Recognition of Paintings at an Museum

This article investigates a technique which recognizes a painting from its snapshot using the given training set of snapshots. The snap shot of the painting might have been taken at a different vantage point and time compared to its snap shots in the training set. This kind of techniques is known as ‘Augmented reality’ techniques. created a database of Iraqi National museum and Free drawing exhibition in Ministry of culture and media in Baghdad, We initially use a histogram of colors as our features, and then we analyze more advanced features like the histogram of gradient orientations (HOG). apply several multi-class classification techniques like k-nearest neighbors, decision tree, and k-means to our problem and achieve a maximum classification accuracy of 97/98% for recognition of paintings

کلیدواژه ها:

Recognition Image ، Augmented Reality ، Painting at an Museum