Visual learning and recognition of 3-d objects from appearance

The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image.A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.     

Illumination planning for object recognition using parametriceigenspaces

Presents a novel approach to the problem of illumination planning for robust object recognition in structured environments. Given a set of objects, the goal is to determine the illumination for which the objects are most distinguishable in appearance from each other. Correlation is used as a measure of similarity between objects. For each object, a large number of images is automatically obtained by varying the pose and the illumination direction. Images of all objects together constitute the planning image set. The planning set is compressed using the Karhunen-Loeve transform to obtain a low-dimensional subspace, called the eigenspace. For each illumination direction, objects are represented as parametrized manifolds in the eigenspace. The minimum distance between the manifolds of two objects represents the similarity between the objects in the correlation sense. The optimal source direction is therefore the one that maximizes the shortest distance between the object manifolds. Several experiments have been conducted using real objects. The results produced by the illumination planner have been used to enhance the performance of an object recognition system     

基于球面谐波基图像的任意光照下的人脸识别

提出了一种基于球面谐波基图像的光照补偿算法,用以在任意光照条件下进行人脸识别.算法分两步进行：光照估计和光照补偿.基于人脸形状大致相同和每个人脸的反射率基本相等的假设,首先估计了输入人脸图像光照的9个低频谐波系数.根据光照估计的结果,提出了两种光照补偿方法：纹理图像和差图像.纹理图像为输入图像与其光照辐照图之商,与输入图像的光照条件无关.差图像为输入图像与平均人脸在相同光照下的图像之差,通过减去平均人脸在相同光照下的图像,减弱了光照的影响.在CMU-PIE人脸库和Yale B人脸库上的实验表明,通过光照补偿,不同光照下人脸图像识别率有了很大提高.     

变化光照的对象图像合成

光照是真实感图形绘制和许多图像应用中的一个非常重要的因素.提出了一种完全基于图像的方法来反映光照变化在绘制对图像时的影响.所提出的方法不是直接去估计对象反射模型中的参数,或是去拟合BRDF函数,而是用奇异值分解(SVD)来拟合Lambertian 对象在光照和几何朝向变化情况下的所有图像集合.其中,光线方向的解析表达可以由样本图像、基图像以及已知类对象的图像集导出,对象在新的光线方向下的图像可通过适当地线性组合基图像而有效地绘出.另外,利用对SVD系数的线性插值可以生成反映对象几何朝向和光线变化的连续变形     

Face recognition under varying illumination

To eliminate the effects of illumination variation, the conventional approaches firstly produce a compensation-based face image under standard illumination from the input image and then match the image with the face templates in a database. This method is not inapplicable to the input image with large illumination variation. Therefore, a novel method for varying illumination conditions is proposed. Firstly, the quotient image method is improved. Then, the nine basis images of each subject are generated by the improved quotient image method. Thirdly, one new image of each subject under the same lighting conditions with an input image is synthesized by the corresponding basis images. Finally, the synthetic images and the input image are projected to PCA plane to fulfill the recognition task. The experimental results show that the proposed approach can eliminate the effects of illumination variation and have a high recognition rate in the illumination conditions with remarkable changes.     

Generalization to Novel Views: Universal,Class-based,and Model-based Processing

A major problem in object recognition is that a novel image of a given object can be different from all previously seen images. Images can vary considerably due to changes in viewing conditions such as viewing position and illumination. In this paper we distinguish between three types of recognition schemes by the level at which generalization to novel images takes place: universal, class, and model-based. The first is applicable equally to all objects, the second to a class of objects, and the third uses known properties of individual objects. We derive theoretical limitations on each of the three generalization levels. For the universal level, previous results have shown that no invariance can be obtained. Here we show that this limitation holds even when the assumptions made on the objects and the recognition functions are relaxed. We also extend the results to changes of illumination direction. For the class level, previous studies presented specific examples of classes of objects for which functions invariant to viewpoint exist. Here, we distinguish between classes that admit such invariance and classes that do not. We demonstrate that there is a tradeoff between the set of objects that can be discriminated by a given recognition function and the set of images from which the recognition function can recognize these objects. Furthermore, we demonstrate that although functions that are invariant to illumination direction do not exist at the universal level, when the objects are restricted to belong to a given class, an invariant function to illumination direction can be defined. A general conclusion of this study is that class-based processing, that has not been used extensively in the past, is often advantageous for dealing with variations due to viewpoint and illuminant changes.     

Distinctive Image Features from Scale-Invariant Keypoints

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.     

Face relighting using discriminative 2D spherical spaces for face recognition

As part of the face recognition task in a robust security system, we propose a novel approach for the illumination recovery of faces with cast shadows and specularities. Given a single 2D face image, we relight the face object by extracting the nine spherical harmonic bases and the face spherical illumination coefficients by using the face spherical spaces properties. First, an illumination training database is generated by computing the properties of the spherical spaces out of face albedo and normal values estimated from 2D training images. The training database is then discriminately divided into two directions in terms of the illumination quality and light direction of each image. Based on the generated multi-level illumination discriminative training space, we analyze the target face pixels and compare them with the appropriate training subspace using pre-generated tiles. When designing the framework, practical real-time processing speed and small image size were considered. In contrast to other approaches, our technique requires neither 3D face models nor restricted illumination conditions for the training process. Furthermore, the proposed approach uses one single face image to estimate the face albedo and face spherical spaces. In this work, we also provide the results of a series of experiments performed on publicly available databases to show the significant improvements in the face recognition rates.     

In-the-wild Material Appearance Editing using Perceptual Attributes

Intuitively editing the appearance of materials from a single image is a challenging task given the complexity of the interactions between light and matter, and the ambivalence of human perception. This problem has been traditionally addressed by estimating additional factors of the scene like geometry or illumination, thus solving an inverse rendering problem and subduing the final quality of the results to the quality of these estimations. We present a single-image appearance editing framework that allows us to intuitively modify the material appearance of an object by increasing or decreasing high-level perceptual attributes describing such appearance (e.g., glossy or metallic). Our framework takes as input an in-the-wild image of a single object, where geometry, material, and illumination are not controlled, and inverse rendering is not required. We rely on generative models and devise a novel architecture with Selective Transfer Unit (STU) cells that allow to preserve the high-frequency details from the input image in the edited one. To train our framework we leverage a dataset with pairs of synthetic images rendered with physically-based algorithms, and the corresponding crowd-sourced ratings of high-level perceptual attributes. We show that our material editing framework outperforms the state of the art, and showcase its applicability on synthetic images, in-the-wild real-world photographs, and video sequences.     

可变光照条件下的人脸图像识别

对于人脸图像识别中光照变化的影响,传统的解决方法是对待识别图像进行光照补偿,先使它成为标准光照条件下的图像,然后和模板图像匹配来进行识别。为了提高在光照条件大范围变化时,人脸图像的识别率,提出了一种新的可变光照条件下的人脸图像识别方法。该方法首先利用在9个基本光照方向下分别获得的9幅图像来构成人脸光照特征空间,再通过这个光照特征空间,将图像库中的人脸图像变换成与待识别图像具有相同光照条件的图像,并将其作为模板图像;然后利用特征脸方法进行识别。实验结果表明,这种方法不仅能够有效地解决人脸识别中由于光照变化影响所造成的识别率下降的问题,而且对于光照条件大范围变化的情况,也可以得到比较高的正确识别率。     

Appearance characterization of linear Lambertian objects, generalized photometric stereo, and illumination-invariant face recognition

Traditional photometric stereo algorithms employ a Lambertian reflectance model with a varying albedo field and involve the appearance of only one object. In this paper, we generalize photometric stereo algorithms to handle all appearances of all objects in a class, in particular the human face class, by making use of the linear Lambertian property. A linear Lambertian object is one which is linearly spanned by a set of basis objects and has a Lambertian surface. The linear property leads to a rank constraint and, consequently, a factorization of an observation matrix that consists of exemplar images of different objects (e.g., faces of different subjects) under different, unknown illuminations. Integrability and symmetry constraints are used to fully recover the subspace bases using a novel linearized algorithm that takes the varying albedo field into account. The effectiveness of the linear Lambertian property is further investigated by using it for the problem of illumination-invariant face recognition using just one image. Attached shadows are incorporated in the model by a careful treatment of the inherent nonlinearity in Lambert's law. This enables us to extend our algorithm to perform face recognition in the presence of multiple illumination sources. Experimental results using standard data sets are presented     

Feature space trajectory methods for active computer vision

We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from multiple object views in determining the final object class and pose estimate. A probabilistic feature space trajectory (FST) in a global eigenspace is used to represent 3D distorted views of an object and to estimate the class and pose of an input object. Confidence measures for the class and pose estimates, derived using the probabilistic FST object representation, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information. We demonstrate the ability to use FSTs constructed from images rendered from computer-aided design models to recognize real objects in real images and present test results for a set of metal machined parts.     

A CAD Model Based System for Object Recognition

3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.     

Illumination robust single sample face recognition using multi-directional orthogonal gradient phase faces

Due to the limitation of the storage space in the real-world face recognition application systems, only one sample image per person is often stored in the system, which is the so-called single sample problem. Moreover, real-world illumination has impact on recognition performance. This paper presents an illumination robust single sample face recognition approach, which utilizes multi-directional orthogonal gradient phase faces to solve the above limitations. In the proposed approach, an illumination insensitive orthogonal gradient phase face is obtained by using two vertical directional gradient values of the original image. Multi-directional orthogonal gradient phase faces can be used to extend samples for single sample face recognition. Simulated experiments and comparisons on a subset of Yale B database, Yale database, a subset of PIE database and VALID face database show that the proposed approach is not only an outstanding method for single sample face recognition under illumination but also more effective when addressing illumination, expression, decoration, etc.     

Complex object relighting via split-then-composition by semantics and materials

Complex object illumination transfer is a special challenge in computer vision. In our paper, we put forward a method for complex object illumination transfer. Firstly, the input object image was divided into object components by semantic analysis, to find the reference object images consistent with the object component material in the physical world by material analysis. Material has a great influence on the illumination transfer of object image, so the use of material analysis can greatly reduce the influence of material on the illumination transfer in the later stage. Next, a block matching algorithm was used to deform each reference object image and made it match with each component shape of the input object image. Then, each component of the input object image and each warped reference object image were illuminated by local and global transfer model. Finally, semantic analysis was used to synthesize the re-illumination components of the input object image to obtain the re-illumination input object image. The experimental results prove that the method could make a good effect on the illumination transfer. Our main contribution is the use of semantic and material analysis to split complex objects into simple objects, and skillfully combine semantic and material parsing and composition, block matching algorithm, local and global light migration model to achieve the relighting of complex objects.

     

Detection and Segmentation of Multiple,Partially Occluded Objects by Grouping,Merging, Assigning Part Detection Responses

We propose a method that detects and segments multiple, partially occluded objects in images. A part hierarchy is defined for the object class. Both the segmentation and detection tasks are formulated as binary classification problem. A whole-object segmentor and several part detectors are learned by boosting local shape feature based weak classifiers. Given a new image, the part detectors are applied to obtain a number of part responses. All the edge pixels in the image that positively contribute to the part responses are extracted. A joint likelihood of multiple objects is defined based on the part detection responses and the object edges. Computation of the joint likelihood includes an inter-object occlusion reasoning that is based on the object silhouettes extracted with the whole-object segmentor. By maximizing the joint likelihood, part detection responses are grouped, merged, and assigned to multiple object hypotheses. The proposed approach is demonstrated with the class of pedestrians. The experimental results show that our method outperforms the previous ones.