Identity management systems with biometric key binding make digital transactions secure and reliable. A novel methodology is proposed to develop an intelligent key management system using facial emotions. Key binding with facial emotions makes use of an intrinsic user specific trait facilitating a more natural computer to human interaction. The proposed system utilizes metaheuristic swarm intelligence based optimization techniques to extract optimal features. The work demonstrates key binding by encrypting an image with a secret key bound to optimal features extracted from facial emotions. Efficiency and correctness of proposed key management is validated by successful decryption at receiving end with any one of the enrolled emotions given as input. Deer Hunting Optimization Algorithm and Chicken Swarm Optimization are merged to select optimal features from facial emotions. The derived algorithm is called Fitness Sorted Deer Hunting Optimization Algorithm with Rooster Update. Seven facial emotions — anger, disgust, fear, happiness, sadness, surprise and neutral are used to extract optimal features from Japanese Female Facial Expressions and Yale Facial datasets to train the neural network. Proposed work achieved better performance results over state-of-art optimization algorithms such as whale optimization algorithm, grey wolf optimization, chicken swarm optimization and deer hunting optimization algorithm. Accuracy of proposed model is 2.2% better than deer hunting optimization algorithm and 12.3% better than chicken swarm optimization for a key length 80.