We witness many people who face disabilities like being deaf, dumb, blind etc. They face a lot of challenges and difficulties trying to interact and communicate with others. This paper presents a new technique by providing a virtual solution without making use of any sensors. Histogram Oriented Gradient (HOG) along with Convolutional Neural Network (CNN) have been implemented. The algorithm recognizes the real-time image gestures, identifies the text, and gives voice output. In this paper, we introduce a Sign Language recognition. The user must be able to capture images of hand gestures using a web camera in this analysis, and the system must predict and show the name of the captured image. The captured image undergoes series of processing steps, which include various Computer vision techniques such as the conversion to gray - scale, and mask operation. Convolutional Neural Network (CNN) is used to train our model and identify the pictures.