This paper mainly focuses on developing an interactive system that enables users to create digital art using hand gestures real-time video captured through a webcam. It classifies the video frame gestures and translates them into drawing actions like brush strokes, color changes, size adjustments, etc. The existing system addresses limitations in gesture-based platforms, such as reliance on hardware-intensive devices like notepads and some digital slates for drawing purpose. To overcome these limitations, the workflow begins with a dataset comprising video frames input, which undergo preprocessing for which Gaussian noise and minor variations caused by sensor inaccuracies are removed by Gaussian Blur filtering technique. Then, the feature extraction is carried out in two stages: static features and dynamic features. The static features include spatial data like hand shape, position, and the relative coordinates of key landmarks such as fingertips and joints. The dynamic features capture temporal changes, such as the velocity and trajectory of hand movements derived from consecutive frames. These features are then fed into classification algorithms such as K-Nearest Neighbors (KNN), Support Vector Machines (SVMs), and Convolutional Neural Networks (CNNs), for gesture recognition. Finally, the performance of all algorithms has been measured by the evaluation metrics like accuracy, false positive, false negative, and ambiguous gestures. This type of solution enhances creative human–computer interaction and paves the way for accessible and innovative gesture recognition-based interfaces.