The Agnosia is a neurological condition that leads to an inability to name, recognize, and extract meaning from the visual, auditory, and sensory environment, despite the fact that the receptor organ is perfect. Visual agnosia is the most common type of this disorder. People with agnosia have trouble communicating between the mind and the brain. As a result, they cannot understand the images seen. In this paper, a model is proposed that is based on the visual pathway so that it first receives the visual stimulus and then, after understanding, the object is identified. In this paper, a model based on the visual pathway is proposed and using intelligent Fuzzy Cognitive Map will help improve image processing in the minds of these patients. First, the proposed model that is inspired by the visual perception pathway, is designed. Then, appropriate attributes that include the texture and color of the images are extracted and the concept of the seen image is perceived using Fuzzy Cognitive Mapping, the meaning recognition and the relationships between objects. This model reduces the difficulty of perceiving and recognizing objects in patients with visual agnosia. The results show that the proposed model, with 98.1% accuracy, shows better performance than other methods. تفاصيل المقالة

Facial expressions determine the inner emotional states of people. Different emotional states such as anger, fear, happiness, etc. can be recognized on people's faces. One of the most important emotional states is the state of fear because it is used to diagnose many diseases such as panic syndrome, post-traumatic stress disorder, etc. The face is one of the biometrics that has been proposed to detect fear because it contains small features that increase the recognition rate. In this paper, a biological model inspired an early biological model is proposed to extract effective features for optimal fear detection. This model is inspired by the model of the brain and nervous system involved with the human brain, so it shows a similar function compare to brain. In this model, four computational layers were used. In the first layer, the input images will be pyramidal in six scales from large to small. Then the whole pyramid entered the next layer and Gabor filter was applied for each image and the results entered the next layer. In the third layer, a later reduction in feature extraction is performed. In the last layer, normalization will be done on the images. Finally, the outputs of the model are given to the svm classifier to perform the recognition operation. Experiments will be performed on JAFFE database images. In the experimental results, it can be seen that the proposed model shows better performance compared to other competing models such as BEL and Naive Bayes model with recognition accuracy, precision and recall of 99.33%, 99.71% and 99.5%, respectively تفاصيل المقالة