Neural perceptual model to global-local vision for recognition of the logical structure of administrative documents
This work addresses document structure recognition for administrative processing, but it appears incremental as it builds on existing neural network methods with a focus on transparency.
The paper tackles the problem of segmenting administrative document images by defining a Transparent Neural Network (TNN) that simulates global-local vision, based on psychological studies, and shows it is clearer for users and more powerful in recognition compared to a multi-layer perceptron (MLP).
This paper gives the definition of Transparent Neural Network "TNN" for the simulation of the globallocal vision and its application to the segmentation of administrative document image. We have developed and have adapted a recognition method which models the contextual effects reported from studies in experimental psychology. Then, we evaluated and tested the TNN and the multi-layer perceptron "MLP", which showed its effectiveness in the field of the recognition, in order to show that the TNN is clearer for the user and more powerful on the level of the recognition. Indeed, the TNN is the only system which makes it possible to recognize the document and its structure.