Yolande Belaïd

Morphological tagging approach in document analysis of invoices

A morphological tagging approach for document image invoice analysis is described. Tokens close by their morphology and confirmed in their location within different similar contexts make apparent some parts of speech representative of the structure elements. This bottom up approach avoids the use of an priori knowledge provided that there are redundant and frequent contexts in the text. The approach is applied on the invoice body text roughly recognized by OCR and automatically segmented. The method makes possible the detection of the invoice articles and their different fields. The regularity of the article composition and its redundancy in the invoice is a good help for its structure. The recognition rate of 276 invoices and 1704 articles, is over than 91.02% for articles and 92.56% for fields.

A Stream-Based Semi-supervised Active Learning Approach for Document Classification

We consider an industrial context where we deal with a stream of unlabelled documents that become available progressively over time. Based on an adaptive incremental neural gas algorithm (AING), we propose a new stream-based semi supervised active learning method (A2ING) for document classification, which is able to actively query (from a human annotator) the class-labels of documents that are most informative for learning, according to an uncertainty measure. The method maintains a model as a dynamically evolving graph topology of labelled document-representatives that we call neurons. Experiments on different real datasets show that the proposed method requires on average only 36.3% of the incoming documents to be labelled, in order to learn a model which achieves an average gain of 2.15-3.22% in precision, compared to the traditional supervised learning with fully labelled training documents.

Case-Based Reasoning for Invoice Analysis and Recognition

This paper introduces the approach CBRDIA (Case-based Reasoning for Document Invoice Analysis) which uses the principles of case-based reasoning to analyze, recognize and interpret invoices. Two CBR cycles are performed sequentially in CBRDIA. The first one consists in checking whether a similar document has already been processed, which makes the interpretation of the current one easy. The second cycle works if the first one fails. It processes the document by analyzing and interpreting its structuring elements (adresses, amounts, tables, etc) one by one. The CBR cycles allow processing documents from both knonwn or unknown classes. Applied on 923 invoices, CBRDIA reaches a recognition rate of 85,22% for documents of known classes and 74,90% for documents of unknown classes.

Incremental classification of invoice documents

This paper deals with incremental classification and its particular application to invoice classification. An improved version of an already existant incremental neural network called IGNG (incremental growing neural gas) is used for this purpose. This neural network tries to cover the space of data by adding or deleting neurons as data is fed to the system. The improved version of the IGNG, called I2GNG used local thresholds in order to create or delete neurons. Applied on invoice documents represented with graphs, I2GNG shows a recognition rate of 97.63%.

An End-to-End Administrative Document Analysis System

This paper presents an end-to-end administrative document analysis system. This system uses case-based reasoning in order to process documents from known and unknown classes. For each document, the system retrieves the nearest processing experience in order to analyze and interpret the current document. When a complete analysis is done, this document needs to be added to the document database. This requires an incremental learning process in order to take into account every new information, without losing the previous learnt ones. For this purpose, we proposed an improved version of an already existing neural network called Incremental Growing Neural Gas. Applied on documents learning and classification, this neural network reaches a recognition rate of 97.63%.

Form Analysis by Neural Classification of Cells

Our aim in this paper is to present a generic approach for linearly combining multi neural classifier for cell analysis of forms. This approach can be applied in a preprocessing step in order to highlight the different kind of information filled in the form and to determine the appropriate treatment. Features used for the classification are relative to the text orientation and to its character morphology. Eight classes are extracted among numeric, alphabetic, vertical, horizontal, capitals, etc. Classifiers are multi-layered perceptrons considering firstly global features and refining the classification at each step by looking for more precise features. The recognition rate of the classifiers for 3. 500 cells issued from 19 forms is about 91%.

A Case-Based Reasoning Approach for Invoice Structure Extraction

This paper shows the use of case-based reasoning (CBR) for invoice structure extraction and analysis. This method, called CBR-DIA (CBR for document invoice analysis), is adaptive and does not need any previous training. It analyses a document by retrieving and analysing similar documents or elements of documents (cases) stored in a database. The retrieval step is performed thanks to graph comparison techniques like graph probing and edit distance. The analysis step is done thanks to the information found in the nearest retrieved cases. Applied on 950 invoices, CBR-DIA reaches a recognition rate of 85.29% for documents of known classes and 76.33% for documents of unknown classes.

Administrative Document Analysis and Structure

This chapter reports our knowledge about the analysis and recognition of scanned administrative documents. Regarding essentially the administrative paper flow with new and continuous arrivals, all the conventional techniques reserved to static databases modeling and recognition are doomed to failure. For this purpose, a new technique based on the experience was investigated giving very promising results. This technique is related to the case-based reasoning already used in data mining and various problems of machine learning. After the presentation of the context related to the administrative document flow and its requirements in a real time processing, we present a case based reasonning for invoice processing. The case corresponds to the co-existence of a problem and its solution. The problem in an invoice corresponds to a local structure such as the keywords of an address or the line patterns in the amounts table, while the solution is related to their content. This problem is then compared to a document case base using graph probing. For this purpose, we proposed an improvement of an already existing neural network called Incremental Growing Neural Gas.

Adaptive technology for mail-order form segmentation

In this paper, an approach for adaptive region segmentation of mail-order forms for high volume application is described. Regions are first identified through a selection of their anchor points described by a constraint graph, illustrating their typographic aspects in the nodes, and their topographical relationships in the arcs. Then the identification of the actual anchor points is performed from a list of textual candidates, using the Arc Consistency Algorithm (AC4). Finally, some contextual heuristics are investigated for properly delimiting the regions. The originality of this approach lies mainly in the absence of a rigid a priori model, replaced by a simple and reliable association of anchor points. The constraint graph used for their description can be easily derived from a general logical definition of their content. Experimental results are overall encouraging and the methodology integration is under execution for commercialization.

Document image and zone classification through incremental learning

We present an incremental learning method for document image and zone classification. We consider an industrial context where the system faces a large variability of digitized administrative documents that become available progressively over time. Each new incoming document is segmented into physical regions (zones) which are classified according to a zonemodel. We represent the document by means of its classified zones and we classify the document according to a document-model. The classification relies on a reject utility in order to reject ambiguous zones or documents. Models are updated by incrementally learning each new document and its extracted zones. We validate the method on real administrative document images and we achieve a recognition rate of more than 92%.