Showing papers on "Orientation (computer vision) published in 2004"

Catheterscope 3D Guidance and Interface System

Abstract: Visual-assisted guidance of an ultra-thin flexible endoscope to a predetermined region of interest within a lung during a bronchoscopy procedure. The region may be an opacity-identified by non-invasive imaging methods, such as high-resolution computed tomography (HRCT) or as a malignant lung mass that was diagnosed in a previous examination. An embedded position sensor on the flexible endoscope indicates the position of the distal tip of the probe in a Cartesian coordinate system during the procedure. A visual display is continually updated, showing the present position and orientation of the marker in a 3-D graphical airway model generated from image reconstruction. The visual display also includes windows depicting a virtual fly-through perspective and real-time video images acquired at the head of the endoscope, which can be stored as data, with an audio or textual account.

Design of steerable filters for feature detection using canny-like criteria

Abstract: We propose a general approach for the design of 2D feature detectors from a class of steerable functions based on the optimization of a Canny-like criterion. In contrast with previous computational designs, our approach is truly 2D and provides filters that have closed-form expressions. It also yields operators that have a better orientation selectivity than the classical gradient or Hessian-based detectors. We illustrate the method with the design of operators for edge and ridge detection. We present some experimental results that demonstrate the performance improvement of these new feature detectors. We propose computationally efficient local optimization algorithms for the estimation of feature orientation. We also introduce the notion of shape-adaptable feature detection and use it for the detection of image corners.

Learning object detection from a small number of examples: the importance of good features

Abstract: Face detection systems have recently achieved high detection rates and real-time performance. However, these methods usually rely on a huge training database (around 5,000 positive examples for good performance). While such huge databases may be feasible for building a system that detects a single object, it is obviously problematic for scenarios where multiple objects (or multiple views of a single object) need to be detected. Indeed, even for multi-viewface detection the performance of existing systems is far from satisfactory. In this work we focus on the problem of learning to detect objects from a small training database. We show that performance depends crucially on the features that are used to represent the objects. Specifically, we show that using local edge orientation histograms (EOH) as features can significantly improve performance compared to the standard linear features used in existing systems. For frontal faces, local orientation histograms enable state of the art performance using only a few hundred training examples. For profile view faces, local orientation histograms enable learning a system that seems to outperform the state of the art in real-time systems even with a small number of training examples.

Specular reflections and the perception of shape.

Abstract: Many materials, including leaves, water, plastic, and chrome exhibit specular reflections It seems reasonable that the visual system can somehow exploit specular reflections to recover three-dimensional (3D) shape Previous studies (eg, J T Todd & E Mingolla, 1983; J F Norman, J T Todd, & G A Orban, 2004) have shown that specular reflections aid shape estimation, but the relevant image information has not yet been isolated Here we explain how specular reflections can provide reliable and accurate constraints on 3D shape We argue that the visual system can treat specularities somewhat like textures, by using the systematic patterns of distortion across the image of a specular surface to recover 3D shape However, there is a crucial difference between textures and specularities: In the case of textures, the image compressions depend on the first derivative of the surface depth (ie, surface orientation), whereas in the case of specularities, the image compressions depend on the second derivative (ie, surfaces curvatures) We suggest that this difference provides a cue that can help the visual system distinguish between textures and specularities, even when present simultaneously More importantly, we show that the dependency of specular distortions on the second derivative of the surface leads to distinctive fields of image orientation as the reflected world is warped across the surface We find that these "orientation fields" are (i) diagnostic of 3D shape, (ii) remain surprisingly stable when the world reflected in the surface is changed, and (iii) can be extracted from the image by populations of simple oriented filters Thus the use of specular reflections for 3D shape perception is both easier and more reliable than previous computational work would suggest

Light-emitting stylus and user input device using same

Abstract: The present invention provides a user input device that includes and array of light detectors and a light emitting stylus configured to emit a beam of light detectable by the light detectors. The light beam is wide enough at the plane of the detectors so that at least two detectors are illuminated for all positions of interest. This allows the light beam position to be interpolated to obtain positional resolution that is greater than would be expected simply due to the spacing between detectors. Interpolation can be further aided by using a light beam that has a known variance in cross-sectional intensity. The present invention also provides for determining the orientation of the stylus by comparing the detected shape of the light beam cross-section to the known shape of the light beam cross-section.

Image Analysis of Defocused Single-Molecule Images for Three-Dimensional Molecule Orientation Studies

Abstract: An efficient algorithm for pattern matching has been developed based on least-squares analysis of fitting a discrete set of master patterns against measured images. This algorithm has been applied to determine three-dimensional molecule orientations in defocused single-molecule images. The developed algorithm exploits the excellent agreement between electrodynamic calculations of single-molecule emission and experimentally measured images. The procedure is found to be reliable and simple and can be applied to any kind of pattern recognition where the patterns to be recognized are precisely known a priori. The procedure works well even for noisy and low-intensity signals as usually encountered in single-molecule experiments.

Color and texture image retrieval using chromaticity histograms and wavelet frames

Abstract: In this paper, we explore image retrieval mechanisms based on a combination of texture and color features. Texture features are extracted using Discrete Wavelet Frames (DWF) analysis, an over-complete decomposition in scale and orientation. Two-dimensional (2-D) or one-dimensional (1-D) histograms of the CIE Lab chromaticity coordinates are used as color features. The 1-D histograms of the a, b coordinates were modeled according to the generalized Gaussian distribution. The similarity measure defined on the feature distribution is based on the Bhattacharya distance. Retrieval benchmarking is performed over the Brodatz album and on images from natural scenes, obtained from the VisTex database of MIT Media Laboratory and from the Corel Photo Gallery. As a performance indicator recall (relative number of correct images retrieved) is measured on both texture and color separately and in combination. Experiments show this approach to be as effective as other methods while computationally more tractable.

Mobile terminal with ergonomic imaging functions

Abstract: The present invention provides for a mobile terminal (100, 300, 400) with ergonomic imaging or camera functions. A single display (104, 302, 404) can be used, for example in portrait mode while terminal functions are being used and in landscape mode while imaging functions are being used. The change between the two orientations can be accomplished automatically (206, 210, 214). In some embodiments, the capability is also provided to process an image for assignment to a terminal function (508, 518), where the image has at least one display attribute that makes it at least partly unsuitable for use with the terminal function. This processing can be accomplished for example, so that a landscape image can be viewed conveniently in a portrait orientation.

Disambiguating Visual Motion Through Contextual Feedback Modulation

Abstract: Motion of an extended boundary can be measured locally by neurons only orthogonal to its orientation (aperture problem) while this ambiguity is resolved for localized image features, such as corners or nonocclusion junctions. The integration of local motion signals sampled along the outline of a moving form reveals the object velocity. We propose a new model of V1-MT feedforward and feedback processing in which localized V1 motion signals are integrated along the feedforward path by model MT cells. Top-down feedback from MT cells in turn emphasizes model V1 motion activities of matching velocity by excitatory modulation and thus realizes an attentional gating mechanism. The model dynamics implement a guided filling-in process to disambiguate motion signals through biased on-center, off-surround competition. Our model makes predictions concerning the time course of cells in area MT and V1 and the disambiguation process of activity patterns in these areas and serves as a means to link physiological mechanisms with perceptual behavior. We further demonstrate that our model also successfully processes natural image sequences.

Optical image-based position tracking for magnetic resonance imaging applications

Abstract: An optical image-based tracking system determines the position and orientation of objects such as biological materials or medical devices within or on the surface of a human body undergoing Magnetic Resonance Imaging (MRI). Three-dimensional coordinates of the object to be tracked are obtained initially using a plurality of MR-compatible cameras. A calibration procedure converts the motion information obtained with the optical tracking system coordinates into coordinates of an MR system. A motion information file is acquired for each MRI scan, and each file is then converted into coordinates of the MRI system using a registration transformation. Each converted motion information file can be used to realign, correct, or otherwise augment its corresponding single MR image or a time series of such MR images. In a preferred embodiment, the invention provides real-time computer control to track the position of an interventional treatment system, including surgical tools and tissue manipulators, devices for in vivo delivery of drugs, angioplasty devices, biopsy and sampling devices, devices for delivery of RF, thermal energy, microwaves, laser energy or ionizing radiation, and internal illumination and imaging devices, such as catheters, endoscopes, laparoscopes, and like instruments. In other embodiments, the invention is also useful for conventional clinical MRI events, functional MRI studies, and registration of image data acquired using multiple modalities.

Capture of hair geometry from multiple images

Abstract: Hair is a major feature of digital characters. Unfortunately, it has a complex geometry which challenges standard modeling tools. Some dedicated techniques exist, but creating a realistic hairstyle still takes hours. Complementary to user-driven methods, we here propose an image-based approach to capture the geometry of hair.The novelty of this work is that we draw information from the scattering properties of the hair that are normally considered a hindrance. To do so, we analyze image sequences from a fixed camera with a moving light source. We first introduce a novel method to compute the image orientation of the hairs from their anisotropic behavior. This method is proven to subsume and extend existing work while improving accuracy. This image orientation is then raised into a 3D orientation by analyzing the light reflected by the hair fibers. This part relies on minimal assumptions that have been proven correct in previous work.Finally, we show how to use several such image sequences to reconstruct the complete hair geometry of a real person. Results are shown to illustrate the fidelity of the captured geometry to the original hair. This technique paves the way for a new approach to digital hair generation.

Calibration of a surveying instrument

Abstract: A method for calibrating a surveying instrument is disclosed the survey instrument comprising a base element (3) and a camera with an image sensor (10), the camera being rotatable about a vertical axis (2) fixed with respect to said base element and being rotatable about a tilting axis (4), the tilting axis being rotated about the vertical axis with rotation of the camera about the vertical axis, In the method, data associated with calibration points (P) and images (P1) of the calibration points on the image sensor captured in different faces are used, the data for each of said calibration points comprising distance data and the data for each of the images of each said calibration point comprising image position data and orientation data. Further, on the basis of the distance data for each of the calibration points and the image position and orientation data for each of the images of the calibration points the surveying instrument is calibrated simultaneously taking into account at least one optical property of camera and at least one of the relative orientation of the vertical axis and the tilting axis and the orientation of the camera relative to one of the base element, the vertical axis and the tilting axis.

Fingerprint image quality analysis

Abstract: Fingerprint image quality analysis is crucial in eliminating poor fingerprint images, which will affect the performance of the automatic fingerprint identification system. In this article, two types of new quality measures will be introduced: ridge and valley clarity and global orientation flow to calculate the overall image quality score that can be used to quantitatively determine the quality of the fingerprint image. In order to evaluate the performance of the proposed algorithm, the quality measure is used to rank the performance of a fingerprint recognition system and the ranking is compared with the quality measure rated manually. The result shows that the proposed scheme will return a score that ensures its reliability to indicate the quality of a given fingerprint image.

Apparatus, method, and medium for controlling image orientation

Abstract: An apparatus, method, and medium for controlling image orientation are disclosed. An orientation mode detector measures multi-directional rotational angles of a display panel and determines an orientation mode for original image data based on the measured rotational angles. A system memory stores orientation parameters corresponding to a plurality of image orientation modes. A system controller initially acquires information indicating the orientation mode from the orientation mode detector, and it extracts orientation parameters corresponding to the acquired information from the system memory. Finally, a driver changes an orientation of the original image data according to the extracted orientation parameters.

Context-dependent perceptual ranges and their relevance to animal movements in landscapes

Abstract: Summary 1. An animal’s perceptual range defines the spatial extent of the landscape for which information is available to make movement decisions. Ecologists studying and modelling animal dispersal have commonly assumed that individual movements arise from a predefined set of local decision rules operating within a static isotropic (i.e. circular) perceptual range. 2. We discuss how this assumption fails to recognize the potential for plasticity in perceptual ranges and present a conceptual model that illustrates how anisotropic perceptual ranges can arise from animal orientation to environmental stimuli. 3. Using model simulations we show how perceptual distance (i.e. greatest Euclidean distance at which habitat patches can be perceived), horizon (i.e. panoramic view or angular degrees of the landscape perceived) and breadth (i.e. areal extent of the landscape perceived), change as a function of increased strength of a hypothetical stimuli. 4. Our results show that anisotropic perceptual ranges can differ substantially from traditional, isotropic perceptual ranges in all three aspects depending on the strength of the stimuli and nature in which it interacts with other elements of the landscape. 5. We highlight the implications of these findings for modelling animal movements in ecological landscapes with the hope that context-dependent perceptual ranges are considered in future studies.

Salient region detection using weighted feature maps based on the human visual attention model

Abstract: Detection of salient regions in images is useful for object based image retrieval and browsing applications. This task can be done using methods based on the human visual attention model [1], where feature maps corresponding to color, intensity and orientation capture the corresponding salient regions. In this paper, we propose a strategy for combining the salient regions from the individual feature maps based on a new Composite Saliency Indicator (CSI) which measures the contribution of each feature map to saliency. The method also carries out a dynamic weighting of individual feature maps. The experiment results indicate that this combination strategy reflects the salient regions in an image more accurately.

The use of force histograms for affine-invariant relative position description

Abstract: Affine invariant descriptors have been widely used for recognition of objects regardless of their position, size, and orientation in space. Examples of color, texture, and shape descriptors abound in the literature. However, many tasks in computer vision require looking not only at single objects or regions in images but also at their spatial relationships. In an earlier work, we showed that the relative position of two objects can be quantitatively described by a histogram of forces. Here, we study how affine transformations affect this descriptor. The position of an object with respect to another changes when the objects are affine transformed. We analyze the link between: 1) the applied affinity, 2) the relative position before transformation (described through a force histogram), and 3) the relative position after transformation. We show that any two of these elements allow the third one to be recovered. Moreover, it is possible to determine whether (or how well) two relative positions are actually related through an affine transformation. If they are not, the affinity that best approximates the unknown transformation can be retrieved, and the quality of the approximation assessed.

Image processing device and method

Abstract: An image processing device and method automatically enable proper screen display orientation when using a portable device. The image processing device includes an image input unit for acquiring an image of an image of a subject, a face area detector for detecting the face area of the subject in the obtained image, a rotation direction judging unit for judging a relative rotation direction and angle of a face with respect to a device depending on the vertical direction of the detected face area, and a screen controller for rotating an image to be displayed according to the rotation direction of the corresponding image and for displaying the image to be displayed.

An Integrative Neural Network for Detecting Inertial Motion and Head Orientation

Abstract: The ability to navigate in the world and execute appropriate behavioral responses depends critically on the contribution of the vestibular system to the detection of motion and spatial orientation. A complicating factor is that otolith afferents equivalently encode inertial and gravitational accelerations. Recent studies have demonstrated that the brain can resolve this sensory ambiguity by combining signals from both the otoliths and semicircular canal sensors, although it remains unknown how the brain integrates these sensory contributions to perform the nonlinear vector computations required to accurately detect head movement in space. Here, we illustrate how a physiologically relevant, nonlinear integrative neural network could be used to perform the required computations for inertial motion detection along the interaural head axis. The proposed model not only can simulate recent behavioral observations, including a translational vestibuloocular reflex driven by the semicircular canals, but also accounts for several previously unexplained characteristics of central neural responses such as complex otolith-canal convergence patterns and the prevalence of dynamically processed otolith signals. A key model prediction, implied by the required computations for tilt-translation discrimination, is a coordinate transformation of canal signals from a head-fixed to a spatial reference frame. As a result, cell responses may reflect canal signal contributions that cannot be easily detected or distinguished from otolith signals. New experimental protocols are proposed to characterize these cells and identify their contributions to spatial motion estimation. The proposed theoretical framework makes an essential first link between the computations for inertial acceleration detection derived from the physical laws of motion and the neural response properties predicted in a physiologically realistic network implementation.

Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes

Abstract: Local feature approaches to vision geometry and object recognition are based on selecting and matching sparse sets of visually salient image points, known as 'keypoints' or 'points of interest'. Their performance depends critically on the accuracy and reliability with which corresponding keypoints can be found in subsequent images. Among the many existing keypoint selection criteria, the popular Forstner-Harris approach explicitly targets geometric stability, defining keypoints to be points that have locally maximal self-matching precision under translational least squares template matching. However, many applications require stability in orientation and scale as well as in position. Detecting translational key- points and verifying orientation/scale behaviour post hoc is suboptimal, and can be misleading when different motion variables interact. We give a more principled formulation, based on extending the Forstner-Harris approach to general motion models and robust template matching. We also incorporate a simple local appear- ance model to ensure good resistance to the most common illumination variations. We illustrate the resulting methods and quantify their performance on test images.

Method and device for visualizing computer-generated informations

Abstract: To improve the operation of robots in installations reprogramming and emptying an operating sequence to be performed by them, the invention provides a method and a device for visualizing computer-assisted information in an image of the real environment on a viewing device, in which there is a determination of the position and orientation or pose of the image receiving device and that robot-specific informations corresponding to this determination are faded over the image of the real environment on the viewing device.

Information processing apparatus, method, storage medium and program

Abstract: In retrieval of a registered image that resembles an input image, retrieval is performed accurately in a short period of time irrespective of orientation of the input image. Specifically, there is disclosed an information processing method for retrieving image data, which has a high degree of similarity to input image data, from registered image data, the method includes an area identification step (S 402 ) of identifying a text area and a non-text area in the input image data; a direction identification step (S 404 ) of recognizing text in the identified text area and identifying orientation of the input image data based upon orientation of the text recognized; a rotation step (S 406 ) of rotating the identified input image data to a prescribed orientation based upon the orientation identified; and a retrieval step (S 409 ) of retrieving image data, which has a high degree of similarity to the input image data after the rotation thereof, from the registered image data.

Configuration analysis of five-axis machine tools using a generic kinematic model

Abstract: Five-axis machine tools are designed in a large variety of kinematic configurations and structures. Regardless of the type of the intended analysis, a kinematic model of the machine tool has to be developed in order to determine the translational and rotational joint movements required to achieve a specified position and orientation of the cutting tool relative to the workpiece. A generic and unified model is developed in this study as a viable alternative to the particular solutions that are only applicable to individual machine configurations. This versatile model is then used to verify the feasibility of the two rotational joints within the kinematic chain of three main types of five-axis machine tools: the spindle rotating, rotary table, and hybrid type. A numerical measure of total translational joint movement is proposed to evaluate the kinematic performance of a five-axis machine tool. The corresponding kinematic analyses have confirmed the advantages of the popular machine design that employs intersecting rotational axes and the common industrial practice during setup that minimizes the characteristic rotating arm length of the cutting tool and/or workpiece.

A TV Flow Based Local Scale Measure for Texture Discrimination

Abstract: We introduce a technique for measuring local scale, based on a special property of the so-called total variational (TV) flow. For TV flow, pixels change their value with a speed that is inversely proportional to the size of the region they belong to. Exploiting this property directly leads to a region based measure for scale that is well-suited for texture discrimination. Together with the image intensity and texture features computed from the second moment matrix, which measures the orientation of a texture, a sparse feature space of dimension 5 is obtained that covers the most important descriptors of a texture: magnitude, orientation, and scale. A demonstration of the performance of these features is given in the scope of texture segmentation.

Using clear-coded, see-through objects to manipulate virtual objects

Abstract: An object placed on an interactive display surface is detected and its position and orientation are determined in response to IR light that is reflected from an encoded marking on the object. Upon detecting the object on an interactive display surface, a software program produces a virtual entity or image visible through the object to perform a predefined function. For example, the object may appear to magnify text visible through the object, or to translate a word or phrase from one language to another, so that the translated word or phrase is visible through the object. When the object is moved, the virtual entity or image that is visible through the object may move with it, or can control the function being performed. A plurality of such objects can each display a portion of an image, and when correctly positioned, together will display the entire image, like a jigsaw puzzle.

Surface Reconstruction of Noisy and Defective Data Sets

Abstract: We present a novel surface reconstruction algorithm that can recover high-quality surfaces from noisy and defective data sets without any normal or orientation information. A set of new techniques are introduced to afford extra noise tolerability, robust orientation alignment, reliable outlier removal, and satisfactory feature recovery. In our algorithm, sample points are first organized by an octree. The points are then clustered into a set of monolithically singly-oriented groups. The inside/outside orientation of each group is determined through a robust voting algorithm. We locally fit an implicit quadric surface in each octree cell. The locally fitted implicit surfaces are then blended to produce a signed distance field using the modified Shepardýs method. We develop sophisticated iterative fitting algorithms to afford improved noise tolerance both in topology recognition and geometry accuracy. Furthermore, this iterative fitting algorithm, coupled with a local model selection scheme, provides a reliable sharp feature recovery mechanism even in the presence of bad input.

Interactive system and method

Abstract: An interactive system for interacting with a device in a mixed reality environment, the system comprising an object having at least two surfaces, each surface having a marker, an image capturing device to capture images of the object in a first scene, and a microprocessor configured to track the position and orientation of the object in the first scene by identifying a marker. In addition, the microprocessor is configured to respond to manipulation of the object causes the device to perform an associated operation.