Orientation (computer vision)

About: Orientation (computer vision) is a research topic. Over the lifetime, 17196 publications have been published within this topic receiving 358181 citations.

Super-resolving Noisy Images

Abstract: Our goal is to obtain a noise-free, high resolution (HR) image, from an observed, noisy, low resolution (LR) image. The conventional approach of preprocessing the image with a denoising algorithm, followed by applying a super-resolution (SR) algorithm, has an important limitation: Along with noise, some high frequency content of the image (particularly textural detail) is invariably lost during the denoising step. This 'denoising loss' restricts the performance of the subsequent SR step, wherein the challenge is to synthesize such textural details. In this paper, we show that high frequency content in the noisy image (which is ordinarily removed by denoising algorithms) can be effectively used to obtain the missing textural details in the HR domain. To do so, we first obtain HR versions of both the noisy and the denoised images, using a patch-similarity based SR algorithm. We then show that by taking a convex combination of orientation and frequency selective bands of the noisy and the denoised HR images, we can obtain a desired HR image where (i) some of the textural signal lost in the denoising step is effectively recovered in the HR domain, and (ii) additional textures can be easily synthesized by appropriately constraining the parameters of the convex combination. We show that this part-recovery and part-synthesis of textures through our algorithm yields HR images that are visually more pleasing than those obtained using the conventional processing pipeline. Furthermore, our results show a consistent improvement in numerical metrics, further corroborating the ability of our algorithm to recover lost signal.

Exploring Patterns of Gradient Orientations and Magnitudes for Face Recognition

Abstract: A novel direction for efficiently describing face images is proposed by exploring the relationships between both gradient orientations and magnitudes of different local image structures. Presented in this paper are not only a novel feature set called patterns of orientation difference (POD) but also several improvements to our previous algorithm called patterns of oriented edge magnitudes (POEM). The whitened principal component analysis (PCA) dimensionality reduction technique is applied upon both the POEM- and POD-based representations to get more compact and discriminative face descriptors. We then show that the two methods have complementary strength and that by combining the two algorithms, one obtains stronger results than either of them considered separately. By experiments carried out on several common benchmarks, including the FERET database with both frontal and nonfrontal images as well as the very challenging LFW data set, we prove that our approach is more efficient than contemporary ones in terms of both higher performance and lower complexity.

Three-dimensional computer modelling

Abstract: To generate a 3D computer model of a subject object 210, images 300-316, 380-384 of the subject object are recorded from different viewing positions and directions. The image data is processed to generate a plurality of sets of images, each set containing images having registered imaging positions and directions. A preliminary 3D computer model 390 is generated using the images from a first of the sets such that the position and orientation of the preliminary 3D computer model 390 is registered with the images in the set. The imaging positions and directions of the images in the first set are then registered with the imaging positions and directions of the images in each other respective set. This is done by projecting the preliminary 3D computer model 390 into images from each other set, and changing the relative position and orientation of the preliminary 3D computer model 390 and images to align the silhouette of the projected 3D computer model with the silhouette of the imaged subject object in the images. A refined 3D computer model of the subject object is generated using images from the different sets which are registered.

Language-free layout analysis

Abstract: A system for isolating blocks, lines, words, and symbols within images of machine-printed textual documents that is, to a large existent, independent of language and writing system is described. This is achieved by exploiting a small number of nearly universal typesetting and layout conventions. The system does not require prior knowledge of page orientation (module 90/spl deg/), and copes well with nonzero skew and shear angles (within 10/spl deg/). Also it locates blocks of text without reliance on detailed a priori layout models, and in spite of unknown or mixed horizontal and vertical text-line orientations. Within blocks, it infers text-line orientation and isolates lines, without knowledge of the language, symbol set, text sizes, or the number of text lines. Segmentation into words and symbols, and determination of reading order, normally require some knowledge of the language: this is held to minimum by relying on shape-driven algorithms. The underlying algorithms are based on Fourier theory, digital signal processing, computational geometry, and statistical decision theory. Most of the computation occurs within algorithms that possess unambiguous semantics (that is, heuristics are kept to a minimum). The effectiveness of the method on English, Japanese, Hebrew, Thai, and Korean documents is discussed. >