Halftone Image Classification Using LMS Algorithm and Naive Bayes

• Published in: IEEE transactions on image processing Vol. 20; no. 10; pp. 2837 - 2847
• Main Authors: LIU, Yun-Fu, GUO, Jing-Ming, LEE, Jiann-Der
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.10.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive filters; Applied sciences; Bayes theorem; Bayesian analysis; Classification; Classification algorithms; Detection, estimation, filtering, equalization, prediction; Dithering; Entropy; Exact sciences and technology; Feature extraction; halftone image classification; halftoning; image analysis; Image classification; Image processing; Information, signal and communications theory; Inverse; inverse halftoning; Least squares approximation; Optimization; Robustness; Satellite broadcasting; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Telecommunications and information theory; Performance evaluation; Automatic classification; halftoning; Image processing; Dithering; halftone image classification; Signal classification; Image quality; Image analysis; Accuracy; Error diffusion; Robustness; Bayes methods; Half tone image; Image classification; Least mean squares methods; Bayes theorem; inverse halftoning
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2011.2136354

Former research on inverse halftoning most focus on developing a general-purpose method for all types of halftone patterns, such as error diffusion, ordered dithering, etc., while fail to consider the natural discrepancies among various halftoning methods. To achieve optimal image quality for each halftoning method, the classification of halftone images is highly demanded. This study employed the least mean-square filter for improving the robustness of the extracted features, and employed the naive Bayes classifier to verify all the extracted features for classification. Nine of the most well-known halftoning methods were involved for testing. The experimental results demonstrated that the classification performance can achieve a 100% accuracy rate, and the number of distinguishable halftoning methods is more than that of a former method established by Chang and Yu.