Due to the variations of facial expressions, the process of emotion recognition is a highly demanding and challenging task in many image processing applications. So, the traditional works introduced different techniques for facial image recognitions, which includes the drawbacks of reduced accuracy and recognition rate. Thus, this work aims to develop a new emotion recognition system by implementing different image processing techniques. Initially, the image obtained from the video sequence is preprocessed by employing the Neighborhood Pixel Intensity based Filtering (NPIF) technique. Then, the Viola Jones algorithm is implemented to extract the face by suppressing the background and foreground regions, which increases the accuracy of recognition. After that, the Convoluted Local Binary Pattern (CLBP) technique is employed to extract the patterns of the background suppressed image. Based on the extracted key points, the emotion of the given image is recognized by using the Grouping based Neural Network (GNN) classification technique.