D. S. Guru

A simple and robust line detection algorithm based on small eigenvalue analysis

In this paper, a simple and robust algorithm is proposed for detecting straight line segments in an edge image. The proposed algorithm is based on small eigenvalue analysis. The statistical and geometrical properties of the small eigenvalue of the covariance matrix of a set of edge pixels over a connected region of support are explored for the purpose of straight line detection. The approach scans an input edge image from the top left corner to the bottom right corner with a moving mask of size k × k for some odd integer k > 1. At every stage, the small eigenvalue of the covariance matrix of the edge pixels covered by the mask and connected to the center pixel of the mask is computed. These pixels are said to be linear edge pixels if the computed small eigenvalue is less than a pre-defined threshold value. Several experiments have been conducted on various images with considerable background noise and also with significant edge point location errors to reveal the efficacy of the proposed model. The results of the experiments emphasize that the proposed model outperforms other models specifically the Hough transform and its variants in addition to being robust to image transformations such as rotation, scaling and translation.

Multivalued type proximity measure and concept of mutual similarity value useful for clustering symbolic patterns

In this paper, a novel similarity measure for estimating the degree of similarity between two patterns (described by interval type data) is proposed. The proposed measure computes the degree of similarity between two patterns and approximates the computed similarity value by a multivalued type data. Unlike conventional proximity matrices, the proximity matrix obtained through the application of the proposed similarity measure is not necessarily symmetric. Based on this unconventional similarity matrix a modified agglomerative method by introducing the concept of mutual similarity value (MSV) for clustering symbolic patterns is also presented. Experiments on various data sets have been conducted in order to study the efficacy of the proposed methodology.

Rapid and brief communication: Multivalued type dissimilarity measure and concept of mutual dissimilarity value for clustering symbolic patterns

A successful attempt in exploring a dissimilarity measure which captures the reality is made in this paper. The proposed measure unlike other measures (Pattern Recognition 24(6) (1991) 567; Pattern Recognition Lett. 16 (1995) 647; Pattern Recognition 28(8) (1995) 1277; IEEE Trans. Syst. Man Cybern. 24(4) (1994)) is multivalued and non-symmetric. The concept of mutual dissimilarity value is introduced to make the existing conventional clustering algorithms work on the proposed unconventional dissimilarity measure.

Symbolic representation of two-dimensional shapes

In this paper, we present a method for representing a two-dimensional shape by symbolic features. A shape is represented in terms of multi-interval valued type features. A similarity measure defined over symbolic features that is useful for retrieval of shapes from a shape database is also presented. Unlike other shape representation schemes, the proposed scheme is capable of preserving both contour as well as region information. The proposed method of shape representation and retrieval is shown to be invariant to image transformations (translation, rotation, reflection and scaling) and robust to minor deformations and occlusions. Several experiments have been conducted to demonstrate the feasibility of the methodology and also to highlight its advantages over an existing methodology.

Triangular spatial relationship: a new approach for spatial knowledge representation

Abstract In this paper, an important aspect of problems in symbolic image database retrieval (SIDR) is addressed. The problems in conventional pairwise spatial relationships, particularly the 9DLT-matrix-based approach, used to represent a symbolic image in SID are discussed. A new concept called triangular spatial relationship (TSR) is introduced as an improved, invariant spatial relationship to take care of object transformations. A set of quadruples is used to preserve the TSR among the components in a symbolic image. The proposed method is based on principal component analysis. The first principal component vector (PCV) of the set of quadruples is used to represent a symbolic image in SID. The proposed algorithm requires O(log n ) search time in the worst case in the recognition phase, where n is the number of symbolic images stored in the symbolic image database.

Symbolic image indexing and retrieval by spatial similarity: An approach based on B-tree

In this paper, the problem of indexing symbolic images based on spatial similarity is addressed. A model based on modified triangular spatial relationship (TSR) and B-tree is proposed. The model preserves TSR among the components in a symbolic image by the use of quadruples. A Symbolic Image Database (SID) is created through the construction of B-tree, an efficient multilevel indexing structure. A methodology to retrieve similar symbolic images for a given query image is also presented. The presented retrieval model has logarithmic search time complexity. The study made in this work reveals that the model bears various advantages when compared to other existing models and it could be extended towards dynamic databases. An extensive experimentation is conducted on various symbolic images and also on the ORL and YALE face databases. The results of the experimentation conducted have revealed that the proposed scheme outperforms the existing algorithms and is of practical relevance.

An invariant scheme for exact match retrieval of symbolic images based upon principal component analysis

In this paper, an important aspect in creating a symbolic image database (SID), useful for exact match retrieval is addressed. The problem in conventional pairwise spatial relationships (particularly the 9DLT matrix) based approach for representing symbolic images in SID is discussed. An efficient method specifically for exact match retrieval, invariant to image transformations is proposed. In order to take care of image transformations, a new concept called direction of reference is introduced. The relative spatial relationships existing among the components present in an image are perceived with respect to the direction of reference and preserved by a set of triples. The proposed method is based upon principal component analysis (PCA). The first principal component vector (PCV) of the set of triples corresponding to an image is computed and stored as the representative of that image. The PCVs corresponding to n images to be archived in the SID are stored in a sorted order. A methodology for exact match retrieval is also presented in this paper. The presented retrieval algorithm takes O(log n) search time in the worst case, with the help of the binary search technique, where n is the number of symbolic images stored in the SID.

Symbolic representation of text documents

This paper presents a novel method of representing a text document by the use of interval valued symbolic features. A method of classification of text documents based on the proposed representation is also presented. The newly proposed model significantly reduces the dimension of feature vectors and also the time taken to classify a given document. Further, extensive experimentations are conducted on vehicles-wikipedia datasets to evaluate the performance of the proposed model. The experimental results reveal that the obtained results are on par with the existing results for vehicles-wikipedia dataset. However, the advantage of the proposed model is that it takes relatively a less time for classification as it is based on a simple matching strategy.

Archival and retrieval of symbolic images: an invariant scheme based on triangular spatial relationship

In this paper, a novel scheme for representing symbolic images in a symbolic image database (SID) is proposed. The proposed scheme is based on triangular spatial relationship (TSR) [Pattern Recognition Lett. 22 (2001) 999]. The scheme preserves TSR among the components in a symbolic image by the use of quadruples. A SID is created through the construction of B-tree, an efficient multilevel indexing structure. A methodology to retrieve similar images for a given query image is also presented. The presented retrieval model has logarithmic search time complexity. The study made in this work reveals that the model bears various advantages when compared to other existing models and could be extended towards dynamic databases.

Textural features in flower classification

In this work, we investigate the effect of texture features for the classification of flower images. A flower image is segmented by eliminating the background using a threshold-based method. The texture features, namely the color texture moments, gray-level co-occurrence matrix, and Gabor responses, are extracted, and combinations of these three are considered in the classification of flowers. In this work, a probabilistic neural network is used as a classifier. To corroborate the efficacy of the proposed method, an experiment was conducted on our own data set of 35 classes of flowers, each with 50 samples. The data set has different flower species with similar appearance (small inter-class variations) across different classes and varying appearance (large intra-class variations) within a class. Also, the images of flowers are of different pose, with cluttered background under various lighting conditions and climatic conditions. The experiment was conducted for various sizes of the datasets, to study the effect of classification accuracy, and the results show that the combination of multiple features vastly improves the performance, from 35% for the best single feature to 79% for the combination of all features. A qualitative comparative analysis of the proposed method with other well-known existing state of the art flower classification methods is also given in this paper to highlight the superiority of the proposed method.