Abstract : We propose to implement the computational principles raised by the study on the K-cells of the retina using a variational specification of the visual front-end, with an important consequence: In such a framework, the GC are not to be considered individually, but as a network, yielding a mesoscopic view of the retinal processWe consider this visual event detection mechanism to be based on image segmentation and specific natural statistical recognition, including temporal pattern recognition, yielding fast region categorization. We discuss how such sophisticated functionalities could be implemented in the biological tissues as a unique generic two-layered non-linear filtering mechanism with feedback. We use computer vision methods to propose an effective link between the observed functions and their possible implementation in the retinal network. The available computational architecture is a two-layers network with non-separable local spatio-temporal convolution as input, and recurrent connections performing non-linear diffusion before prototype based visual event detection. The numerical robustness of the proposed model has been experimentaly checked on real natural images. Finally, model predictions to be verified at the biological level are discussed.