Dimension Reduction Using Image Transform for Content-Based Feature Extraction

Technological advancements in the field of machine learning have attempted classification of the images of gigantic datasets. Classification with content-based image feature extraction categorizes the images based on the image content in contrast to conventional text-based annotation. The chapter has presented a feature extraction technique based on application of image transform. The method has extracted meaningful features and facilitated feature dimension reduction. A technique, known as fractional coefficient of transforms, is adopted to facilitate feature dimension reduction. Two different color spaces, namely RGB and YUV, are considered to compare the classification metrics to figure out the best possible reduced feature dimension. Further, the results are compared to state-of-the-art techniques which have revealed improved performance for the proposed feature extraction technique.