Requirement for a person to face a camera for face identification process may no longer be necessary if the face recognition system is robust against variation of facial pose. In this paper, we proposed a face recogni...
详细信息
Requirement for a person to face a camera for face identification process may no longer be necessary if the face recognition system is robust against variation of facial pose. In this paper, we proposed a face recognition method which remains reliable even in very large head pose variations. In this method, feature from local regions of face are extracted after employing both discrete cosine transform and discrete wavelet transform. Learning strategy is then applied to infer the relationship between face in a given pose and its frontal view. Results we obtained are very promising considering that our proposed method solely relies on a single gallery image. We also demonstrated the high performance of our method in a condition whereby the face images are of low-resolution quality.
This paper investigates the use of a single image of a smooth Lambertian surface to calibrate and remove some image nonlinearities due to the imaging device. To the best of our knowledge, this has not been addressed b...
详细信息
This paper investigates the use of a single image of a smooth Lambertian surface to calibrate and remove some image nonlinearities due to the imaging device. To the best of our knowledge, this has not been addressed before in the literature. We show that this is possible, both theoretically and practically, taking advantage of some local shading measures that vary nonlinearly as a function of luminance and geometric nonlinearities (e.g., gamma correction and lens distortion). This can work as a basis for developing a simple method to estimate these nonlinearities from a single image. Several experiments are reported to validate the proposed method.
Polarization imaging can give information about surface shape, and roughness. Polarization has been used for shape recovery, but with convex/concave reconstruction ambiguity. In this paper, we present a direct method ...
详细信息
Polarization imaging can give information about surface shape, and roughness. Polarization has been used for shape recovery, but with convex/concave reconstruction ambiguity. In this paper, we present a direct method to shape recovery using both polarization and shading that resolves this ambiguity, without the need for nonlinear optimization routines. Several experiments on synthetic and real datasets are reported to evaluate the proposed method. The method consistently outperforms some well-known methods based on polarization information alone.
One of the major goals of computervision and machine intelligence is the development of flexible and efficient methods for shape representation. This paper presents an approach for shape retrieval based on sparse rep...
详细信息
One of the major goals of computervision and machine intelligence is the development of flexible and efficient methods for shape representation. This paper presents an approach for shape retrieval based on sparse representation of scale-invariant heat kernel. We use the Laplace-Beltrami eigen functions to detect a small number of critical points on the shape surface. Then a shape descriptor is formed based on the heat kernels at the detected critical points for different scales, combined with the normalized eigen values of the Lap lace-Beltrami operator. Sparse representation is used to reduce the dimensionality of the calculated descriptor. The proposed descriptor is used for classification via the collaborative representation-based classification with regularized least square algorithm. We compare our approach to two well-known approaches on two different data sets: the nonrigid world data set and the SHREC 2011. The results have indeed confirmed the improved performance of the proposed approach, yet reducing the time and space complicity of the shape retrieval problem.
In this paper, we present an inexpensive system for diverless video capture and fast image stitching of image frames for rapid reef assessment of shallow coral reefs. Our system has two main components: 1) Teardrop, a...
详细信息
In this paper, we present an inexpensive system for diverless video capture and fast image stitching of image frames for rapid reef assessment of shallow coral reefs. Our system has two main components: 1) Teardrop, a...
详细信息
In this paper, we present an inexpensive system for diverless video capture and fast image stitching of image frames for rapid reef assessment of shallow coral reefs. Our system has two main components: 1) Teardrop, a boat-towable, winged hull apparatus designed to house a commercial digital camera, and 2) a mosaicking algorithm to stitch the coral reef video into mosaics for further appreciation and analysis. The captured reef video is then separated into image frames which are to be stitched sequentially using Fast image Labeling. The overlap between image frames is estimated using Single-Step DFT, an efficient sub-pixel estimation algorithm. The estimated overlap is used to compute for the area to be added to the mosaic space. The overlapping section between succeeding image-pairs are stitched along a seam determined by a minimal-cost path using dynamic programming. The visibility of the seam boundaries is further minimized by utilizing blending on multi-resolution splines. Experimental results on automated reef mosaics creation from actual coral reef video taken using Teardrop shows the performance of the system described. The main contribution of this work is the demonstration of a rapid reef visualization system using a diverless system and commercially available, non-research-grade imaging equipment.
Bone cancer is a pathologic condition which may occur for both humans and canines. This tumor develops quickly from within the bone tissue and become painful as it grows outward. A metastasized bone tumor may be cured...
详细信息
Bone cancer is a pathologic condition which may occur for both humans and canines. This tumor develops quickly from within the bone tissue and become painful as it grows outward. A metastasized bone tumor may be cured by amputation, otherwise it will be fatal. The current diagnostic imaging methods for bone cancer are X-rays, Computed Tomography scan (CT scan), and Magnetic Resonance Imaging (MRI). The disadvantages of these methods include not enough detail in X-ray images, high dose of radiation from CT scans, and high expense of the time-consuming MRI method. In most of the bone cancer cases, when this tumor is detected by these imaging methods, it has already metastasized. The study is to investigate whether it is possible to detect canine bone cancer by thermography imaging. This alternative imaging method will decrease diagnostic time, expenses and prevent radiation exposure. The best classification success rate obtained in this study is 80.77%.
In this paper, we introduce a new framework for registering pre-operative 3D volumetric data to intra-operative 2D images. We are particularly interested in examining the problem of aligning CT volumes to correspondin...
详细信息
In this paper, we introduce a new framework for registering pre-operative 3D volumetric data to intra-operative 2D images. We are particularly interested in examining the problem of aligning CT volumes to corresponding X-ray images. Our objective is to apply the 2D-3D registration in the field of orthopedics, specifically on ankle surgery. The long-term goal of this work is to apply this technique to ankle fusion surgery to determine the proper size and orientation of the screws which are used for fusing the bones together. In addition, we try to localize the best bone region to fix these screws. Our framework adopts the shear-warp factorization method to generate synthetic 2D images from the given 3D volume. Also, the alignment score is determined according to Exponential Correlation (EC) as a new similarity measure. We used a variety of methods to evaluate registration quality of our system. It has been tested on 15 clinical CT datasets. Evaluation results indicate the degree of accuracy of our registration framework.
Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectu...
详细信息
Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectural styles is viewed as a task of classifying separate architectural structural elements. In the scope of building facade architectural style classification the current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade. Since certain gradient directions dominate on the shape of each architectural element, discrimination between dominating gradients means classification of architectural elements and thus architectural styles. We use local features to describe gradient directions. Our approach is based on clustering and learning of local features and yields a high classification rate.
image formation involves understanding sensor characteristics and object reflectance. In dentistry, an accurate 3-D representation of the human jaw may be used for diagnostic and treatment purposes. Photogrammetry can...
详细信息
image formation involves understanding sensor characteristics and object reflectance. In dentistry, an accurate 3-D representation of the human jaw may be used for diagnostic and treatment purposes. Photogrammetry can offer a flexible, cost effective solution for accurate 3-D representation of the human teeth, which can be used for diagnostic and treatment purposes. Nonetheless there are several challenges, such as the non-friendly image acquisition environment inside the human mouth, problems with lighting and errors due to the data acquisition sensors. In this paper, we focus on the 3D surface reconstruction aspect for human teeth based on a single image. We introduce a more realistic formulation of the shape-from-shading (SFS) problem by considering the image formation components;the camera, the light source, and the surface reflectance. We propose a non-Lambertian SFS algorithm under perspective projection which benefits from camera calibration parameters. We take into account the attenuation of illumination due to near-field imaging. The surface reflectance is modeled using Oren-Nayar-Wolff model which accounts for the retro-reflection case. Our experiments provide promising quantitative metric results for the proposed approach.
暂无评论