Performance evaluation of image retrieval using Enhanced 2D Dual Tree Discrete Wavelet Transform

摘要

Content based image retrieval is emerging as an important area of research in image processing. Based on dual tree discrete wavelet transform, and minimum distance classification the feature vectors are extracted and similarity is found in existing research. This paper proposes a new method for improving the performance of image retrieval system using Enhanced 2D Dual Tree Discrete Wavelet Transform (E-2D-DT-DWT). The number feature vectors are increased with higher levels of decomposition in the extraction method. In addition to Euclidean distance as the distance measure of feature vectors, this paper also proposes minimum distance classification for an efficient and effective distance classification. Performance evaluation is done using two parameters precision and recall. The experimental results show that precision and recall is improved with the proposed method.