Relevance Modeling Approach 

to Handwritten Historical Document Retrieval

T. M. Rath, R. Manmatha, V. Lavrenko [trath, manmatha, lavrenko]


Words that appear in a historical document are treated as having a dual representation: an image form and the corresponding annotation (or label). In the relevance model retrieval framework, the image form of a word is represented with terms from a discrete image vocabulary. This vocabulary can be seen as forming a language, just like French or any other kind of language.

Illustration of the dual representation of words

Figure 1: Illustration of the dual representation concept of words

Once we are presented with an ASCII query in English (e.g. 'Wilper'), the goal is to find (retrieve) images of words, which are likely to be "translations" of the query in the image language. The approach here is inspired by the success of the cross-language information retrieval  (CLIR) approach based on relevance modeling. In the CLIR framework, documents in a foreign language (e.g. French) are retrieved using quer
es in a familiar language (e.g. English).

Retrieval Approaches

Probabilistic Annotation

The probabilistic annotation model annotates each word image in the collection with all possible annotations/labels. That is, a particular word image could have any given ASCII annotation. Each of these annotation has an attached probability, to express the uncertainty about the labeling. The per-word image annotation probabilities form a probability distribution over the entire annotation vocabulary that is considered.
For the retrieval of documents, all word-level annotation distributions in a document are averaged to obtain an approximate document language model. These language models can then be used with classical information retrieval approaches. We use the query-likelihood ranking approach to perform retrieval.

Kullback-Leibler Scoring

In the probabilistic annotation model, the mapping from the image language to the annotation language (English) is done beforehand, and the retrieval operates on the probabilistic annotations, that is, in the annotation vocabulary space.

In the KL-scoring approach, a given query is mapped into the image language at query time. The result is a distribution over image vocabulary terms, the query model. In order to rank word images in the collection, their word image model (image vocabulary distribution) is compared to the query model using Kullback-Leibler divergence. Due to the realtime query 'translation' into the image language, this approach has a longer per-query processing time.

Demonstration Systems

Currently, three demonstration systems are available:
  1. Line Retrieval using probabilistic annotation: This is the first retrieval system that was built for line retrieval. The collection size is 20 pages, which equals 657 lines. 90% of the collection was used for training, 10% (i.e. ~65 lines) to build the retrieval system. Quantitative results on this dataset are available. They indicate average precision scores between 54% and 89% for 1-word to 4-word queries respectively [2].

  2. Page retrieval using probabilistic annotation: The collection size is roughly 1000 pages, with an additional 100 training pages. This demo uses the reordering approach described in [1], so only 1 query term is allowed [1].

  3. Page retrieval using Kullback-Leibler scoring (will be available in the future): This uses the same collection as above. KL-scoring only supports 1-word queries [1].

All datasets used for retrieval were automatically segmented using a scale-space approach [3].


[1] T. M. Rath, R. Manmatha and V. Lavrenko: A Search Engine for Historical Manuscript Images. To appear in the Proc. of the ACM SIGIR 2004 conference, Sheffield, UK, July 25-29.

[2] T. M. Rath, V. Lavrenko and R. Manmatha: A Statistical Approach to Retrieving Historical Manuscript Images without Recognition. CIIR Technical Report MM-42, 2003.

[3] R. Manmatha and N. Srimal: Scale Space Technique for Word Segmentation in Handwritten Documents. In: Proc. of the Second Int'l Conf. on Scale-Space Theories in Computer Vision. Corfu, Greece, September 26-27, 1999, pp. 22-33.