Robotics is the fastest growing technology in the scientific world. Robotics today is being applied to various industries for different applications. Also it replaces human process and where people are required to do monotonous job repeatedly. At these places robots are found ideal replacements. In this paper we will discuss one such robot localization algorithm called as SIFT algorithm. Scale Invariant Feature Transform (SIFT) is an algorithm in Computer vision to detect local features of image.  Identification of target in image processing using SIFT algorithm is proposed in this paper. This SIFT feature descriptor is invariant to uniform scaling, orientation and invariant to illumination changes.


 Improvement in SIFT has also been proposed in this paper using the fusion of Discrete Wavelet Transform (DWT), Singular Value Descriptor (SVD) and SIFT algorithm. This combination of algorithm preserves the features from the images. With the help of this proposed technique improved efficiency is obtained in terms of resolution and contrast