Compact object recognition using energy-function-based optimization

Describes a method of recognizing objects whose contours can be represented in smoothly varying polar coordinate form. Both low- and high-level information about the object (contour smoothness and edge sharpness at the low level and contour shape at the high level) are incorporated into a single energy function that defines a 1D, cyclic, Markov random field (1DCMRF). This 1DCMRF is based on a polar coordinate object representation whose center can be initialized at any location within the object. The recognition process is based on energy function minimization, which is implemented by simulated annealing     

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.     

Online robust action recognition based on a hierarchical model

Action recognition solely based on video data has known to be very sensitive to background activity, and also lacks the ability to discriminate complex 3D motion. With the development of commercial depth cameras, skeleton-based action recognition is becoming more and more popular. However, the skeleton-based approach is still very challenging because of the large variation in human actions and temporal dynamics. In this paper, we propose a hierarchical model for action recognition. To handle confusing motions, a motion-based grouping method is proposed, which can efficiently assign each video a group label, and then for each group, a pre-trained classifier is used for frame-labeling. Unlike previous methods, we adopt a bottom-up approach that first performs action recognition for each frame. The final action label is obtained by fusing the classification to its frames, with the effect of each frame being adaptively adjusted based on its local properties. To achieve online real-time performance and suppressing noise, bag-of-words is used to represent the classification features. The proposed method is evaluated using two challenge datasets captured by a Kinect. Experiments show that our method can robustly recognize actions in real-time.     

Evaluating a color-based active basis model for object recognition

Wu and coworkers introduced an active basis model (ABM) for object recognition in 2010, in which the learning algorithm tends to sketch edges in textures. A grey-value local power spectrum was used to find a common template and deformable templates from a set of training images and to detect an object in new images by template matching. In this paper, we propose a color-based active basis model (color-based ABM for short), which incorporates color information. We adopt the framework of Wu et al. in the learning, detection, and classification of the color-based ABM. However, in order to improve the performance in object recognition, we modify the framework of Wu et al. by using different color-based features in both the learning and template matching algorithms. In this color-based ABM approach, two types of learning (i.e., supervised learning and unsupervised learning) are also explored. Moreover, the usefulness of the color-based ABM for practical object recognition in computer vision applications is demonstrated and its significant improvement in recognizing objects is reported.     

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     

基于随机游走模型的物体识别

针对传统物体识别算法中只依赖于视觉特征进行识别的单一性缺陷,提出了一种结合先验关系的物体识别算法。在训练阶段,通过图模型结构化表示先验关系,分别构建了图像-图像、语义-语义两个子图以及两子图之间的联系,利用该图模型建立随机游走模型;在识别阶段,建立待识别图像与随机游走模型中的图像节点和语义节点的关系,在该概率模型上进行随机游走,将随机游走的结果作为物体识别的结果。实验结果证明了结合先验关系的物体识别算法的有效性;提出的物体识别算法具有较强的识别性能。     

Coupling-and-decoupling: A hierarchical model for occlusion-free object detection

Handling occlusion is a very challenging problem in object detection. This paper presents a method of learning a hierarchical model for X-to-X occlusion-free object detection (e.g., car-to-car and person-to-person occlusions in our experiments). The proposed method is motivated by an intuitive coupling-and-decoupling strategy. In the learning stage, the pair of occluding X?s (e.g., car pairs or person pairs) is represented directly and jointly by a hierarchical And–Or directed acyclic graph (AOG) which accounts for the statistically significant co-occurrence (i.e., coupling). The structure and the parameters of the AOG are learned using the latent structural SVM (LSSVM) framework. In detection, a dynamic programming (DP) algorithm is utilized to find the best parse trees for all sliding windows with detection scores being greater than the learned threshold. Then, the two single X?s are decoupled from the declared detections of X-to-X occluding pairs together with some non-maximum suppression (NMS) post-processing. In experiments, our method is tested on both a roadside-car dataset collected by ourselves (which will be released with this paper) and two public person datasets, the MPII-2Person dataset and the TUD-Crossing dataset. Our method is compared with state-of-the-art deformable part-based methods, and obtains comparable or better detection performance.     

Mathematical model of hierarchical menu structure optimization

A mathematical model is proposed to optimize the structure of hierarchical menus and directories. The model considers each element popularity. The problem of discrete optimization is solved regarding the choice of menu structure minimizing the average search time. It is demonstrated that optimal menu panels should provide the user with identical number of options having popularity levels split in the same proportion. It is indicated that the model allows for comparing the types of menu, as well as for choosing the best one. A certain algorithm is developed to design optimal menu, taking into account both semantic constraints and results of optimization. Application of the algorithm is illustrated using mobile phone menu optimization as an example.     

A tree-based context model for object recognition

There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations or locations of objects and guide detectors to produce a semantically coherent interpretation of a scene. However, the performance benefit of context models has been limited because most of the previous methods were tested on data sets with only a few object categories, in which most images contain one or two object categories. In this paper, we introduce a new data set with images that contain many instances of different object categories, and propose an efficient model that captures the contextual information among more than a hundred object categories using a tree structure. Our model incorporates global image features, dependencies between object categories, and outputs of local detectors into one probabilistic framework. We demonstrate that our context model improves object recognition performance and provides a coherent interpretation of a scene, which enables a reliable image querying system by multiple object categories. In addition, our model can be applied to scene understanding tasks that local detectors alone cannot solve, such as detecting objects out of context or querying for the most typical and the least typical scenes in a data set.     

一种融合神经稀疏编码机制的层次目标识别算法

针对基本层次化目标识别计算模型缺乏明确学习概念和有效学习方法的问题,利用神经稀疏编码的学习规则,生成原型向量集合。通过模拟复杂细胞的感受野特性,实现层次化的稀疏编码过程,提出基于神经稀疏编码的层次目标特征提取算法。并利用简化的分类器设计,完成复杂场景下的广义目标识别问题。在Caltech101数据库上进行实验对比,结果表明本文算法相对Serre计算模型在识别正确率上有较大提高,时间复杂度增加并不明显,且更加符合生物视觉机理。     

基于ColorMax模型的拟视皮层图像识别*

受生物学研究启发,模拟视皮层组织结构提出了ColorMax层次模型用于彩色图像识别问题。利用ColorMax模型进行学习能得到较高层次的复杂仿真视觉特征,这些特征具有较好的识别可分性和不变性。利用该模型实现基于对象颜色、纹理和形状的综合特征识别与比较。实验结果表明,提出的模型能够在学习样本数量少的情况下进行学习,提高了识别的速度,能达到与当前先进算法相当识别效果。     

基于上下文相似度的对象识别模型的研究

对象识别是数据集成的一个重要问题,针对学术领域的对象集成问题,提出一个基于上下文环境的对象识别模型。利用作者名字的上下文环境,包括合作者、国际会议、论文时间、论文标题4维信息对作者进行对象识别。通过计算两个表象每一维信息的相似程度,采用感知器模型对于少量的专家标注的学习用例进行学习从而获得每一维合适的权重以及对应的阈值,最后利用构造的模型进行准确预测。实验结果表明该模型具有较高的可用性。     

Approximate control optimization based on transformation of object model

It is considered an approach to approximate solving of control problems using different simplifying transformation of object model based on principles of extension or contraction of searching area and possible schemes of its realization. This approach focuses on getting, generally speaking, of a rough approximation to a global solution with two-sided estimation. Main attention focused on effective non-traditional schemes of continuous system velocity set transformation and discrete system transition set transformation. The obtained global approximate solutions can be considered as initial approximations in various iterative optimization procedures to be improved.     

基于主题模型对象判别特征的场景识别

为了解决场景识别中存在的类内差异性与类间相似性问题,提出一种基于主题模型的对象判别特征的场景识别方法。首先,使用双卷积神经网络模型提取图像的全局空间特征和对象特征;然后用主题模型的方法对对象特征进行描述,将非欧几里得空间中的判别向量投影到欧几里得空间,得到对象判别图像描述符;最后将全局空间特征和对象判别图像描述符相融合,并采用分类器进行分类。实验结果表明,所提出的方法具有更好的场景分类性能。     

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。     

Web cache optimization with nonlinear model using object features

In this paper, Web cache optimization by utilizing syntactic features extracted from cache objects is studied. A nonlinear model is used to predict the value of each cache object by using features from the HTTP responses of the server, the access log of the cache, and from the HTML structure of the object. In a case study, linear and nonlinear models are used to classify about 50,000 HTML documents according to their popularity. The nonlinear model yields classification percentages of 64 and 74 for the documents to be stored or to be removed from the cache, respectively. A synthetic workload is then used to study the performance gain from the classifier in a conventional Least Recently Used cache model. The results suggest that the proposed approach can improve the performance of the cache substantially.     

Evolutionary learning of hierarchical decision rules

This paper describes an approach based on evolutionary algorithms, hierarchical decision rules (HIDER), for learning rules in continuous and discrete domains. The algorithm produces a hierarchical set of rules, that is, the rules are sequentially obtained and must therefore be tried until one is found whose conditions are satisfied. Thus, the number of rules may be reduced because the rules could be inside of one another. The evolutionary algorithm uses both real and binary coding for the individuals of the population. We tested our system on real data from the UCI repository, and the results of a ten-fold cross-validation are compared to C4.5s, C4.5Rules, See5s, and See5Rules. The experiments show that HIDER works well in practice.