A Method for Detecting Document Orientation by Using NaÏve Bayes Classifier

An approach for document orientation detection and classification using Naive Bayes theorem is proposed in this paper. First, all the characters in a document image will be isolated and some valid ones are selected. Using the valid characters, the document image will be vectorized to a 32-dimensional vector. Gaussian distribution function is used to calculate the probability of each dimension, and then the posterior probabilities of the query document image in each class are also calculated. Finally, the orientation of document is detected as the class with the highest probability. Experimental results show the accuracy of the proposed method is considerably higher than Bray Curtis distance, even for some worse samples.