This paper presents an improvement on a biologically inspired net- work for image classification. Previous models have used a multi- scale and multi-orientation architecture to gain robustness to trans- formations and to extract complex visual features. Our contribution to this type of architecture resides in the building of complex visual features which are better tuned to images structures. We allow the network to build complex features with richer information in terms of the local scales of image structures. Our classification results show significant improvements over previous architectures using the same framework.