This paper focuses on an empirical hand gesture recognition system in the domain of image processing and machine learning. The hand gesture is probably the most intuitive and frequently used mode of nonverbal communication in human society. The paper analyzes the efficiency of the Histogram of Oriented Gradients (HOG) as the feature descriptor and Support Vector Machine (SVM) as the classification model in case of gesture recognition. There are three stages of the recognition procedure namely

more »

... age binarization, feature extraction, and classification. The findings of the paper show that the model classifies hand gestures for the given dataset with satisfactory efficiency. The outcome of this work can be further utilized in practical fields of realworld applications dealing with non-verbal communication. From the confusion matrix, it is evident that the proposed method is highly efficient and can meet the real-time application requirements. V. CONCLUSION This paper outlines an empirical approach to hand gesture recognition. The system model presents a simple yet powerful and suitable method that can detect and recognize hand gestures by combining HOG based feature extraction method and SVM based classification. The work presented here provides a groundwork which can be utilized in real-life applications. The simplicity of the model provides support for lite-applications. We can further extend the work to include more nonverbal communication modes, eye-contacts, understanding the meaning of gesture signals in a cross-culture context, etc. ACKNOWLEDGMENT I would like to express my gratitude to the Ministry of ICT, Government of Bangladesh for providing me with a fellowship during my research period.