Histogram-Based Image Pre-processing for Machine Learning
Sada Ayumi, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya · 2018
This paper proposes to use some image processing methods as a data normalization method for machine learning. Conventionally, z-score normalization is widely used for pre-processing of data. In the proposed approach, in addition to z-score normalization, a number of histogram-based image processing methods such as histogram equalization are applied to training data and test data as a pre-processing method for machine learning. We evaluate the effectiveness of the proposed approach by using a support vector machine algorithm and a random forest one. In experiments, the proposed scheme is applied to a face-based authentication algorithm with SVM/random forest classifiers to confirm the effectiveness. For SVM classifiers, both z-score normalization and image enhancement work well as a pre-processing method for improving the accuracy. In contrast, for random forest classifiers, a number of image enhancement methods work well, although z-score normalization is unuseful for improving the accuracy.