The aim of image (photo) based emotion recognition system emotion is to detect and classify the emotion from the human face from an image. The automatic system mainly has two components i.e. extraction of facial feature and classification of facial feature. To classify the feature precisely effective feature classification methods should be applied. Many recent systems uses additional information from classification which reduces accuracy as well as increase execution time. In this system Double Local Binary Pattern (DLBP) is used for feature extraction which is a variant of Local Binary Pattern (LBP). Since DLBP has small dimension size which reduces the detection time. To handle local illumination problem Logarithmic Laplace-Domain is proposed (LoL-Domain). Finally, Convolution Neural Network (CNN) is used for an obtained feature for classification.