A feature construction method for general object recognition

This paper presents a novel approach for object detection using a feature construction method called Evolution-COnstructed (ECO) features. Most other object recognition approaches rely on human experts to construct features. ECO features are automatically constructed by uniquely employing a standard genetic algorithm to discover series of transforms that are highly discriminative. Using ECO features provides several advantages over other object detection algorithms including: no need for a human expert to build feature sets or tune their parameters, ability to generate specialized feature sets for different objects, and no limitations to certain types of image sources. We show in our experiments that ECO features perform better or comparable with hand-crafted state-of-the-art object recognition algorithms. An analysis is given of ECO features which includes a visualization of ECO features and improvements made to the algorithm.     

Local and global Gabor features for object recognition

Invariant object recognition is one of the most central problems in computer vision. To be successful when occlusion and distortions are present, object recognition has to be based on local features. The features should express the significant information while being robust in the presence of noise and distortions, and stable in terms of feature parameters. In this study, Gabor filtering based features is analyzed in terms of the above requirements. Two classes of Gabor features are introduced: global Gabor features and fundamental frequency Gabor features. The Gabor filter response and stability issues are analyzed in terms of the filtering parameters. The robustness of the proposed features is examined through experiments. Both analytical and experimental results indicate that when certain conditions on the filter parameters are met, Gabor filtering can be reliably used in low-level feature extraction in image processing, and the filter responses can be used to construct robust invariant recognition systems.     

Coloured object recognition using invariant spectral features

A new algorithm using invariant spectral features for segmenting colour images is presented in this paper. Input data are three primary images obtained from a colour sensor. The input colour image is transformed to IHS (Intensity, Hue, Saturation) colour space. This colour space transform compensates for illumination variations and delivers image pixel values with low variance for individual colour regions, hence contributing to simplified segmentation. The hue and saturation images are then separately filtered and combined. The resulting image is segmented by means of a threshold process. An opening operation on the segmented image completes the algorithm. Experimental results obtained for several images are presented. Issues related to illumination and sensors are also addressed.     

用于目标快速识别的特征选取方法

现有的基于图像局部特征的目标识别算法,在保证较高识别率的情况下无法满足实时性要求。针对这个问题,考虑到多数局部特征是不稳定、不可靠或与目标无关的,可通过正确匹配的训练图像,对图像局部特征选取一个子集用于目标识别。提出一种在特征包方法基础上,通过无监督地选取鲁棒性强及足够特殊、稳定的局部特征用于目标识别的新方法并应用于目标识别实验。实验结果证实该方法在仅仅使用原图像约4%的局部特征的情况下获得了与使用全部局部特征几乎相近的目标识别率,目标识别时间由秒缩短至几十毫秒,满足了目标识别实时性要求。     

Learning optimized features for hierarchical models of invariant object recognition

There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.     

Evidential reasoning for object recognition

The authors present a framework to guide development of evidential reasoning in object recognition systems. Principles of evidential reasoning processes for open-world object recognition are proposed and applied to build evidential reasoning capabilities. The principles summarize research and findings by the authors up through the mid-1990s, including seminal results in object-centered computer vision, figure-ground discrimination, and the application of hierarchical Bayesian inference, Bayesian networks, and decision graphs to evidential reasoning for object recognition.     

Probabilistic indexing for object recognition

Recent papers have indicated that indexing is a promising approach to fast model-based object recognition because it allows most of the possible matches between sets of image features and sets of model features to be quickly eliminated from consideration. This correspondence describes a system that is capable of indexing using sets of three points undergoing 3D transformations and projection by taking advantage of the probabilistic peaking effect. To be able to index using sets of three points, we must allow false negatives. These are overcome by ensuring that we examine several correct hypotheses. The use of these techniques to speed up the alignment method is described. Results are given on real and synthetic data     

3-D multiview object representations for model-based object recognition

3-D multiview object representations are presented as an alternative approach to traditional 3-D volumetric object representations. 3-D multiview models store features in a viewer-centered representation and thus can be immediately used to match features derived from 2-D images. Algorithms are presented that construct, search and perform region growing on 3-D multiview object models.     

Texture features for object salience

Although texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset.     

通用对象识别技术

遵循通用对象识别系统的一般框架,重点讨论了各种特征区域选取、特征区域描述技术,比较了几种主流的识别模型和模型的训练方法,并介绍了对象识别系统的性能评估方法及其常用数据集,最后分析了未来可能的研究发展方向。     

An object model for image recognition

The use of object-oriented database principles to help model an image for computer vision, specifically, for line-image analysis, is described. The resulting representation, called thin line code (TLC), is general across known applications and extensible to new applications. TLC's advantages, and also some difficulties it has in strictly adhering to traditional notions of object orientation, are addressed. A review of relevant aspects of object modeling is included     

Planning multiple observations for object recognition

Most computer vision systems perform object recognition on the basis of the features extracted from a single image of the object. The problem with this approach is that it implicitly assumes that the available features are sufficient to determine the identity and pose of the object uniquely. If this assumption is not met, then the feature set is insufficient, and ambiguity results. Consequently, much research in computer vision has gone toward finding sets of features that are sufficient for specific tasks, with the result that each system has its own associated set of features. A single, general feature set would be desirable. However, research in automatic generation of object recognition programs has demonstrated that predetermined, fixed feature sets are often incapable of providing enough information to unambiguously determine either object identity or pose. One approach to overcoming the inadequacy of any feature set is to utilize multiple sensor observations obtained from different viewpoints, and combine them with knowledge of the 3-D structure of the object to perform unambiguous object recognition. This article presents initial results toward performing object recognition by using multiple observations to resolve ambiguities. Starting from the premise that sensor motions should be planned in advance, the difficulties involved in planning with ambiguous information are discussed. A representation for planning that combines geometric information with viewpoint uncertainty is presented. A sensor planner utilizing the representation was implemented, and the results of pose-determination experiments performed with the planner are discussed.     

Using orientation tokens for object recognition

We propose the use of co-occurrence matrices/histograms (of relative distance, relative angle) between pairs of orientation tokens for silhouette recognition and texture discrimination. The orientation tokens are defined as the tangent vectors to the boundary of the silhouette, or the gradient vectors for grey images. The efficiency of the method is demonstrated with the help of three different series of experiments with real data.     

面向灵巧操作的视觉目标识别

为了能够实现灵巧手对目标物体进行精准操作,研究了一种利用Kinect检测出目标物体,在帧差法的基础上对获取的深度进行背景相减,获取出目标物体的运动点,在此基础上利用获取的目标物体的特征采用T-S模糊逻辑判断出目标物体的方法,以BH8-280对目标物体进行抓取实验为例,在实验中,Kinect在帧差法的基础上检测出目标物体的位姿,大小,形状,以此为基础建立起T-S模糊逻辑系统,判断出目标物体的属性和类别,通过实验结果进一步说明了利用本文研究的方法显著地提高了判断物体的准确率和效率,为灵巧手的精细控制抓取奠定了基础。     

Onboard object recognition for planetary exploration

Machine learning techniques have shown considerable promise for automating common visual inspection tasks such as the detection of human faces in cluttered scenes. Here, we examine whether similar techniques can be used (or adapted) for the problem of automatically locating geologic landforms in planetary images gathered by spacecraft. Beyond enabling more efficient and comprehensive ground analysis of down-linked data, we are aiming toward perceptive spacecraft that use onboard processing to autonomously analyze their collected imagery and take appropriate actions. In our current study, we have employed various supervised learning algorithms, including neural networks, ensemble methods, support vector machines (SVM), and continuously-scalable template models (CSTM) to derive detectors for craters from ground-truthed images. The resulting detectors are evaluated on a challenging set of Viking Orbiter images of Mars containing roughly one thousand craters. The SVM approach with normalized image patches provides detection and localization performance closest to that of human labelers and is shown to be substantially superior to boundary-based approaches such as the Hough transform. However, the run-time cost in applying the SVM solution in the standard way (spatial scanning in which the SVM is applied to each patch of the image on a window-by-window basis) is too high due both to the number of support vectors required and the number of test vectors generated by sliding a window across the data. We have developed an implementation using FFTs and the overlap-and-add technique, which can be used to efficiently apply SVMs to sensor data in resource-constrained environments such as on a spacecraft. The technique allows exact computation of the SVM decision function over an image using minimal RAM (typically less than 5% of the size of the image) and only ${\mathcal{O}}(n_{s} (\log_{2} d + 11))$ real multiplications per pixel, where n _s is the number of support vectors and d is the dimensionality of the vectors compared with ${\mathcal{O}}(n_{s} d)$ real multiplications per pixel for spatial scanning. Our approach is complementary to reduced set methods providing (in theory) a multiplicative gain in performance.     

A fast 3D object recognition algorithm using plane-constrained point pair features

Multimedia Tools and Applications - The point pair feature (PPF) algorithm is one of the best-performing 3D object recognition algorithms. However, the high dimensionality of its search space is a...