol. 2, no. 1, pp. 60–71, 2013.
[16] H. Yongzhen, H. Kaiqi, W. Liangsheng, T. Dacheng, T. Tieniu, and L. Xuelong, "Enhanced biologically inspired model," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 23–28, 2008.
[17] H. Lechner and J. Zimmermann, "Application of deep learning algorithms to detect agnosia from MRI brain images," Journal of Neuroscience Methods, vol. 330, 2020.
[18] K. L. Ng and E. T. Wong, "A machine learning approach for classifying agnosia types based on behavioral assessments," Frontiers in Neurology, vol. 12, p. 689832, 2021.
[19] Y. Dauphin and H. Cho, "Personalized treatment plans for agnosia: The role of artificial intelligence in rehabilitation," Journal of Cognitive Neuroscience, vol. 34, no. 8, pp. 1293–1305, 2022.
[20] R. Cecere, N. Dundon, and C. Bertini, "When apperceptive agnosia is explained by a deficit of primary visual processing," Elsevier Ltd., pp. 12–27, 2014.
[21] K. Eriksson, A. inen, K. Hirvonen, P. Nieminen, and M. Koivikko, "Visual agnosia in a child with non-lesional occipito-temporal CSWS," Brain & Development, pp. 262–267, 2003.
[22] T. Foulsham and J. Barton, "Modeling eye movements in visual agnosia with a saliency map approach: Bottom–up guidance or top–down strategy?," Neural Networks, vol. 24, pp. 665–677, 2011.
[23] F. Yaghouti and S. Motamed, "Face recognition based on the improved HMAX model," Advances in Cognitive Science, vol. 21, no. 1, pp. 29–44, 2019.
[24] N. Safari and S. Motamed, "Face recognition based on hierarchical model and X (HMAX)," Advances in Cognitive Science, vol. 21, no. 1, pp. 29–44, 2019.
[25] E. Askari, S. K. Setaredan, A. Sheikhani, M. R. Mohammadi, and M. Teshnelab, "Modeling the connections of brain regions in children with autism using cellular neural networks and electroencephalography analysis," Journal of Artificial Intelligence in Medicine, vol. 89, pp. 40–50, 2018.
[26] P. Zhao, H. Xue, X. Ji, H. Liu, and L. Han, "Zero-shot learning via visual feature enhancement and dual classifier learning for image recognition," Information Sciences, vol. 642, 2023.
[27] H. Lissauer, "A case of visual agnosia with a contribution to theory," Cognition Neuropsychology, vol. 5, pp. 153–192, 1988.
[28] B. L. Finlay, "Focusing the eyes and recognizing objects: evo-devo and the sensitive period," Current Opinion in Behavioral Sciences, vol. 36, pp. 36–41, 2020.
[29] H. Sufikarimi and K. Mohammadi, "Role of the secondary visual cortex in HMAX model for object recognition," Cognitive Systems Research, vol. 64, pp. 15–28, 2020.
[30] Y. Wu, "Fusion-based modeling of an intelligent algorithm for enhanced object detection using a deep learning approach on radar and camera data," Information Fusion, vol. 113, 2025.
[31] S. Etemad and M. Amirmazlaghani, "Color texture image retrieval based on Copula multivariate modeling in the Shearlet domain," Engineering Applications of Artificial Intelligence, vol. 102, 2021.
[32] C. Singh, E. Walia, and K. PreetKaur, "Color texture description with novel local binary patterns for effective image retrieval," Pattern Recognition, vol. 76, pp. 50–68, 2018.
[33] H. Zoubir, M. Rguig, M. E. Aroussi, R. Saadane, and A. Chehri, "Pixel-level concrete bridge crack detection using Convolutional Neural Networks, Gabor filters, and attention mechanisms," Engineering Structures, vol. 314, 2024.
[34] J. L. Salmeron and I. Arévalo, "Concurrent vertical and horizontal federated learning with fuzzy cognitive maps," Future Generation Computer Systems, vol. 162, 2025.
[35] S. M. Tabatabaii, T. M. Nazeri, and M. Dastorani, "Performance comparison of GP, ANN, BCSD and SVM models for temperature simulation," Journal of Meteorology and Atmospheric Sciences, vol. 1, no. 1, pp. 53–64, 2018.
[36] V. Kumar, V. Kumar, and T. Chan, "Bayes and Naive Bayes Classifier," arXiv, 2014.
[37] J. Morén, T. Shibata, and K. Doya, "The mechanism of saccade motor pattern generation investigated by a large-scale spiking neuron model of the superior colliculus," PloS One, vol. 8, 2013.