Shape-based word recognition

We describe a process of word recognition that has high tolerance for poor image quality, tunability to the lexical content of the documents to which it is applied, and high speed of operation. This process relies on the transformation of text images into character shape codes, and on special lexica that contain information on the shape of words. We rely on the structure of English and the high efficiency of mapping between shape codes and the characters in the words. Remaining ambiguity is reduced by template matching using exemplars derived from surrounding text, taking advantage of the local consistency of font, face and size as well as image quality. This paper describes the effects of lexical content, structure and processing on the performance of a word recognition engine. Word recognition performance is shown to be enhanced by the application of an appropriate lexicon. Recognition speed is shown to be essentially independent of the details of lexical content provided the intersection of the occurrences of words in the document and the lexicon is high. Word recognition accuracy is dependent on both intersection and specificity of the lexicon. Received May 1, 1998 / Revised October 20, 1998     

Shape-based retrieval of video objects

The increasing availability of object-based video content requires new technologies for automatically extracting and matching of the low level features of arbitrarily shaped video. This paper proposes methods for shape retrieval of arbitrarily shaped video objects. Our methods take into account not only the still shape features but also the shape deformations that may occur in an object's lifespan. We compute the shape similarity of video objects by comparing the similarity of their representative temporal instances. We also describe motion of a video object via describing the deformations in an object's shape. Experimental results show that our proposed methods offer very good retrieval performance and match closely with the human ranking.     

Shape-based interpolation

Extensions to a shape-based interpolation method in which pixels that share a boundary edge (one inside and the other outside the object) are considered to be at a distance between adjacent pixel centers are proposed. Using such an initialization for distance calculations, a generalization of the chamfer distance calculation is developed. The generalization allows the simultaneous calculation of distances within the object and its background by two consecutive chamfering processes. The performances of a number of variants of the methods are evaluated. It is shown that the shape-based interpolation using a near-optimal 3×3 distance and modified cubic spline between-slice interpolation has superior properties to previously proposed methods for estimating object locations in missing slices in tomographic radiology     

Evidence-based recognition of 3-D objects

An evidence-based recognition technique is defined that identifies 3-D objects by looking for their notable features. This technique makes use of an evidence rule base, which is a set of salient or evidence conditions with corresponding evidence weights for various objects in the database. A measure of similarity between the set of observed features and the set of evidence conditions for a given object in the database is used to determine the identity of an object in the scene or reject the object(s) in the scene as unknown. This procedure has polynomial time complexity and correctly identifies a variety of objects in both synthetic and real range images. A technique for automatically deriving the evidence rule base from training views of objects is shown to generate evidence conditions that successfully identify new views of those objects     

On the recognition of curved objects

The problem of determining the identity and pose of occluded objects from noisy data is examined. Previous work has shown that local measurements of the position and surface orientation of small patches of an object's surface may be used in a constrained search process to solve this problem, for the case of rigid polygonal objects using 2-D sensory data, or rigid polyhedral objects using 3-D data. The recognition system is extended to recognize and locate curved objects. The extension is done in two dimensions, and applies to the recognition of 2-D objects from 2-D data, or to the recognition of the 3-D objects in stable positions from 2-D data     

Deformable template recognition of multiple occluded objects

Based on deformable templates, the paper formulates an integrated and flexible Bayesian recognition system of multiple occluded objects. Various local dependence properties of the model are obtained to reduce the computational cost with the increase in the number of objects. Numerical results for a synthetic image and for a real image of mushrooms are discussed     

Local association based recognition of two-dimensional objects

A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.     

Local appearance modeling for objects class recognition

Pattern Analysis and Applications - In this work, we propose a new formulation of the objects modeling combining geometry and appearance; it is useful for detection and recognition. The object...     

Reconstruction of images and recognition of polyhedral objects

An indirect way of reconstructing the coordinates of points on the surface of a 3D object by its planar parallel projections is proposed. The approach is based on the substitution of the object by another (virtual) object, for which this operation can be carried out simply, whereas the correctness of the obtained results is controlled. The specificities of obtaining a mathematical model of reconstructed objects with a polyhedral shape, the issues of normalization of the angular discrepancies between the recognized and the etalon objects, and the solution of the problem of their recognition based on the introduced model are considered.     

Hierarchical vibrations for part-based recognition of complex objects

We propose a technique for the recognition and segmentation of complex shapes in 2D images using a hierarchy of finite element vibration modes in an evolutionary shape search. The different levels of the shape hierarchy can influence each other, which can be exploited in top-down part-based image analysis. Our method overcomes drawbacks of existing structural approaches, which cannot uniformly encode shape variation and co-variation, or rely on training. We present results demonstrating that by utilizing a quality-of-fit function the model explicitly recognizes missing parts of a complex shape, thus allowing for categorization between shape classes.     

Angle densities and recognition of 3D objects

Recognition of 3D objects using computer vision is complicated by the fact that geometric features vary with view orientation. An important factor in designing recognition algorithms in such situations is understanding the variation of certain critical features such as angles. In this paper we derive the two dimensional joint density function of two angles in a scene given an isotropic view orientation and an orthographic projection. The analytic expression for the densities are useful in determining statistical decision rules to recognize surfaces and objects. Experiments to evaluate the usefulness of the proposed methods are reported     

Edge replacement in the recognition of occluded objects

The Generalized Hough Transform recognizes objects more successfully when all edges are visible. To facilitate recognition, this paper introduces a preliminary Generalized Hough process that restores edges which were invisible because of occlusion or because of lack of contrast between occluding and occluded areas. Space and time complexity of Generalized Hough processes are reduced by chained hashing techniques. Experimental results show that recognition of occluded objects via a Generalized Hough Transform is improved if occluding objects are first recognized and subtracted out of the input picture, and occluded edges are then reconstructed prior to recognition of occluded objects.     

On the recognition of parameterized 2D objects

Determining the identity and pose of oceluded objects from noisy data is a critical step in interacting intelligently with an unstructured environment. Previous work has shown that local measurements of position and surface orientation may be used in a constrained search process to solve this problem, for the case of rigid objects, either two-dimensional or three-dimensional. This paper considers the more general problem of recognizing and locating objects that can vary in parameterized ways. We consider two-dimensional objects with rotational, translational, or scaling degrees of freedom, and two-dimensional objects that undergo stretching transformations. We show that the constrained search method can be extended to handle the recognition and localization of such generalized classes of object families.This report describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology. Support for the laboratory's artificial intelligence research is provided in part by an Office of Naval Research University Research Initiative grant under contract N00014-86-K-0180, in part by the Advanced Research Projects Agency of the Department of Defense under Army contract number DACA76-85-C-0010, and in part by DARPA under. Office of Naval Research contract N00014-85-K-0124. A preliminary version of this work appeared in the proceedings of the First International Conference on Computer Vision, London, England, 1987.     

Shape-based Invariant Texture Indexing

This paper introduces a new texture analysis scheme, which is invariant to local geometric and radiometric changes. The proposed methodology relies on the topographic map of images, obtained from the connected components of level sets. This morphological tool, providing a multi-scale and contrast-invariant representation of images, is shown to be well suited to texture analysis. We first make use of invariant moments to extract geometrical information from the topographic map. This yields features that are invariant to local similarities or local affine transformations. These features are invariant to any local contrast change. We then relax this invariance by computing additional features that are invariant to local affine contrast changes and investigate the resulting analysis scheme by performing classification and retrieval experiments on three texture databases. The obtained experimental results outperform the current state of the art in locally invariant texture analysis.     

Main objects interaction activity recognition in real images

Automatically describing the image caption is a challenging task in computer vision. The difficulty mainly lies in capturing the interesting objects and recognizing the interaction activity of the interesting objects. In this paper, we introduce “centerpiece interaction,” a complex visual composite, to represent the main objects interaction activity. We propose a centerpiece interaction recognition framework to achieve the detection of interesting objects and the recognition of their interaction activity by regarding them as an integrated task. In our framework, firstly, a graph-based model is proposed to learn the 2.5D spatial co-occurrence context among objects, which strongly facilitates the interesting objects detection. Secondly, we propose a hierarchical model, with the help of 2.5D spatial co-occurrence context obtained, to learn the relational features of the interesting objects in a hierarchy of stages by integrating the features of the interesting objects, which significantly improve the recognition of centerpiece interaction. Experiments on a joint dataset show that our framework outperforms state-of-the-art in spatial co-occurrence context analysis, the interesting objects detection and the centerpiece interaction recognition.     

基于能量图像的目标识别方法

提出了一种基于AdaBoost算法,利用能量图像进行目标分类的算法.该算法通过灰度图像创建能量图像,并将能量图像作为样本进行机器的集中学习,实现对骑车人、行人和车辆目标的分类识别.根据待检测目标的能量分布,构建了能描述目标的典型特征,并以检测区域的能量差异作为其特征值.重点讨论了骑车人和行人的分类识别问题.实验结果表明,所提出方法对本课题中的特定目标具有较好的识别率,并具有较强的鲁棒性.     

Automated recognition of urban objects for morphological urban analysis

It has often been suggested that the physical structure of traditional urban settlements represents a time-tested response to the climatic constraints of a given location, particularly in hot-arid or other regions that are characterized by thermally harsh conditions. To test this premise, vernacular urban forms have been analyzed to identify patterns of built morphology which might have developed as a response to prevailing climatic conditions. This approach is often based on visual analysis and subjective and qualitative recognition of climate-related patterns.