Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the input information consists of directed positional acyclic graphs (DPAGs). In fact, recursive networks are fed following the partial order defined by the links of the graph. Unfortunately, the hypothesis of processing DPAGs is sometimes too restrictive, being the nature...

Retrieving graphs containing a query graph from a large graph database is a key task in many graph-based applications, including chemical compounds discovery, protein complex prediction, and structural pattern recognition. However, graph data handled by these applications is often noisy, incomplete, and inaccurate because of the way the data is produced. In this paper,we study subgraph queries ...

We consider a problem which can greatly enhance the areas of cursive script recognition and the recognition of printed character sequences. This problem involves recognizing words/strings by processing their noisy subsequences. Let X* be any unknown word from a finite dictionary H. Let U be any arbitrary subsequence of X*. We study the problem of estimating X* by processing Y, a noisy version o...

Various factors affect the degree of mass crime of an environment, including social, economic, and physical factors. The purpose of this research is to investigate the role of the physical components of an environment on mass crime rate. In this regard, open spaces between residential complexes were selected as the case studies and based on five outdoor patterns including linear pattern, disper...

This paper describes a method for affine-invariant syntactic pattern recognition of geometric patterns using a new type of context-free graph grammar. The grammar accommodates variability in the geometric relations between parts of patterns; this variability is modelled using affine transformations and metric tensors. A parallel parsing algorithm is outlined, which is suitable for non-Eulerian ...

In the present paper we address the fingerprint classification problem with a structural pattern recognition approach. Our main contribution is the definition of modified directional variance in orientation vector fields. The new directional variance allows us to extract regions from fingerprints that are relevant for the classification in the Henry scheme. After processing the regions of inter...

In this paper, we outline a self-organizing map (SOM) based approach to monitor process transitions. The framework integrates SOM with clustering and sequence comparison methods for plant wide monitoring and fault diagnosis. Process abnormality is detected through cluster analysis while syntactic pattern recognition technique and profile sequence comparison techniques render data based fault di...

We study the problem of recognizing a string Y which is the noisy version of some unknown string X* chosen from a finite dictionary, H. The traditional case which has been extensively studied in the literature is the one in which Y contains substitution, insertion and deletion (SID) errors. Although some work has been done to extend the traditional set of edit operations to include the straight...

This paper describes a syntactic approach to the classiication of moving objects in front of a video camera. The implementation of syntactic pattern recognition techniques is examined for a real-time system, focusing on the detection of human heads in front of a video camera. In particular, I will be describing the technique used to classify objects between heads and non-heads, the results achi...