Automatic image annotation base on Naive Bayes and Decision Tree classifiers using MPEG-7

TL;DR

This paper presents an image annotation method using MPEG-7 features combined with Naive Bayes and Decision Tree classifiers, demonstrating improved precision and efficiency with Naive Bayes.

Contribution

It introduces a hybrid approach utilizing MPEG-7 descriptors and PCA for feature extraction, and compares classifier performance for image annotation.

Findings

Naive Bayes outperforms Decision Tree in precision and speed.

MPEG-7 descriptors effectively extract relevant image features.

PCA reduces feature dimensionality without significant loss.

Abstract

Recently it has become essential to search for and retrieve high-resolution and efficient images easily due to swift development of digital images, many present annotation algorithms facing a big challenge which is the variance for represent the image where high level represent image semantic and low level illustrate the features, this issue is known as semantic gab. This work has been used MPEG-7 standard to extract the features from the images, where the color feature was extracted by using Scalable Color Descriptor (SCD) and Color Layout Descriptor (CLD), whereas the texture feature was extracted by employing Edge Histogram Descriptor (EHD), the CLD produced high dimensionality feature vector therefore it is reduced by Principal Component Analysis (PCA). The features that have extracted by these three descriptors could be passing to the classifiers (Naive Bayes and Decision Tree) for training. Finally, they annotated the query image. In this study TUDarmstadt image bank had been used. The results of tests and comparative performance evaluation indicated better precision and executing time of Naive Bayes classification in comparison with Decision Tree classification.