Object Recognition Robust under Translation, Rotation and Scaling in Application of Image Retrieval

We present object recognition algorithm robust under translation, rotation, scaling, local texture distortion and local geometrical deformation of an image. We first solve the problems in image database retrieval by transforming the image space into the Trace transform space. A robust feature from the Trace transform can be thought of as texture representations which can be used in an object recognition. The Trace transform captures the key characteristics of an object by suppressing variations of the image, while maintaining discriminability. In addition, the redundant features are ignored by using only the flagged line in the Trace transform with the help of weighted Trace transform. We obtain a high recognition of 96.78% on 353 images.