Digital photos are massively produced while digital cameras are becoming popular; however, not every photo has good quality. Blur is one of the conventional image quality degradation which is caused by various factors like limited contrast; inappropriate exposure time and improper device handling. Blurry images make up a significant percentage of anyone's picture collections. So, an efficient tool is requiring for detecting blurry images and labeling or separating them for automatic deletion in order to preserve storage capacity. There are various methods to detect the blur from the blurry images some of which requires transforms like DCT or Wavelet and some don’t require transform. A new technique is presented which automatically detect blurry images and separate them for later processing. The method will find out key points for both original and filtered image by using SIFT algorithm. After that calculate variance value for both the key points. Draw and analyse the plotted graph to determine whether the image is blurry or not. According to the type of image whether it is sharp or blur it is save in respective folder for later processing and also calculate time needed for processing.