Detection of hand gestures with human computer recognition by using support vector machine

Many applications, such as interactive data analysis and sign detection, can benefit from hand gesture recognition. We offer a low-cost approach based on human-computer interaction for predicting hand movements in real time. Our technique involves using a color glove to train a random forest classifier and then predicting a naked hand at the pixel level. Our algorithm anticipates all pixels at a rate of around 3 frames per second and is unaffected by differences in the surroundings. It's also been proven that HCI-based data augmentation is more effective than any other way for enhancing interactive data. In addition, the augmentation experiment was carried out on multiple subsets of the original hand skeleton sequence dataset, each with a different number of classes, as well as on the entire dataset. On practically all subsets, the proposed base architecture improved classification accuracy. When the entire dataset was used, there was even a modest improvement. Correct identification could be regarded as a quality indicator. The best accuracy score was 94.02 percent for the HCI-model with support vector machine (SVM) classifier.