This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters), or gray level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability, and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application. Feature extraction Optical character recogniti...

The Core Experiment CE-Shape-1 for shape descriptors performed for the MPEG-7 standard gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour. There are two main differences with respect to other comparison results reported in the literature: (1) For each shape descriptor, the experiments were carried out by an institute that is in favor of this descriptor. This implies that the parameters for each system were optimally determined and the implementations were throughly tested. (2) It was possible to compare the performance of shape descriptors based on totally different mathematical approaches. A more theoretical comparison of these descriptors seems to be extremely hard. In this paper we report on the MPEG-7 Core Experiment CE-Shape1. 1.

The recognition of objects from imagery in a manner that is independent of scale, posi-tion, and orientation may be achieved by characterizing an object with a set of extracted invariant features. Several different recognition techniques have been demonstrated that utilize moments to generate such invariant features. These techniques are derived from general moment theory that is widely used throughout statistics and mechanics. In this paper, basic Cartesian moment theory is reviewed and its application to object recognition and image analysis is presented. The geometric properties of low-order moments are discussed along with the definition of several moment-space linear geometric transforms. Finally, significant research in moment-based object recognition is reviewed. 1.

Abstract—We present an approach for comparing two sequences of deforming shapes using both parametric models and nonparametric methods. In our approach, Kendall’s definition of shape is used for feature extraction. Since the shape feature rests on a non-Euclidean manifold, we propose parametric models like the autoregressive model and autoregressive moving average model on the tangent space and demonstrate the ability of these models to capture the nature of shape deformations using experiments on gaitbased human recognition. The nonparametric model is based on Dynamic Time-Warping. We suggest a modification of the Dynamic time-warping algorithm to include the nature of the non-Euclidean space in which the shape deformations take place. We also show the efficacy of this algorithm by its application to gait-based human recognition. We exploit the shape deformations of a person’s silhouette as a discriminating feature and provide recognition results using the nonparametric model. Our analysis leads to some interesting observations on the role of shape and kinematics in automated gait-based person authentication. Index Terms—Shape, shape sequences, shape dynamics, comparison of shape sequences, gait recognition. 1

future trends

Content based 3D shape retrieval for broad domains like the World Wide Web has recently gained considerable attention in Computer Graphics community. One of the main challenges in this context is the mapping of 3D objects into compact canonical representations referred to as descriptors, which serve as search keys during the retrieval process. The descriptors should have certain desirable properties like invariance under scaling, rotation and translation. Very importantly, they should possess descriptive power providing a basis for similarity measure between three-dimensional objects which is close to the human notion of resemblance. In this paper we advocate the usage of so-called 3D Zernike invariants as descriptors for content based 3D shape retrieval. The basis polynomials of this representation facilitate computation of invariants under the above transformations. Some theoretical results have already been summarized in the past from the aspect of pattern recognition and shape analysis. We provide practical analysis of these invariants along with algorithms and computational details. Furthermore, we give a detailed discussion on influence of the algorithm parameters like type and resolution of the conversion into a volumetric function, number of utilized coefficients, etc. As is revealed by our study, the 3D Zernike descriptors are natural extensions of spherical harmonics based descriptors, which are reported to be among the most successful representations at present. We conduct a comparison of 3D Zernike descriptors against these regarding computational aspects and shape retrieval performance.

In a typical content-based image retrieval (CBIR) system, query results are a set of images sorted by feature similarities with respect to the query. However, images with high feature similarities to the query may be very di#erent from the query in terms of semantics. This discrepancy between low-level features and high-level concepts is known as the semantic gap. This paper introduces a novel image retrieval scheme, CLUster-based rEtrieval of images by unsupervised learning (CLUE), which attempts to tackle the semantic gap problem based on a hypothesis that images of the same semantics are similar in a way, images of di#erent semantics are di#erent in their own ways. CLUE attempts to capture semantic concepts by learning the way that images of the same semantics are similar and retrieving image clusters instead of a set of ordered images. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. Therefore, the clusters give the algorithm as well as the users semantic relevant clues as to where to navigate. CLUE is a general approach that can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus it may be embedded in many current CBIR systems. An experimental image retrieval system using CLUE has been implemented. The performance of the system is evaluated on a database of about 60, 000 images from COREL. Empirical results demonstrate improved performance compared with a typical CBIR system using the same image similarity measure. In addition, preliminary results on images returned by Google's Image Search reveal the potential of applying CLUE to real world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.

this paper we establish some limitation on the class of non model-based recognition schemes. A non model-based scheme is based on functions invariant to viewing position and illumination conditions. We show that every function that is invariant to viewing position of all objects is the trivial (constant) function. The same result holds even if the recognition function is not required to be perfect, but is allowed to make mistakes and misidentify each object from a substantial fraction of viewing directions. It follows that every consistent recognition scheme for recognizing 3-D objects must in general be model based

Accessing large image databases requires effective indexing in order to restrict the number of database items that have to be processed. Indexing based on shapes is particularly challenging owing to the difficulty of deriving a similarity measure that supports clustering of shapes conforming with human perceptual similarity. Most previous techniques are based on the extraction of salient shape features and their organization into multi-dimensional point access structures. However, these features are extracted by analyzing shapes at a single resolution scale, and are not able to provide a robust representation. In this paper, we present a technique which exploits multi-scale analysis of shapes, to derive a hierarchical shape representation in which shape details are progressively filtered out while shape characterizing elements are preserved. A graph structure is introduced to represent shape parts at different scales and a procedure is defined to merge graphs of different shapes. Given a query shape, the graph can be traversed to select, through a coarse to fine matching, those database shapes which share similar structural parts with the query. # 1999 Elsevier Science B.V. All rights reserved.

We address the problem of texture segmentation by using a novel affine invariant model. The introduction of affine invariance as a requirement for texture analysis goes beyond what is known of the human performance and also beyond the psychophysical theories. We propose to compute texture features using affine invariant intrinsic neighborhoods and affine invariant intrinsic orientation matrices. We discuss several possibilities for the definition of the channels and give comparative experimental results where an affine invariant Mumford-Shah type energy functional is used to compute the multichannel affine invariant segmentation. We prove that the method is able to retrieve faithfully the texture regions and to recover the shape from texture information in images where several textures are present. The numerical algorithm is multiscale.