Abstract
In this paper, we propose an algorithm for a Content Based Image Retrieval (CBIR) system based on Wavelet Transformation and Deep Autoencoder (DAE). For the proposed algorithm, the image is first processed by wavelet transform and decomposed into wavelet coefficients. The wavelet coefficients then become the input for a multiple input multiple task deep autoencoder (MIMT-DAE). In our design, only the approximation coefficients (CA) and diagonal detail coefficients (CD) are used. The result of retrieval performance is tested on the MNIST handwriting data base. The testing results show that the combination of wavelet transformation and MIMT-DAE increases the performance of image retrieval for shape and texture compared to a traditional single input single task deep autoencoder with far fewer training parameters required.