This paper presents the evaluation of a parsing strategy for the recognition of sketched diagrams. The architecture of the recognition system consists of three hierarchically arranged layers where the user’ strokes are first segmented and interpreted as primitive shapes, then by exploiting the domain context they are clustered into symbols of the domain and an interpretation of whole sentence i...

In this chapter we discuss the problem of searching a database of hand-drawn documents for a particular hand-drawn query. We show how to break the problem into two parts. First, a matching algorithm must extract pieces of the query and pieces of the database that might be placed in correspondence. Second, the algorithm must examine the pieces in detail to determine how similar they are. We pres...

In the Middle Ages and the Renaissance, it was easy to know the public perception of every rank and occupation of society. The Dance of Death was a popular art form that showed in a series of cartoons each person, from king to peasant, from merchant to beggar, from judge to robber in the final rendezvous with Death, with his or her frailties, dishonesty, and hypocrisies mercilessly exposed. The...

We describe a trainable, hand-drawn symbol recognizer based on a multi-layer recognition scheme. Symbols are internally represented as binary templates. An ensemble of four different classifiers compares and ranks definition symbols according to their similarity to the unknown symbol. The scores of the individual classifiers are aggregated to produce a combined score for each definition. The de...

We present a sketch understanding system for network-like diagrams consisting of symbols linked together. This system employs a novel parser to automatically extract symbols from a continuous stream of pen strokes. The parser uses geometric information to enumerate candidate symbols, and then uses domain knowledge to prune away unlikely candidates. The candidates are classified with a novel, do...

Freehand sketches are complex for recognition. Individual fragments of the drawing are often ambiguous to be interpreted without contextual cues. Markov Random Field (MRF) that ends up with a global model by simply specifying local interactions can naturally suffice the requirement. In our project, a recognizer based on MRF has been constructed to jointly analyze local features in order to inco...

Objectives: The aim of the present study is to investigate the variations of the electro encephalographic (EEG) alpha rhythm in or der to measure the appreciation of bilateral and unilateral young cochlear implant users during the observation of a musical cartoon. The cartoon has been modified for the gen eration of three experimental conditions: one with the original audio, another one with a ...

If we laugh at a ]oke we are likely to think it funny, and funnier situations are expected to cause more laughter and more positive judgments (Calvert, 1949, Zigler, Levme, & Could, 1966) Common sense and psychological theories (Rosenberg, 1^0) suggest that a person's attitudes (evaluations) and emotional reactions are hkely to be consistent But does this consistency between laughter and evalua...

Human observers are capable of interpreting hand drawn sketches as threedimensional objects, despite inconsistencies in lengths, variability in angles, and unconnected vertices. The current system is an attempt to achieve such robust performance in the limited domain of sketches of wireframe rectangular polyhedra. The rst version of this system reconstructs three-dimensional objects from perfec...