By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 11 • Date Nov. 2004

Filter Results

Displaying Results 1 - 17 of 17
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (128 KB)  
    Freely Available from IEEE
  • [Inside front cover]

    Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (75 KB)  
    Freely Available from IEEE
  • Introduction of new Associate Editors

    Page(s): 1393 - 1394
    Save to Project icon | Request Permissions | PDF file iconPDF (153 KB)  
    Freely Available from IEEE
  • Convolutional face finder: a neural architecture for fast and robust face detection

    Page(s): 1408 - 1423
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1739 KB) |  | HTML iconHTML  

    In this paper, we present a novel face detection approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns, rotated up to ±20 degrees in image plane and turned up to ±60 degrees, in complex real world images. The proposed system automatically synthesizes simple problem-specific feature extractors from a training set of face and nonface patterns, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. The face detection procedure acts like a pipeline of simple convolution and subsampling modules that treat the raw input image as a whole. We therefore show that an efficient face detection system does not require any costly local preprocessing before classification of image areas. The proposed scheme provides very high detection rate with a particularly low level of false positives, demonstrated on difficult test sets, without requiring the use of multiple networks for handling difficult cases. We present extensive experimental results illustrating the efficiency of the proposed approach on difficult test sets and including an in-depth sensitivity analysis with respect to the degrees of variability of the face patterns. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings

    Page(s): 1395 - 1407
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1689 KB) |  | HTML iconHTML  

    In integrated segmentation and recognition of character strings, the underlying classifier is trained to be resistant to noncharacters. We evaluate the performance of state-of-the-art pattern classifiers of this kind. First, we build a baseline numeral string recognition system with simple but effective presegmentation. The classification scores of the candidate patterns generated by presegmentation are combined to evaluate the segmentation paths and the optimal path is found using the beam search strategy. Three neural classifiers, two discriminative density models, and two support vector classifiers are evaluated. Each classifier has some variations depending on the training strategy: maximum likelihood, discriminative learning both with and without noncharacter samples. The string recognition performances are evaluated on the numeral string images of the NIST special database 19 and the zipcode images of the CEDAR CDROM-1. The results show that noncharacter training is crucial for neural classifiers and support vector classifiers, whereas, for the discriminative density models, the regularization of parameters is important. The string recognition results compare favorably to the best ones reported in the literature though we totally ignored the geometric context. The best results were obtained using a support vector classifier, but the neural classifiers and discriminative density models show better trade-off between accuracy and computational overhead. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid genetic algorithms for feature selection

    Page(s): 1424 - 1437
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2842 KB) |  | HTML iconHTML  

    This paper proposes a novel hybrid genetic algorithm for feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of their fine-tuning power, and their effectiveness and timing requirements are analyzed and compared. The hybridization technique produces two desirable effects: a significant improvement in the final performance and the acquisition of subset-size control. The hybrid GAs showed better convergence properties compared to the classical GAs. A method of performing rigorous timing analysis was developed, in order to compare the timing requirement of the conventional and the proposed algorithms. Experiments performed with various standard data sets revealed that the proposed hybrid GA is superior to both a simple GA and sequential search algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image distortion analysis using polynomial series expansion

    Page(s): 1438 - 1451
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1321 KB) |  | HTML iconHTML  

    In this paper, we derive a technique for analysis of local distortions which affect data in real-world applications. In the paper, we focus on image data, specifically handwritten characters. Given a reference image and a distorted copy of it, the method is able to efficiently determine the rotations, translations, scaling, and any other distortions that have been applied. Because the method is robust, it is also able to estimate distortions for two unrelated images, thus determining the distortions that would be required to cause the two images to resemble each other. The approach is based on a polynomial series expansion using matrix powers of linear transformation matrices. The technique has applications in pattern recognition in the presence of distortions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical region merging

    Page(s): 1452 - 1458
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2805 KB) |  | HTML iconHTML  

    This paper explores a statistical basis for a process often described in computer vision: image segmentation by region merging following a particular order in the choice of regions. We exhibit a particular blend of algorithmics and statistics whose segmentation error is, as we show, limited from both the qualitative and quantitative standpoints. This approach can be efficiently approximated in linear time/space, leading to a fast segmentation algorithm tailored to processing images described using most common numerical pixel attribute spaces. The conceptual simplicity of the approach makes it simple to modify and cope with hard noise corruption, handle occlusion, authorize the control of the segmentation scale, and process unconventional data such as spherical images. Experiments on gray-level and color images, obtained with a short readily available C-code, display the quality of the segmentations obtained. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust adaptive-scale parametric model estimation for computer vision

    Page(s): 1459 - 1474
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1772 KB) |  | HTML iconHTML  

    Robust model fitting essentially requires the application of two estimators. The first is an estimator for the values of the model parameters. The second is an estimator for the scale of the noise in the (inlier) data. Indeed, we propose two novel robust techniques: the two-step scale estimator (TSSE) and the adaptive scale sample consensus (ASSC) estimator. TSSE applies nonparametric density estimation and density gradient estimation techniques, to robustly estimate the scale of the inliers. The ASSC estimator combines random sample consensus (RANSAC) and TSSE, using a modified objective function that depends upon both the number of inliers and the corresponding scale. ASSC is very robust to discontinuous signals and data with multiple structures, being able to tolerate more than 80 percent outliers. The main advantage of ASSC over RANSAC is that prior knowledge about the scale of inliers is not needed. ASSC can simultaneously estimate the parameters of a model and the scale of the inliers belonging to that model. Experiments on synthetic data show that ASSC has better robustness to heavily corrupted data than least median squares (LMedS), residual consensus (RESC), and adaptive least Kth order squares (ALKS). We also apply ASSC to two fundamental computer vision tasks: range image segmentation and robust fundamental matrix estimation. Experiments show very promising results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to detect objects in images via a sparse, part-based representation

    Page(s): 1475 - 1490
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2538 KB) |  | HTML iconHTML  

    We study the problem of detecting objects in still, gray-scale images. Our primary focus is the development of a learning-based approach to the problem that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in the previous work. A secondary focus of this paper is to highlight these issues, and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effective multiresolution arc segmentation: algorithms and performance evaluation

    Page(s): 1491 - 1506
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2255 KB) |  | HTML iconHTML  

    Arc segmentation plays an important role in the process of graphics recognition from scanned images. The GREC arc segmentation contest shows that there is a lot of room for improvement in this area. This paper proposes a multiresolution arc segmentation method based on our previous seeded circular tracking algorithm which largely depends on the OOPSV model. The newly-introduced multiresolution paradigm can handle arcs/circles with large radii well. We describe new approaches for arc seed detection, arc localization, and arc verification, making the proposed method self-contained and more efficient. Moreover, this paper also brings major improvement to the dynamic adjustment algorithm of circular tracking to make it more robust. A systematic performance evaluation of the proposed method has been conducted using the third-party evaluation tool and test images obtained from the GREC arc segmentation contests. The overall performance over various arc angles, arc lengths, line thickness, noises, arc-arc intersections, and arc-line intersections has been measured. The experimental results and time complexity analyses on real scanned images are also reported and compared with other approaches. The evaluation result demonstrates the stable performance and the significant improvement on processing large arcs/circles of the MAS method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible similarity measure for 3D shapes recognition

    Page(s): 1507 - 1520
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1572 KB) |  | HTML iconHTML  

    This paper is devoted to presenting a new strategy for 3D objects recognition using a flexible similarity measure based on the recent modeling wave (MW) topology in spherical models. MW topology allows us to establish an n-connectivity relationship in 3D objects modeling meshes. Using the complete object model, a study on considering different partial information of the model has been carried out to recognize an object. For this, we have introduced a new feature called cone-curvature (CC), which originates from the MW concept. CC gives an extended geometrical surroundings knowledge for every node of the mesh model and allows us to define a robust and adaptable similarity measure between objects for a specific model database. The defined similarity metric has been successfully tested in our lab using range data of a wide variety of 3D shapes. Finally, we show the applicability of our method presenting experimentation for recognition on noise and occlusion conditions in complex scenes. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A POCS-based graph matching algorithm

    Page(s): 1526 - 1530
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (285 KB) |  | HTML iconHTML  

    A novel projections onto convex sets (POCS) graph matching algorithm is presented. Two-way assignment constraints are enforced without using elaborate penalty terms, graduated nonconvexity, or sophisticated annealing mechanisms to escape from poor local minima. Results indicate that the presented algorithm is robust and compares favorably to other well-known algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth estimation and image restoration using defocused stereo pairs

    Page(s): 1521 - 1525
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (458 KB) |  | HTML iconHTML  

    We propose a method for estimating depth from images captured with a real aperture camera by fusing defocus and stereo cues. The idea is to use stereo-based constraints in conjunction with defocusing to obtain improved estimates of depth over those of stereo or defocus alone. The depth map as well as the original image of the scene are modeled as Markov random fields with a smoothness prior, and their estimates are obtained by minimizing a suitable energy function using simulated annealing. The main advantage of the proposed method, despite being computationally less efficient than the standard stereo or DFD method, is simultaneous recovery of depth as well as space-variant restoration of the original focused image of the scene. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contour-based object tracking with occlusion handling in video acquired using mobile cameras

    Page(s): 1531 - 1536
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (645 KB) |  | HTML iconHTML  

    We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame to frame by minimizing some energy functional evaluated in the contour vicinity defined by a band. Our approach has two major components related to the visual features and the object shape. Visual features (color, texture) are modeled by semiparametric models and are fused using independent opinion polling. Shape priors consist of shape level sets and are used to recover the missing object regions during occlusion. We demonstrate the performance of our method in real sequences with and without object occlusions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Inside back cover]

    Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (75 KB)  
    Freely Available from IEEE
  • TPAMI Information for authors

    Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (128 KB)  
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois