A new Image recognition technique supported wavelet transform (DWT) and Singular price Decomposition (SVD) that's capable of retrieving most of the photographs like the target image. during this technique used DWT to transfer the target image from the spatial domain into frequency domain during which it's divided into four sub bands, Low-Low (LL), Low-High (LH), poker (HL) and High-High (HH) frequencies. during this applied 3 levels of 2-D DWT to concentrate the image illumination elements into the third-level LL sub band and so applied SVD to extract its singular values because the reliable and strong options for the popularity. we tend to additionally calculated the mean and variance of the low frequency LL sub-band for the input image to make a feature vector composed of mean, variance, and singular values of the LL sub band, also because the coefficients of the LL sub band. Once the feature vector is made it's compared with the feature vectors keep in our information to acknowledge and retrieve the pictures that are like target image supported the minimum error criteria.