Character Recognition Based on k-Nearest Neighbor, Simple Logistic Regression, and Random Forest

Characters recognition has gained significant attention in recent years within the field of artificial intelligence and computer vision as robots increasingly engage in activities that involve collecting and processing texture information. This paper presents a performance comparison among three algorithms: k-nearest neighbor, simple logistic regression, and random forest, for recognizing the alphabet and numeric characters. The proposed method involves obtaining random eigenvalues through random sampling of the training sets. Subsequently, a decision tree is constructed based on the obtained eigenvalues, and multiple decision trees are combined to yield the final judgment result, thus mitigating the risk of overfitting. The implementation of these algorithms is feasible using Python and existing frameworks. The experimental results demonstrate that the random forest algorithm model achieved accurate recognition of simple alphanumeric characters, with a detection accuracy of up to 95.7% in a processing time of 64.37 s.