A novel relevance feedback method for CBIR

In this paper, we address the challenge about insufficiency of training set and limited feedback information in each relevance feedback (RF) round during the process of content based image retrieval (CBIR). We propose a novel active learning scheme to utilize the labeled and unlabeled images to build the initial Support Vector Machine (SVM) classifier for image retrieving. In our framework, two main components, a pseudo-label strategy and an improved active learning selection method, are included. Moreover, a feature subspace partition algorithm is proposed to model the retrieval target from users by the analysis from relevance labeled images. Experimental results demonstrate the superiority of the proposed method on a range of databases with respect to the retrieval accuracy.     

Blink detection for real-time eye tracking

This work is motivated by our goal of providing non-contact head and eye based control of computer systems for people with motor difficulties. The system described here uses spatio-temporal filtering and variance maps to locate the head and find the eye-feature points, respectively. These feature points are accurately tracked in the succeeding frames by using a modified version of the Lucas–Kanade tracking algorithm with pyramidal implementation. Accurate head and eye tracking results are obtained at a processing rate of more than 30 frames per second (fps) in more than 90% cases with a low false positive blink detection rate of 0.01%. This is achieved under varying lighting conditions for people of different ethnicity, with and without wearing glasses.     

A real-time framework for eye detection and tracking

Epidemiological studies indicate that automobile drivers from varying demographics are confronted by difficult driving contexts such as negotiating intersections, yielding, merging and overtaking. We aim to detect and track the face and eyes of the driver during several driving scenarios, allowing for further understanding of a driver’s visual search pattern behavior. Traditionally, detection and tracking of objects in visual media has been performed using specific techniques. These techniques vary in terms of their robustness and computational cost. This research proposes a real-time framework that is built upon a foundation synonymous to boosting, which we extend from learners to trackers and demonstrate that the idea of an integrated framework employing multiple trackers is advantageous in forming a globally strong tracking methodology. In order to model the effectiveness of trackers, a confidence parameter is introduced to help minimize the errors produced by incorrect matches and allow more effective trackers with a higher confidence value to correct the perceived position of the target.     

A novel confidence estimation method for heterogeneous implicit feedback

Implicit feedback, which indirectly reflects opinion through user behaviors, has gained increasing attention in recommender system communities due to its accessibility and richness in real-world applications. A major way of exploiting implicit feedback is to treat the data as an indication of positive and negative preferences associated with vastly varying confidence levels. Such algorithms assume that the numerical value of implicit feedback, such as time of watching, indicates confidence, rather than degree of preference, and a larger value indicates a higher confidence, although this works only when just one type of implicit feedback is available. However, in real-world applications, there are usually various types of implicit feedback, which can be referred to as heterogeneous implicit feedback. Existing methods cannot efficiently infer confidence levels from heterogeneous implicit feedback. In this paper, we propose a novel confidence estimation approach to infer the confidence level of user preference based on heterogeneous implicit feedback. Then we apply the inferred confidence to both point-wise and pair-wise matrix factorization models, and propose a more generic strategy to select effective training samples for pair-wise methods. Experiments on real-world e-commerce datasets from Tmall.com show that our methods outperform the state-of-the-art approaches, considering several commonly used ranking-oriented evaluation criteria.     

An improved likelihood model for eye tracking

While existing eye detection and tracking algorithms can work reasonably well in a controlled environment, they tend to perform poorly under real world imaging conditions where the lighting produces shadows and the person’s eyes can be occluded by e.g. glasses or makeup. As a result, pixel clusters associated with the eyes tend to be grouped together with background-features. This problem occurs both for eye detection and eye tracking. Problems that especially plague eye tracking include head movement, eye blinking and light changes, all of which can cause the eyes to suddenly disappear. The usual approach in such cases is to abandon the tracking routine and re-initialize eye detection. Of course this may be a difficult process due to missed data problem. Accordingly, what is needed is an efficient method of reliably tracking a person’s eyes between successively produced video image frames, even in situations where the person’s head turns, the eyes momentarily close and/or the lighting conditions are variable. The present paper is directed to an efficient and reliable method of tracking a human eye between successively produced infrared interlaced image frames where the lighting conditions are challenging. It proposes a log likelihood-ratio function of foreground and background models in a particle filter-based eye tracking framework. It fuses key information from even, odd infrared fields (dark and bright-pupil) and their corresponding subtractive image into one single observation model. Experimental validations show good performance of the proposed eye tracker in challenging conditions that include moderate head motion and significant local and global lighting changes. The paper presents also an eye detector that relies on physiological infrared eye responses and a modified version of a cascaded classifier.     

使用人眼几何特征的视线追踪方法

目的 视线追踪是人机交互的辅助系统,针对传统的虹膜定位方法误判率高且耗时较长的问题,本文提出了一种基于人眼几何特征的视线追踪方法,以提高在2维环境下视线追踪的准确率。方法 首先通过人脸定位算法定位人脸位置,使用人脸特征点检测的特征点定位眼角点位置,通过眼角点计算出人眼的位置。直接使用虹膜中心定位算法的耗时较长,为了使虹膜中心定位的速度加快,先利用虹膜图片建立虹膜模板,然后利用虹膜模板检测出虹膜区域的位置,通过虹膜中心精定位算法定位虹膜中心的位置,最后提取出眼角点、虹膜中心点等信息,对点中包含的角度信息、距离信息进行提取,组合成眼动向量特征。使用神经网络模型进行分类,建立注视点映射关系,实现视线的追踪。通过图像的预处理对图像进行增强,之后提取到了相对的虹膜中心。提取到需要的特征点,建立相对稳定的几何特征代表眼动特征。结果 在普通的实验光照环境中,头部姿态固定的情况下,识别率最高达到98.9%,平均识别率达到95.74%。而当头部姿态在限制区域内发生变化时,仍能保持较高的识别率,平均识别率达到了90%以上。通过实验分析发现,在头部变化的限制区域内,本文方法具有良好的鲁棒性。结论 本文提出使用模板匹配与虹膜精定位相结合的方法来快速定位虹膜中心,利用神经网络来对视线落点进行映射,计算视线落点区域,实验证明本文方法具有较高的精度。     

An adaptable connectionist text-retrieval system with relevance feedback.

This paper introduces a new connectionist network for certain domain-specific text-retrieval and search applications with expert end users. A new model reference adaptive system is proposed that involves three learning phases. Initial model-reference learning is first performed based upon an ensemble set of input-output of an initial reference model. Model-reference following is needed in dynamic environments where documents are added, deleted, or updated. Relevance feedback learning from multiple expert users then optimally maps the original query using either a score-based or a click-through selection process. The learning can be implemented, in regression or classification modes, using a three-layer network. The first layer is an adaptable layer that performs mapping from query domain to document space. The second and third layers perform document-to-term mapping, search/retrieval, and scoring tasks. The learning algorithms are thoroughly tested on a domain-specific text database that encompasses a wide range of Hewlett Packard (HP) products and for a large number of most commonly used single- and multiterm queries.     

一种针对隐式反馈推荐系统的表征学习方法

基于邻域的top-◢N◣推荐算法利用隐式反馈数据建立排序模型,其算法性能严重依赖于相似度函数的表现。传统相似性度量函数在隐式反馈数据上会遇到数据过于稀疏和维数过高两个问题,稀疏数据不利于推荐模型选取光滑的邻域,过高的数据维数会导致维数灾难问题,导致推荐算法表现较差。为此提出一种基于表征学习方法的推荐算法,改进算法实现了基于二部图网络的多目标节点表征学习方法,在节点表征中通过嵌入不同层次的网络结构信息和适合推荐任务的次序信息来提升推荐性能。三个不同规模真实数据集上的实验结果表明,该算法相较于常用的基于隐式反馈的推荐模型具有更高的准确率和召回率,特别是针对大规模数据集能够有效缓解矩阵稀疏性问题和维数灾难问题,提高推荐性能。     

An improved distance-based relevance feedback strategy for image retrieval

Most CBIR (content based image retrieval) systems use relevance feedback as a mechanism to improve retrieval results. NN (nearest neighbor) approaches provide an efficient method to compute relevance scores, by using estimated densities of relevant and non-relevant samples in a particular feature space. In this paper, particularities of the CBIR problem are exploited to propose an improved relevance feedback algorithm based on the NN approach. The resulting method has been tested in a number of different situations and compared to the standard NN approach and other existing relevance feedback mechanisms. Experimental results evidence significant improvements in most cases.     

基于反馈的实时集群系统中的负载平衡方法

为了提高实时集群系统中各节点的利用率并防止出现CPU使用率的热点,研究了实时集群系统中基于反馈控制的实时调度框架,并提出了一种新的面向任意图结构的负载平衡算法.该算法基于差异迁移系数和扩散负载平衡原理指导任务迁移以实现系统负载均衡,同时结合反馈控制以避免系统节点使用率振荡.实验结果表明,该算法不仅实现了节点间负载平衡,有效避免了局部热点,而且与反馈控制算法有机集成,保证整个系统稳定运行.     

A noisy-smoothing relevance feedback method for content-based medical image retrieval

In this paper, we address a new problem of noisy images which present in the procedure of relevance feedback for medical image retrieval. We concentrate on the noisy images, caused by the users mislabeling some irrelevant images as relevant ones, and a noisy-smoothing relevance feedback (NS-RF) method is proposed. In NS-RF, a two-step strategy is proposed to handle the noisy images. In step 1, a noisy elimination algorithm is adopted to identify and eliminate the noisy images. In step 2, to further alleviate the influence of noisy images, a fuzzy membership function is employed to estimate the relevance probabilities of retained relevant images. After noisy handling, the fuzzy support vector machine, which can take into account different relevant images with different relevance probabilities, is adopted to re-rank the images. The experimental results on the IRMA medical image collection demonstrate that the proposed method can deal with the noisy images effectively.     

A syntactic analysis method for sinusoidal tracking eye movements

A syntactic method for the recognition of sinusoidal eye movements is presented. The method is based on a piecewise transformation of an eye movement signal to strings of a formal language and use of a formal grammar which generates the formal language. Gain and phase parameters of sinusoidal eye movements between a stimulus and its response are computed after the recognition of eye movements and after removing corrective saccades from the transformed signal. The method is used at an otoneurological laboratory.     

一种高效的图像数据库检索方法

对于大型图像库,如何高效地检索出相似图像是图像检索系统的一大挑战。提出了一种改进的K-均值聚类算法建立分层结构的索引,再利用A*树算法和三角不等式原则及N近邻方法对索引库快速高效地搜索,达到对图像库快速高效检索相似图像的目的。实验在Corel图像库上进行,实验结果表明该方法以对数时间复杂度实现基于内容的高效检索。     

一种基于降噪自编码器的隐式反馈推荐算法

现有的隐式反馈协同算法直接利用稀疏的二值社交信任信息辅助推荐,存在严重的数据稀疏问题,且没有深层次地融合社交信任信息的影响。针对以上问题,提出利用降噪自编码器深度融合用户隐式反馈数据与社交信息的算法。首先从不同的角度区分用户信任,提出一种信任相似度的新度量方法来改善社交数据的稀疏性,利用降噪自编码器将信任数据与用户隐式交互信息深度融合,通过综合二者的影响,有效提高了推荐质量。实验表明,该算法优于现有主流的的隐式反馈推荐算法。     

An adaptive real-time intelligent seam tracking system

The concept of a real-time seam tracking system for welding automation and the initial design for building a prototype is presented. The Adaptive Real-time Intelligent Seam Tracker (ARTIST) uses a robot held, laser based vision system for automation of arc welding processes, and is currently under development at the Applied Research Laboratory of the Pennsylvania State University. The design of ARTIST builds upon the concept of a zero-pass technique. The 3D information of seam geometry is collected and processed for real-time guidance and control of the welding torch trailing behind the laser based vision sensor. This zero-pass concept eliminates the need for preprogramming of the weld path and thus, potentially enhances the welding cycle time for small batches. The ARTIST is designed to support multipass arc welding and to handle any tack welds which are encountered during the seam welding operation.     

Collaborative eye tracking based code review through real-time shared gaze visualization

Code review is intended to find bugs in early development phases, improving code quality for later integration and testing. However, due to the lack of experience with algorithm design, or software development, individual novice programmers face challenges while reviewing code. In this paper, we utilize collaborative eye tracking to record the gaze data from multiple reviewers, and share the gaze visualization among them during the code review process. The visualizations, such as borders highlighting current reviewed code lines, transition lines connecting related reviewed code lines, reveal the visual attention about program functions that can facilitate understanding and bug tracing. This can help novice reviewers to make sense to confirm the potential bugs or avoid repeated reviewing of code, and potentially even help to improve reviewing skills. We built a prototype system, and conducted a user study with paired reviewers. The results showed that the shared real-time visualization allowed the reviewers to find bugs more efficiently.     

Ego-similarity measurement for relevance feedback

Relevance Feedback in Content-Based Image Retrieval is an active field of research. Many mechanisms of Relevance Feedback exist with many interactive techniques and implement criteria. In this paper, we proposed a novel approach of RF which can set adaptive weights of similarity measurement for each database image from the user feedback, i.e. ego-similarity measurement. We would explore the feedback records were archived in the two different ways that stored along with query images (QRF-based) or along with each retrieved relevant image from the image database (DBRF-based). In the experiment, DBRF-based relevant feedback improved greatly in the retrieval effectiveness.     

An algorithm for real-time computer control of a tracking system with a nonlinearity

A tracking antenna control system with a nonlinearity is considered. The system is uniformly sampled and the control signal is computed at each sampling interval to achieve optimal position alignment with minimum energy expenditure. A direct minimization method permitting efficient real-time implementation is adopted.