Automated inspection of fruit quality involves computer vision based recognition of healthy and defected fruits based on colour and texture features derived from fruit images. This paper introduces a low level feature, colour texture moments which combines colour moments and local Fourier transform as a texture representation for quality inspection of tropical fruits in Maharashtra such as guavas. First, Local Fourier Transform is applied to derive eight characteristics maps for describing co-occurrence relation of pixel in each colour space. Then, the first and second moments of these maps resulting in 48 dimensional feature vectors are calculated. The colour texture moments with classifiers namely probabilistic Neural Network and Support Vector Machines are tested to sort defective fruits. The results show the effectiveness of the colour texture moments in terms of its absolute performance and comparative performance compared to the other colour space and the support vector machine classifier. An overall 97.14% classification accuracy is achieved by support vector machines. © IDOSI Publications, 2013.