Recognizing Face Micro Expressions Through Surveys

Recognition of facial expressions is essential in a variety of applicationsincluding marketing, commerce, security systems, and psychotherapy. It is rather simple toidentify a macro expression, which is a direct representation of an "emotion." Microexpressions, which are more precise signs of a stream of thought or even subtle, passive, orinvoluntary thoughts, play an equally important role as macro-expressions. Because microexpressions have significantly shorter time periods than macro-expressions and can only beclassified using a bigger classification scale, detecting them is a far more difficult researchquestion. This article provides a thorough examination of all available micro expressionrecognition methods. By breaking down the pipeline into its basic elements—namely, facedetection, pre-processing, facial feature detection and extraction, datasets, and classification—we are able to assess the overall design of the micro-expression recognition system. In additionto highlighting the models and contemporary trends used in their design, we also analyse thefunction of these elements. By contrasting their effectiveness, we also present a thoroughexamination of micro expression recognition systems. We also talk about the new deep learningfeatures that may soon take the role of manually created characteristics for recognizing facemicro expressions. This survey was created with an emphasis on the methodology utilized,databases used, performance related accuracy of recognition, and comparison of these toidentify efficiency gaps, potential future study areas, and research potentials. Through thissurvey, we hope to investigate this issue and create a thorough, effective recognition system.