This study mainly focuses on the effect of sunn pest on wheat. The most prominent feature among the high quality wheat with sun-drenched wheat is the shape differences. For this reason, in this study, a shape recognition method based on the angle information of Fourier transformation is proposed. The performance of the proposed descriptor tested in data sets such as Mpeg-7, leaf, caltech 101, animal. In addition to these datasets, experimental studies were conducted in order to recognize non - classified wheat. Experimental results show that our proposed descriptor provides good accuracies indicating that Fourier Transform based local descriptor captures important characteristics of images that are useful for classification.