Using fractal interpolation over complex network modeling of deep texture representation

Convolutional neural networks have been a funda-mental model in computer vision in the last years. Nevertheless, specifically in the analysis of texture images, the use of that model as a feature extractor rather than trained from scratch or extensively fine tuned has demonstrated to be more effective. In this scenario, such deep features can also benefit from further advanced analysis that can provide more meaningful representation than the direct use of feature maps. A successful example of such procedure is the recent use of visibility graphs to analyze deep features in texture recognition. It has been found that models based on complex networks can quantify properties such as periodicity, randomness and chaoticity. All those features demonstrated usefulness in texture classification. Inspired by this context, here we propose an alternative modeling based on complex networks to leverage the effectiveness of deep texture features. More specifically, we employ recurrence matrices of the neural activation at the penultimate layer. Moreover, the importance of complexity attributes, such as chaoticity and fractality, also instigates us to associate the complex networks with a fractal technique. More precisely, we complement the complex network representation with the application of fractal interpolation over the degree distribution of the recurrence matrix. The final descriptors are employed for texture classification and the results are compared, in terms of accuracy, with classical and state-of-the-art approaches. The achieved results are competitive and pave the way for future analysis on how such complexity measures can be useful in deep learning-based texture recognition.