This paper presents a new approach for the recognition of emotions in noisy environment. The approach presents the cascading of Wiener filter and Mutation based bacteria optimization technique (MBFO) to remove the noise from the highly corrupted face image .After removing the noise by the combination of wiener filter and MBFO technique and then detects the local , global and statistical feature form the image. Bacterial foraging optimization algorithm (BFOA) is inspired by the social foraging behavior of Escherichia coli. BFOA has already drawn the attention of researchers because of its efficiency in solving real-world optimization problems arising in several application domains. In this research paper seven emotions namely anger, fear, happiness, surprise, sad, disgusting and neutral will be tested from database in noisy environment of speckle noise. facial expressions recognition system is based on a representation of the expression, learned from a training set of pre-selected meaningful features. However, in reality the noises that may embed into an image document will affect the performance of face recognition algorithms. Finally, emotion recognition will be performed by giving the extracted eye, lip and mouth blocks as inputs to a feed-forward neural network trained by back-propagation.
Kashyap, kanchan and SHANTAIYA, SANJIVANI
"STUDY AND ANALYSIS OF STATISTICAL FEATURES OF FACE EXPRESSION IN NOISY ENVIRONMENT,"
International Journal of Image Processing and Vision Science: Vol. 1:
2, Article 9.
Available at: https://www.interscience.in/ijipvs/vol1/iss2/9