Showing papers on "3D single-object recognition published in 2001"

The quotient image: class-based re-rendering and recognition with varying illuminations

Abstract: The paper addresses the problem of "class-based" image-based recognition and rendering with varying illumination. The rendering problem is defined as follows: Given a single input image of an object and a sample of images with varying illumination conditions of other objects of the same general class, re-render the input image to simulate new illumination conditions. The class-based recognition problem is similarly defined: Given a single image of an object in a database of images of other objects, some of them multiply sampled under varying illumination, identify (match) any novel image of that object under varying illumination with the single image of that object in the database. We focus on Lambertian surface classes and, in particular, the class of human faces. The key result in our approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. We show that a small database of objects-in our experiments as few as two objects-is sufficient for generating the image space with varying illumination of any new object of the class from a single input image of that object. In many cases, the recognition results outperform by far conventional methods and the re-rendering is of remarkable quality considering the size of the database of example images and the mild preprocess required for making the algorithm work.

Local feature view clustering for 3D object recognition

Abstract: There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to individual training images. This paper presents a method for combining multiple images of a 3D object into a single model representation. This provides for recognition of 3D objects from any viewpoint, the generalization of models to non-rigid changes, and improved robustness through the combination of features acquired under a range of imaging conditions. The decision of whether to cluster a training image into an existing view representation or to treat it as a new view is based on the geometric accuracy of the match to previous model views. A new probabilistic model is developed to reduce the false positive matches that would otherwise arise due to loosened geometric constraints on matching 3D and non-rigid models. A system has been developed based on these approaches that is able to robustly recognize 3D objects in cluttered natural images in sub-second times.

3D object recognition from range images using local feature histograms

Abstract: The paper explores a view-based approach to recognize free-form objects in range images We are using a set of local features that are easy to calculate and robust to partial occlusions By combining those features in a multidimensional histogram, we can obtain highly discriminant classifiers without the need for segmentation Recognition is performed using either histogram matching or a probabilistic recognition algorithm We compare the performance of both methods in the presence of occlusions and test the system on a database of almost 2000 full-sphere views of 30 free-form objects The system achieves a recognition accuracy above 93% on ideal images, and of 89% with 20% occlusion

Generalized feature extraction for structural pattern recognition in time-series data

Abstract: Pattern recognition encompasses two fundamental tasks: description and classification. Given an object to analyze, a pattern recognition system first generates a description of it (i.e., the pattern) and then classifies the object based on that description (i.e., the recognition). Two general approaches for implementing pattern recognition systems, statistical and structural, employ different techniques for description and classification. Statistical approaches to pattern recognition use decision-theoretic concepts to discriminate among objects belonging to different groups based upon their quantitative features. Structural approaches to pattern recognition use syntactic grammars to discriminate among objects belonging to different groups based upon the arrangement of their morphological (i.e., shape-based or structural) features. Hybrid approaches to pattern recognition combine aspects of both statistical and structural pattern recognition. Structural pattern recognition systems are difficult to apply to new domains because implementation of both the description and classification tasks requires domain knowledge. Knowledge acquisition techniques necessary to obtain domain knowledge from experts are tedious and often fail to produce a complete and accurate knowledge base. Consequently, applications of structural pattern recognition have been primarily restricted to domains in which the set of useful morphological features has been established in the literature (e.g., speech recognition and character recognition) and the syntactic grammars can be composed by hand (e.g., electrocardiogram diagnosis). To overcome this limitation, a domain-independent approach to structural pattern recognition is needed that is capable of extracting morphological features and performing classification without relying on domain knowledge. A hybrid system that employs a statistical classification technique to perform discrimination based on structural features is a natural solution. While a statistical classifier is inherently domain independent, the domain knowledge necessary to support the description task can be eliminated with a set of generally-useful morphological features. Such a set of morphological features is suggested as the foundation for the development of a suite of structure detectors to perform generalized feature extraction for structural pattern recognition in time-series data. The ability of the suite of structure detectors to generate features useful for structural pattern recognition is evaluated by comparing the classification accuracies achieved when using the structure detectors versus commonly-used statistical feature extractors. Two real-world databases with markedly different characteristics and established ground truth serve as sources of data for the evaluation. The classification accuracies achieved using the features extracted by the structure detectors were consistently as good as or better than the classification accuracies achieved when using the features generated by the statistical feature extractors, thus demonstrating that the suite of structure detectors effectively performs generalized feature extraction for structural pattern recognition in time-series data.

3D object recognition using shape similiarity-based aspect graph

Abstract: We present an aspect-graph approach to 3D object recognition where the definition of an aspect is motivated by its role in the subsequent recognition step. Specifically, we measure the similarity between two views by a 2D shape metric of similarity measuring the distance between the projected segmented shapes of the 3D object. This endows the viewing sphere with a metric which is used to group similar views into aspects, and to represent each aspect by a prototype. The same shape similarity metric is then used to rate the similarity between unknown views of unknown objects and stored prototypes to identify the object and its pose. The performance of this approach on a database of 18 objects each viewed in five degree increments along the ground viewing plane is demonstrated.

Viewpoint Dependence in Visual and Haptic Object Recognition

Abstract: On the whole, people recognize objects best when they see the objects from a familiar view and worse when they see the objects from views that were previously occluded from sight. Unexpectedly, we found haptic object recognition to be viewpoint-specific as well, even though hand movements were unrestricted. This viewpoint dependence was due to the hands preferring the back "view" of the objects. Furthermore, when the sensory modalities (visual vs. haptic) differed between learning an object and recognizing it, recognition performance was best when the objects were rotated back-to-front between learning and recognition. Our data indicate that the visual system recognizes the front view of objects best, whereas the hand recognizes objects best from the back.

Car detection in low resolution aerial image

Abstract: We present a system to detect passenger cars in aerial images where cars appear as small objects. We pose this as a 3D object recognition problem to account for the variation in viewpoint and the shadow. We started from psychological tests to find important features for human detection of cars. Based on these observations, we selected the boundary of the car body, the boundary of the front windshield and the shadow as the features. Some of these features are affected by the intensity of the car and whether or not there is a shadow along it. This information is represented in the structure of the Bayesian network that we use to integrate all features. Experiments show very promising results even on some very challenging images.

On representing edge structure for model matching

Abstract: We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.

Complementary solutions to the binding problem in vision: Implications for shape perception and object recognition

Abstract: Behavioural, neural, and computational considerations suggest that the visual system may use (at least) two approaches to binding an object's features and/or parts into a coherent representation of shape: Dynamically bound (e.g., by synchrony of firing) representations of part attributes and spatial relations form a structural description of an object's shape, while units representing shape attributes at specific locations (i.e., a static binding of attributes to locations) form an analogue (image-like) representation of that shape. I will present a computational model of object recognition based on this proposal and empirical tests of the model. The model accounts for a large body of findings in human object recognition, and makes several novel and counter intuitive predictions. In brief, it predicts that visual priming for attended objects will be invariant with translation, scale, and left-right reflection, whereas priming for unattended objects will be invariant with translation and scale, but sensiti...

Object finder for photographic images

Abstract: An object finder program for detecting presence of a 3D object in a 2D image containing a 2D representation of the 3D object. The object finder uses the wavelet transform of the input 2D image for object detection. A pre-selected number of view-based detectors are trained on sample images prior to performing the detection on an unknown image. These detectors then operate on the given input image and compute a quantized wavelet transform for the entire input image. The object detection then proceeds with sampling of the quantized wavelet coefficients at different image window locations on the input image and efficient look-up of pre-computed log-likelihood tables to determine object presence. The object finder's coarse-to-fine object detection strategy coupled with exhaustive object search across different positions and scales results in an efficient and accurate object detection scheme. The object finder detects a 3D object over a wide range in angular variation (e.g., 180 degrees) through the combination of a small number of detectors each specialized to a small range within this range of angular variation.

Distortion-tolerant three-dimensional object recognition with digital holography

Abstract: We present a technique to implement three-dimensional (3-D) object recognition based on phase-shift digital holography. We use a nonlinear composite correlation filter to achieve distortion tolerance. We take advantage of the properties of holograms to make the composite filter by using one single hologram. Experiments are presented to illustrate the recognition of a 3-D object in the presence of out-of-plane rotation and longitudinal shift along the z axis.

Model-based recognition of 3D objects from single images

Abstract: In this work, we treat major problems of object recognition which have received relatively little attention lately. Among them are the loss of depth information in the projection from a 3D object to a single 2D image, and the complexity of finding feature correspondences between images. We use geometric invariants to reduce the complexity of these problems. There are no geometric invariants of a projection from 3D to 2D. However, given certain modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions can be either a particular model or a generic assumption about a class of models. Here, we use such assumptions for single-view recognition. We find algebraic relations between the invariants of a 3D model and those of its 2D image under general projective projection. These relations can be described geometrically as invariant models in a 3D invariant space, illuminated by invariant "light rays," and projected onto an invariant version of the given image. We apply the method to real images.

Similarity measures for occlusion, clutter, and illumination invariant object recognition

Abstract: Novel similarity measures for object recognition and image matching are proposed, which are inherently robust against occlusion, clutter, and nonlinear illumination changes. They can be extended to be robust to global as well as local contrast reversals. The similarity measures are based on representing the model of the object to be found and the image in which the model should be found as a set of points and associated direction vectors. They are used in an object recognition system for industrial inspection that recognizes objects under Euclidean transformations in real time.

Apparatus and method for taking dimensions of 3D object

Abstract: The present invention relates to an apparatus and method for real-time automatically taking the length, width and height of a rectangular object that is moved on a conveyor belt. The method of taking the dimensions of a 3D object, the method comprising the steps of: a) obtaining an object image having the 3D object; b) detecting all edges within a region of interest of the 3D object; c) extracting line segments from the edges of the 3D object and then extracting features of the 3D object from the line segments; and d) generating 3D models based on the features of the 3D object and taking the dimensions of the 3D object from the 3D models.

Real-time three-dimensional object recognition with multiple perspectives imaging.

Abstract: A novel system for recognizing three-dimensional (3D) objects by use of multiple perspectives imaging is proposed. A 3D object under incoherent illumination is projected into an array of two-dimensional (2D) elemental images by use of a microlens array. Each elemental 2D image corresponds to a different perspective of the 3D object. Multiple perspectives imaging based on integral photography has been used for 3D display. In this way, the whole set of 2D elemental images records 3D information about the input object. After an optical incoherent-to-coherent conversion, an optical processor is employed to perform the correlation between the input and the reference 3D objects. Use of micro-optics allows us to process the 3D information in real time and with a compact optical system. To the best of our knowledge this 3D processor is the first to apply the principle of integral photography to 3D image recognition. We present experimental results obtained with both a digital and an optical implementation of the system. We also show that the system can recognize a slightly out-of-plane rotated 3D object.

A new signature-based method for efficient 3-D object recognition

Abstract: The paper considers the problem of shape-based recognition and pose estimation of 3D free-form objects in scenes that contain occlusion and clutter. Our approach is based on a novel set of discriminating descriptors called spherical spin images, which encode the shape information conveyed by classes of distributions of surface points constructed with respect to reference points on the surface of an object. The key to this approach is the relationship that exists between the l/sub 2/ metric, which compares n-dimensional signatures in Euclidean space, and the metric of the compact space on which the class representatives (spherical spin images) are defined. The connection allows us to efficiently utilize the linear correlation coefficient to discriminate scene points which have spherical spin images that are similar to the spherical spin images of points on the object being sought. The paper also addresses the problem of compressed spherical-spin-image representation by means of a random projection of the original descriptors that reduces the dimensionality without a significant loss of recognition/localization performance. Finally, the efficacy of the proposed representation is validated in a comparative study of the two algorithms presented that use uncompressed and compressed spherical spin images versus two previous spin image algorithms reported previously (A.E. Johnson and M. Hebert, 1999). The results of 2012 experiments suggest that the performance of our proposed algorithms is significantly better with respect to accuracy and speed than the performance of the other algorithms tested.

Learning models for object recognition

Abstract: We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Hausdorff distance between the model and the new shape is small. We show that such object concepts can be seen as halfspaces (linear threshold functions) in a transformed input space. This makes it possible to use a number of standard algorithms to learn object models from training examples. When a good model exists, we are guaranteed to find one that provides (with high probability) a recognition rule that is accurate. Our approach provides a measure which generalizes the Hausdorff distance in a number of interesting ways. To demonstrate our method we trained a system to detect people in images using a single shape model. The learning techniques can be extended to represent objects using multiple model shapes. In this way, we might be able to automatically learn a small set of canonical shapes that characterize the appearance of an object.

System and method for object recognition

Abstract: A system and method recognize a user-defined model object within an image. The system and method recognize the model object with occlusion when the model object to be found is only partially visible. The system and method also recognize the model object with clutter when there may be other objects in the image, even within the model object. The system and method also recognize the model object with non-linear illumination changes as well as global or local contrast reversals. The model object to be found may have been distorted, when compared to the user-defined model object, from geometric transformations of a certain class such as translations, rigid transformations by translation and rotation, arbitrary affine transformations, as well as similarity transformations by translation, rotation, and scaling.

Neural network for three-dimensional object recognition based on digital holography

Abstract: We present a two-layer neural network for processing of three-dimensional (3D) images that are obtained by digital holography. The network is trained with a real 3D object to compute the weights of the layers. Experiments are presented to illustrate the system performance. The system is designed to detect a 3D object in the presence of various distortions. As an example, experiments are presented to illustrate how the system is able to recognize a 3D object with 360° out-of-plane rotation.

Picture recognition apparatus and method

Abstract: The variations in appearance of an object caused by the variations in a capturing environment are estimated to be modeled, and the object model thus obtained is previously registered in a database. Picture information of an object to be a recognition target is input, and the input picture information is matched with the previously registered object model. The similarity with respect to the registered object model is determined, and the type of the object to be a recognition target is output, which is determined to be most similar among the registered object models. Information of a plurality of pictures captured by changing the relative position and posture of an object is input, and the variations in appearance of an object caused by the possible variations in a capturing environment are estimated to be modeled based on the input information of a plurality of pictures.

Appearance-based object recognition using multiple views

Abstract: Object recognition from a single view fails when the available features are not sufficient to determine the identity of a single object, either because of similarity with another object or because of feature corruption due to clutter and occlusion. Active object recognition systems have addressed this problem successfully, but they require complicated systems with adjustable viewpoints that are not always available. In this paper we investigate the performance gain available by combining the results of a single view object recognition system applied to imagery obtained from multiple fixed cameras. In particular, we address performance in cluttered scenes with varying degrees of information about relative camera pose. We argue that a property common to many computer vision recognition systems, which we term a weak target error, is responsible for two interesting limitations of multi-view performance enhancement: the lack of significant improvement in systems whose single-view performance is weak, and the plateauing of performance improvement as additional multi-view constraints are added.

Locating potentially identical objects across multiple computers

Abstract: Potentially identical objects (such as files) across multiple computers are located. In one embodiment, a computer generates object information for an object stored on the computer. The object information can be generated in a variety of manners (e.g., based on hashing the object, based on characteristics of the object, and so forth). The object information is then transferred to one or more database server computers, where the object information can be compared to object information from other computers to determine whether the object is potentially identical to another object on one of the other computers.

Method and apparatus for performing relational speech recognition

Abstract: A method and apparatus for performing speech recognition using observable relationships between words. Results from a speech recognition pass can be combined with information about the observable word relationships to constrain or simplify subsequent recognition passes. This iterative process greatly reduces the search space required for each recognition pass, making the speech recognition process more efficient, faster and accurate.

Neuromorphic algorithms for computer vision and attention

Abstract: We describe an integrated vision system which reliably detects persons in static color natural scenes, or other targets among distracting objects. The system is built upon the biologically-inspired synergy between two processing stages: A fast trainable visual attention front-end (where), which rapidly selects a restricted number of conspicuous image locations, and a computationally expensive object recognition back-end (what), which determines whether the selected locations are targets of interest. We experiment with two recognition back-ends: One uses a support vector machine algorithm and achieves highly reliable recognition of pedestrians in natural scenes, but is not particularly biologically plausible, while the other is directly inspired from the neurobiology of inferotemporal cortex, but is not yet as robust with natural images. Integrating the attention and recognition algorithms yields substantial speedup over exhaustive search, while preserving detection rate. The success of this approach demonstrates that using a biological attention-based strategy to guide an object recognition system may represent an efficient strategy for rapid scene analysis.

Navigating and selecting a portion of a screen by utilizing a state of an object as viewed by a camera

Abstract: A computer system is described including a camera, a display device (e.g., a display monitor) having a display screen, and a processing system coupled to the camera and the display device. The camera produces image signals representing one or more images of an object under the control of a user. The processing system receives the image signals, and uses the image signals to determine a state of the object. The state of the object may be, for example, a position of the object, an orientation of the object, or motion of the object. Dependent upon the state of the object, the processing system controls cursor movement and selection of a selectable item at a current cursor location. The object may be a body part of the user, such as a face, a hand, or a foot. The object may also be a prominent feature of a body part, such as a nose, a corner of a mouth, a corner of an eye, a finger, a knuckle, or a toe. The object may also be an object held by, attached to, or worn by the user. The object may be selected by the user or selected automatically by the processing system. Multiple images may be chronologically ordered with respect to one another.

Facial image recognition apparatus and a pass control apparatus

Abstract: A first illumination section radiates light at a certain degree of illuminance toward the face of a human recognition object from an upper right part or an upper left part of a camera, and a second illumination section radiates light at a certain degree of illuminance toward the face of the human recognition object from a lower part of a camera. The camera photographs and inputs a facial image of the human recognition object. The image processing section extracts a feature value of the face of the human recognition object from a facial image inputted by the camera and collates the feature value extracted with a standard feature value registered in advance so as to recognize a facial image of the human recognition object.

Object recognition using shape-from-shading

Abstract: Investigates whether surface topography information extracted from intensity images using a shape-from-shading (SFS) algorithm can be used for the purposes of 3D object recognition. We consider how curvature and shape-index information delivered by this algorithm can be used to recognize objects based on their surface topography. We explore two contrasting object recognition strategies. The first of these is based on a low-level attribute summary and uses histograms of curvature and orientation measurements. The second approach is based on the structural arrangement of constant shape-index maximal patches and their associated region attributes. We show that region curvedness and a string ordering of the regions according to size provides recognition accuracy of about 96 percent. By polling various recognition schemes, including a graph matching method, we show that a recognition rate of 98-99 percent is achievable.