The illumination-invariant recognition of 3D objects using localcolor invariants

Traditional approaches to three dimensional object recognition exploit the relationship between three dimensional object geometry and two dimensional image geometry. The capability of object recognition systems can be improved by also incorporating information about the color of object surfaces. Using physical models for image formation, the authors derive invariants of local color pixel distributions that are independent of viewpoint and the configuration, intensity, and spectral content of the scene illumination. These invariants capture information about the distribution of spectral reflectance which is intrinsic to a surface and thereby provide substantial discriminatory power for identifying a wide range of surfaces including many textured surfaces. These invariants can be computed efficiently from color image regions without requiring any form of segmentation. The authors have implemented an object recognition system that indexes into a database of models using the invariants and that uses associated geometric information for hypothesis verification and pose estimation. The approach to recognition is based on the computation of local invariants and is therefore relatively insensitive to occlusion. The authors present several examples demonstrating the system's ability to recognize model objects in cluttered scenes independent of object configuration and scene illumination. The discriminatory power of the invariants has been demonstrated by the system's ability to process a large set of regions over complex scenes without generating false hypotheses     

Using eigencolor normalization for illumination-invariant color object recognition

Color is one of salient features for color object recognition, however, the colors of object images sensitively depend on scene illumination. To overcome the lighting dependency problem, a color constancy or color normalization method has to be used. This paper presents a color image normalization method, called eigencolor normalization, which consists of two phases as follows. First, the compacting method, which was originally used for compensating the adverse effect due to shape distortion for 2-D planar objects, is exploited for 3-D color space to make the color distribution less correlated and more compact. Second, the compact color image is further normalized by rotating the histogram to align with the reference axis computed. Consequently, the object colors are transformed into a new color space, called eigencolor space, which reflects the inherent colors of the object and is more invariant to illumination changes. Experimental results show that our eigencolor normalization method is superior to other existing color constancy or color normalization schemes on achieving more accurate color object recognition.     

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.     

Relighting with the Reflected Irradiance Field: Representation,Sampling and Reconstruction

Image-based relighting (IBL) is a technique to change the illumination of an image-based object/scene. In this paper, we define a representation called the reflected irradiance field which records the light reflected from a scene as viewed at a fixed viewpoint as a result of moving a point light source on a plane. It synthesizes a novel image under a different illumination by interpolating and superimposing appropriate recorded samples. Furthermore, we study the minimum sampling problem of the reflected irradiance field, i.e., how many light source positions are needed. We find that there exists a geometry-independent bound for the sampling interval whenever the second-order derivatives of the surface BRDF and the minimum depth of the scene are bounded. This bound ensures that when the novel light source is on the plane, the error in the reconstructed image is controlled by a given tolerance, regardless of the geometry. We also analyze the bound of depth error so that the extra reconstruction error can also be governed when the novel light source is off-plane. Experiments on both synthetic and real surfaces are conducted to verify our analysis.     

Pictorial recognition of objects employing affine invariance in thefrequency domain

Describes an efficient approach to pose invariant pictorial object recognition employing spectral signatures of image patches that correspond to object surfaces which are roughly planar. Based on singular value decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale, and 2D translation. Unlike previous log-polar representations which were not invariant to slant, our log-log sampling configuration in the frequency domain yields complete affine invariance. The images are preprocessed by a novel model-based segmentation scheme that detects and segments objects that are affine-similar to members of a model set of basic geometric shapes. The segmented objects are then recognized by their signatures using multidimensional indexing in a pictorial dataset represented in the frequency domain. Experimental results with a dataset of 26 models show 100 percent recognition rates in a wide range of 3D pose parameters and imaging degradations: 0-360° swing and tilt, 0-82° of slant, more than three octaves in scale change, window-limited translation, high noise levels (0 dB), and significantly reduced resolution (1:5)     

多相机环境下基于颜色不变量和熵图的目标识别

不同相机环境下的光照条件差异是影响目标识别的一个重要因素.依据光照模型推导出与环境光照无关的颜色不变量,并将其作为目标识别的特征,利用熵图估计出的特征向量的HP相似度作为相似性评价标准进行目标识别.实验结果表明,该方法对于不同相机间环境光照条件的变化具有很好的抵抗能力,目标识别率较高.     

Spatial Color Indexing and Applications

We define a new image feature called the color correlogram and use it for image indexing and comparison. This feature distills the spatial correlation of colors and when computed efficiently, turns out to be both effective and inexpensive for content-based image retrieval. The correlogram is robust in tolerating large changes in appearance and shape caused by changes in viewing position, camera zoom, etc. Experimental evidence shows that this new feature outperforms not only the traditional color histogram method but also the recently proposed histogram refinement methods for image indexing/retrieval. We also provide a technique to cut down the storage requirement of the correlogram so that it is the same as that of histograms, with only negligible performance penalty compared to the original correlogram.We also suggest the use of color correlogram as a generic indexing tool to tackle various problems arising from image retrieval and video browsing. We adapt the correlogram to handle the problems of image subregion querying, object localization, object tracking, and cut detection. Experimental results again suggest that the color correlogram is more effective than the histogram for these applications, with insignificant additional storage or processing cost.     

What Is the Set of Images of an Object Under All Possible Illumination Conditions?

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then–in theory–the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRⁿ and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRⁿ. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.

     

The illumination-invariant matching of deterministic localstructure in color images

The availability of multiple spectral measurements at each pixel in an image provides important additional information for recognition. Spectral information is of particular importance for applications where spatial information is limited. Such applications include the recognition of small objects or the recognition of small features on partially occluded objects. We introduce a feature matrix representation for deterministic local structure in color images. Although feature matrices are useful for recognition, this representation depends on the spectral properties of the scene illumination. Using a linear model for surface spectral reflectance with the same number of parameters as the number of color bands, we show that changes in the spectral content of the illumination correspond to linear transformations of the feature matrices, and that image plane rotations correspond to circular shifts of the matrices. From these relationships, we derive an algorithm for the recognition of local surface structure which is invariant to these scene transformations. We demonstrate the algorithm with a series of experiments on images of real objects     

Color invariance

This paper presents the measurement of colored object reflectance, under different, general assumptions regarding the imaging conditions. We exploit the Gaussian scale-space paradigm for color images to define a framework for the robust measurement of object reflectance from color images. Object reflectance is derived from a physical reflectance model based on the Kubelka-Munk theory for colorant layers. Illumination and geometrical invariant properties are derived from the reflectance model. Invariance and discriminative power of the color invariants is experimentally investigated, showing the invariants to be successful in discounting shadow, illumination, highlights, and noise. Extensive experiments show the different invariants to be highly discriminative, while maintaining invariance properties. The presented framework for color measurement is well-founded in the physics of color as well as in measurement science. Hence, the proposed invariants are considered more adequate for the measurement of invariant color features than existing methods     

Quaternion Fourier-Mellin moments for color images

The quaternion Fourier-Mellin moments for describing color images are introduced, which can be seen as the generalization of traditional Fourier-Mellin moments for gray-level images. Then, the quaternion Fourier-Mellin moment invariants are derived, which could be a useful tool in color object recognition tasks that require the similarity invariance. In addition, the problem of color image registration using quaternion Fourier-Mellin moments is discussed. The registration method can match color images differing in rotation and scaling. The advantage of our method is that it can process color image directly, without losing color information. Experimental results validate the effectiveness of the method we proposed.     

Color space analysis of mutual illumination

Mutual illumination occurs when light reflected from one surface impinges on a second one. The resulting additional illumination incident on the second surface affects both the color and intensity of the light reflected from it. As a consequence, the image of a surface in the presence of mutual illumination differs from what it otherwise would have been in the absence of mutual illumination. Unaccounted for mutual illumination can easily confuse methods that rely on intensity or color such as shape-from-shading or color-based object recognition. In this correspondence, we introduce an algorithm that removes mutual illumination effects from images. The domain is that of previously-segmented images of convex surfaces of uniform color and diffuse reflectance where for each surface the interreflection occurs mainly from one other surface and can be accurately accounted for within a one-bounce model. The algorithm is based on a singular value decomposition of the colors coming from each surface. Geometrical information about where on the surface the colors emanate from is not required. The RGB triples from a single convex surface experiencing interreflection fall in a plane; intersecting the planes generated from two interreflecting surfaces results in a unique interreflection color. Each pixel can then be factored into its interreflection and no-interreflection components so that a complete no-interreflection image is produced     

Edge and corner detection by photometric quasi-invariants

Feature detection is used in many computer vision applications such as image segmentation, object recognition, and image retrieval. For these applications, robustness with respect to shadows, shading, and specularities is desired. Features based on derivatives of photometric invariants, which we is called full invariants, provide the desired robustness. However, because computation of photometric invariants involves nonlinear transformations, these features are unstable and, therefore, impractical for many applications. We propose a new class of derivatives which we refer to as quasi-invariants. These quasi-invariants are derivatives which share with full photometric invariants the property that they are insensitive for certain photometric edges, such as shadows or specular edges, but without the inherent instabilities of full photometric invariants. Experiments show that the quasi-invariant derivatives are less sensitive to noise and introduce less edge displacement than full invariant derivatives. Moreover, quasi-invariants significantly outperform the full invariant derivatives in terms of discriminative power.     

Indexing through laplacian spectra

With ever growing databases containing multimedia data, indexing has become a necessity to avoid a linear search. We propose a novel technique for indexing multimedia databases in which entries can be represented as graph structures. In our method, the topological structure of a graph as well as that of its subgraphs are represented as vectors whose components correspond to the sorted laplacian eigenvalues of the graph or subgraphs. Given the laplacian spectrum of graph G, we draw from recently developed techniques in the field of spectral integral variation to generate the laplacian spectrum of graph G+e without computing its eigendecomposition, where G+e is a graph obtained by adding edge e to graph G. This process improves the performance of the system for generating the subgraph signatures for 1.8% and 6.5% in datasets of size 420 and 1400, respectively. By doing a nearest neighbor search around the query spectra, similar but not necessarily isomorphic graphs are retrieved. Given a query graph, a voting schema ranks database graphs into an indexing hypothesis to which a final matching process can be applied. The novelties of the proposed method come from the powerful representation of the graph topology and successfully adopting the concept of spectral integral variation in an indexing algorithm. To examine the fitness of the new indexing framework, we have performed a number of experiments using an extensive set of recognition trials in the domain of 2D and 3D object recognition. The experiments, including a comparison with a competing indexing method using two different graph-based object representations, demonstrate both the robustness and efficacy of the overall approach.     

Illuminant and device invariant colour using histogram equalisation

Colour can potentially provide useful information for a variety of computer vision tasks such as image segmentation, image retrieval, object recognition and tracking. However, for it to be helpful in practice, colour must relate directly to the intrinsic properties of the imaged objects and be independent of imaging conditions such as scene illumination and the imaging device. To this end many invariant colour representations have been proposed in the literature. Unfortunately, recent work (Second Workshop on Content-based Multimedia Indexing) has shown that none of them provides good enough practical performance.In this paper we propose a new colour invariant image representation based on an existing grey-scale image enhancement technique: histogram equalisation. We show that provided the rank ordering of sensor responses are preserved across a change in imaging conditions (lighting or device) a histogram equalisation of each channel of a colour image renders it invariant to these conditions. We set out theoretical conditions under which rank ordering of sensor responses is preserved and we present empirical evidence which demonstrates that rank ordering is maintained in practice for a wide range of illuminants and imaging devices. Finally, we apply the method to an image indexing application and show that the method out performs all previous invariant representations, giving close to perfect illumination invariance and very good performance across a change in device.     

A volumetric/iconic frequency domain representation for objectswith application for pose invariant face recognition

A novel method for representing 3D objects that unifies viewer and model centered object representations is presented. A unified 3D frequency-domain representation, called volumetric frequency representation (VFR), encapsulates both the spatial structure of the object and a continuum of its views in the same data structure. The frequency-domain image of an object viewed from any direction can be directly extracted employing an extension of the projection slice theorem, where each Fourier-transformed view is a planar slice of the volumetric frequency representation. The VFR is employed for pose-invariant recognition of complex objects, such as faces. The recognition and pose estimation is based on an efficient matching algorithm in a four-dimensional Fourier space. Experimental examples of pose estimation and recognition of faces in various poses are also presented