基于词包和特征融合的目标识别算法

针对现有词包模型对目标识别性能的不足,对特征提取、图像表示等方面进行改进以提高目标识别的准确率。首先,以密集提取关键点的方式取代SIFT关键点提取,减少了计算时间并最大程度地描述了图像底层信息。然后采用尺度不变特征变换(Scale-invariant feature transform, SIFT)描述符和统一模式的局部二值模式(Local binary pattern,LBP)描述符描述关键点周围的形状特征和纹理特征,引入K-Means聚类算法分别生成视觉词典,然后将局部描述符进行近似局部约束线性编码,并进行最大值特征汇聚。分别采用空间金字塔匹配生成具有空间信息的直方图,最后将金字塔直方图相串联,形成特征的图像级融合,并送入SVM进行分类识别。在公共数据库中进行实验,实验结果表明,本文所提方法能取得较高的目标识别准确率。     

基于注意力双层BiReGU模型的方面术语提取方法

方面术语提取是方面级情感分析中的一项重要任务,目的是从在线产品评论中提取关键的方面术语。针对方面术语提取问题,提出基于注意力机制的双层BiReGU模型。该模型在传统BiLSTM模型的基础上,引入双嵌入机制和ReGU（Residual Gated Unit）作为辅助,以提高特征提取的能力。使用BiReGU学习文本特征表示,更好地捕捉词语间的长期依赖关系;在第一层BiReGU之后引入注意力机制,为文本中每个词语赋予不同的权重,得到融合特征后新的知识表示,再输入到第二层BiReGU中学习更加全局的文本特征表示,最后完成提取方面术语的任务。分别在SemEval 2014的Restaurant数据集和Laptop数据集做了相关的对比实验,实验结果证明了所提出方法的有效性。     

基于交互特征表示的评价对象抽取模型

评价对象抽取是对象级情感分析的关键任务之一,评价对象抽取结果会直接影响对象级情感分类的准确率在评价对象抽取任务中,借助手工特征加强模型性能的方式既消耗时间又耗费人力s对数据规模小、特征信息不充分等问题,提出一种基于交互特征表示的评价对象抽取模型(aspect extraction model based on inte...     

双人交互行为的稀疏表征方法*

提出一种双人交互行为的稀疏表征方法,融合体现全局变化的轨迹特征和突出区域运动的时空特征。首先,采用词袋模型得到轨迹特征的稀疏表示。然后,对提取的时空特征采用三层时空金字塔分解得到多层特征,并对其进行稀疏编码,利用多尺度Maxpooling算法融合得到局部稀疏特征。最后,将2种稀疏特征加权串联得到双人交互行为的稀疏表征。采用基于隐动态条件随机场的识别算法对文中提取的稀疏表征进行验证,通过实验证明其有效性。     

Recognizing expressions from face and body gesture by temporal normalized motion and appearance features

Recently, recognizing affects from both face and body gestures attracts more attentions. However, it still lacks of efficient and effective features to describe the dynamics of face and gestures for real-time automatic affect recognition. In this paper, we combine both local motion and appearance feature in a novel framework to model the temporal dynamics of face and body gesture. The proposed framework employs MHI-HOG and Image-HOG features through temporal normalization or bag of words to capture motion and appearance information. The MHI-HOG stands for Histogram of Oriented Gradients (HOG) on the Motion History Image (MHI). It captures motion direction and speed of a region of interest as an expression evolves over the time. The Image-HOG captures the appearance information of the corresponding region of interest. The temporal normalization method explicitly solves the time resolution issue in the video-based affect recognition. To implicitly model local temporal dynamics of an expression, we further propose a bag of words (BOW) based representation for both MHI-HOG and Image-HOG features. Experimental results demonstrate promising performance as compared with the state-of-the-art. Significant improvement of recognition accuracy is achieved as compared with the frame-based approach that does not consider the underlying temporal dynamics.     

Example image-based feature extraction for face recognition

This paper proposes a novel method for recognizing facial images based on the relative distances between an input image and example images. Example facial images can be easily collected online, and a large example database can span new possible facial variations not sufficiently learned during the learning phase. We first extract facial features using a baseline classifier that has a certain degree of accuracy. To achieve a better performance of the proposed method, we divide the collected examples into groups using a clustering method (e.g., k-means), where each clustered group contains examples with similar characteristics. We then hierarchically partition a group formed in the previous level into other groups to analyze more specific facial characteristics, which represent an example pyramid. To describe the characteristics of a group using the clustered examples, we divide the example group into a number of sub-groups. We calculate the averages of the sub-groups and select an example most similar to the average in each sub-group because we assume that the averages of the sub-groups can directly represent their characteristics. Using the selected examples, we build example code words for a novel feature extraction. The example code words are used to measure the distances to an input image and serve as anchors to analyze a facial image in the example domain. The distance values are normalized for each group at all pyramid levels, and are concatenated to form novel features for face recognition. We verified the effectiveness of the proposed example pyramid framework using well-known proposed features, including LBP, HOG, Gabor, and the deep learning method, on the LFW database, and showed that it can yield significant improvements in recognition performance.     

Image-based recognition framework for robotic weed control systems

In this paper, we introduce a novel and efficient image-based weed recognition system for the weed control problem of Broad-leaved Dock (Rumex obtusifolius L.). Our proposed weed recognition system is developed using a framework, that allows the examination of the affects for various image resolutions in detection and recognition accuracy. Moreover, it includes state-of-the-art object/image categorization processes such as feature detection and extraction, codebook learning, feature encoding, image representation and classification. The efficiency of those processes have been improved and optimized by introducing methodologies, techniques and system parameters specially tailored for the goal of weed recognition. Through an exhaustive optimization process, which is presented as our experimental evaluation, we conclude to a weed recognition system that uses an image input resolution of 200 ×150, SURF features over dense feature extraction, an optimized Gaussian Mixture Model based codebook combined with Fisher encoding, using a two level image representation. The resulting image representation vectors are classified using a linear classifier. This system is experimentally shown to yield state-of-the-art recognition accuracy of 89.09% in the examined dataset. Our proposed system is also experimentally shown to comply with the specifications of the examined applications since it provides low false-positive results of 4.38%. As a result, the proposed framework can be efficiently used in weed control robots for precision farming applications.     

Scene classification based on a hierarchical convolutional sparse auto-encoder for high spatial resolution imagery

Efficiently representing and recognizing the semantic classes of the subregions of large-scale high spatial resolution (HSR) remote-sensing images are challenging and critical problems. Most of the existing scene classification methods concentrate on the feature coding approach with handcrafted low-level features or the low-level unsupervised feature learning approaches, which essentially prevent them from better recognizing the semantic categories of the scene due to their limited mid-level feature representation ability. In this article, to overcome the inadequate mid-level representation, a patch-based spatial-spectral hierarchical convolutional sparse auto-encoder (HCSAE) algorithm, based on deep learning, is proposed for HSR remote-sensing imagery scene classification. The HCSAE framework uses an unsupervised hierarchical network based on a sparse auto-encoder (SAE) model. In contrast to the single-level SAE, the HCSAE framework utilizes the significant features from the single-level algorithm in a feedforward and full connection approach to the maximum extent, which adequately represents the scene semantics in the high level of the HCSAE. To ensure robust feature learning and extraction during the SAE feature extraction procedure, a ‘dropout’ strategy is also introduced. The experimental results using the UC Merced data set with 21 classes and a Google Earth data set with 12 classes demonstrate that the proposed HCSAE framework can provide better accuracy than the traditional scene classification methods and the single-level convolutional sparse auto-encoder (CSAE) algorithm.     

混合特征选择和集成学习驱动的代码异味检测

代码异味是违反基本设计原理或编码规范的软件特征,源代码中若存在代码异味将提高其维护的成本和难度。在代码异味检测方法中,机器学习相较其他方法能够取得更好的性能表现。针对使用大量特征进行训练可能会引起“维度灾难”以及单一模型泛化性能不佳的问题,提出一种混合特征选择和集成学习驱动的代码异味检测方法。通过ReliefF、XGBoost特征重要性和Pearson相关系数计算出所有特征的权重并进行融合,删除融合后权重值较低的无关特征,以得到特征子集。构建具有两层结构的Stacking集成学习模型,第一层的基分类器由3种不同的树模型构成,第二层以逻辑回归作为元分类器,两层结构的集成学习模型能够结合多样化模型的优点来增强泛化性能。将特征子集输入Stacking集成学习模型,从而完成代码异味分类与检测任务。实验结果表明,该方法能够减少特征维度,与Stacking集成学习模型第一层中的最优基分类器相比,其在F-measure和G-mean指标上最高分别提升1.46%和0.87%。     

面向恶意网页的静态特征体系研究

恶意网页是一种新型的Web攻击手法,攻击者通常将一段恶意代码嵌入网页中,当用户访问该网页时,恶意代码会试图利用浏览器或其插件漏洞在后台隐秘地执行一系列恶意行为.针对恶意网页静态特征抽取问题,本文从已有的特征中选取了14个信息增益值较高的特征,并通过分析恶意网页的混淆手法提出了8个新的特征,共同组成了22维的静态特征体系.此外,针对已有特征抽取流程提出两点改进：对不同编码格式的原始网页进行预处理;回送JavaScript脚本动态生成的的HTML代码,用以进一步抽取HTML相关特征.实验表明,在不均衡数据集和均衡数据集上,本文的特征体系具有一定的有效性.     

A soft image representation approach by exploiting local neighborhood structure of self-organizing map (SOM)

When images are described with visual words based on vector quantization of low-level color, texture, and edge-related visual features of image regions, it is usually referred as “bag-of-visual words (BoVW)”-based presentation. Although it has proved to be effective for image representation similar to document representation in text retrieval, the hard image encoding approach based on one-to-one mapping of regions to visual words is not expressive enough to characterize the image contents with higher level semantics and prone to quantization error. Each word is considered independent of all the words in this model. However, it is found that the words are related and their similarity of occurrence in documents can reflect the underlying semantic relations between them. To consider this, a soft image representation scheme is proposed by spreading each region’s membership values through a local fuzzy membership function in a neighborhood to all the words in a codebook generated by self-organizing map (SOM). The topology preserving property of the SOM map is exploited to generate a local membership function. A systematic evaluation of retrieval results of the proposed soft representation on two different image (natural photographic and medical) collections has shown significant improvement in precision at different recall levels when compared to different low-level and “BoVW”-based feature that consider only probability of occurrence (or presence/absence) of a word.     

Text document clustering using global term context vectors

Despite the advantages of the traditional vector space model (VSM) representation, there are known deficiencies concerning the term independence assumption. The high dimensionality and sparsity of the text feature space and phenomena such as polysemy and synonymy can only be handled if a way is provided to measure term similarity. Many approaches have been proposed that map document vectors onto a new feature space where learning algorithms can achieve better solutions. This paper presents the global term context vector-VSM (GTCV-VSM) method for text document representation. It is an extension to VSM that: (i) it captures local contextual information for each term occurrence in the term sequences of documents; (ii) the local contexts for the occurrences of a term are combined to define the global context of that term; (iii) using the global context of all terms a proper semantic matrix is constructed; (iv) this matrix is further used to linearly map traditional VSM (Bag of Words—BOW) document vectors onto a ‘semantically smoothed’ feature space where problems such as text document clustering can be solved more efficiently. We present an experimental study demonstrating the improvement of clustering results when the proposed GTCV-VSM representation is used compared with traditional VSM-based approaches.     

Design of evacuation strategies with crowd density feedback

Feature coding is one of the most important procedures in the bag-of-features model for image classification. In this paper, we propose a novel feature coding method called nonnegative correlation coding. In order to obtain a discriminative image representation, our method employs two correlations: the correlation between features and visual words, and the correlation between the obtained codes. The first correlation reflects the locality of codes, i.e., the visual words close to the local feature are activated more easily than the ones distant. The second correlation characterizes the similarity of codes, and it means that similar local features are likely to have similar codes. Both correlations are modeled under the nonnegative constraint. Based on the Nesterov’s gradient projection algorithm, we develop an effective numerical solver to optimize the nonnegative correlation coding problem with guaranteed quadratic convergence. Comprehensive experimental results on publicly available datasets demonstrate the effectiveness of our method.     

基于特征选择与时间一致性稀疏外观模型的目标追踪算法

为了更有效利用追踪目标的判别特征信息,提高目标追踪的精度和鲁棒性,在粒子滤波追踪框架下提出基于特征选择与时间一致性稀疏外观模型的目标追踪算法.首先,采集目标的正负模板和候选目标,根据特征选择模型对正负模板和候选目标进行特征选择,去除多余的干扰信息,得到关键的特征信息.然后,利用正负模板和候选目标的特征建立多任务稀疏表示模型,引入时间一致性正则项,促进更多的候选目标与先前帧的追踪结果具有稀疏表示的相似性.最后,求解多任务稀疏表示模型,得到判别稀疏相似图,获取每个候选目标的判别分,根据目标追踪结果更新正负模板.实验表明,即使在复杂的环境下,文中算法仍然比其它一些追踪算法具有更高的准确性.     

Properties of gray and binary representations

Representations are formalized as encodings that map the search space to the vertex set of a graph. We define the notion of bit equivalent encodings and show that for such encodings the corresponding Walsh coefficients are also conserved. We focus on Gray codes as particular types of encoding and present a review of properties related to the use of Gray codes. Gray codes are widely used in conjunction with genetic algorithms and bit-climbing algorithms for parameter optimization problems. We present new convergence proofs for a special class of unimodal functions; the proofs show that a steepest ascent bit climber using any reflected Gray code representation reaches the global optimum in a number of steps that is linear with respect to the encoding size. There are in fact many different Gray codes. Shifting is defined as a mechanism for dynamically switching from one Gray code representation to another in order to escape local optima. Theoretical results that substantially improve our understanding of the Gray codes and the shifting mechanism are presented. New proofs also shed light on the number of unique Gray code neighborhoods accessible via shifting and on how neighborhood structure changes during shifting. We show that shifting can improve the performance of both a local search algorithm as well as one of the best genetic algorithms currently available.     

PolSAR image classification via multimodal sparse representation-based feature fusion

ABSTRACT

It is well known that various features extraction approaches are utilized in polarimetric synthetic aperture (PolSAR) terrain classification for representing the data characteristic. It needs relevant and effective feature fusion algorithms to process complicated features. To address this issue, this article presents a multimodal sparse representation (MSR) framework based algorithm to fuse the different feature vectors from the complicated data space. Polarimetric data features, decomposition features, and the texture features from Pauli colour-coded image are selected to represent multimodal data in different observation modes. The corresponding multimodal manifold regularizations are added to MSR framework to approximate the data structure. Considering the independence and correlation of features, the intrinsic affinity matrices are calculated from this framework. They are processed via local preserve projection algorithm to project the multimodal features into a low dimensionally intrinsic feature space for subsequent classification. Three datasets are utilized in experiments, Western Xi’an, Flevoland, and San Francisco Bay datasets from the Radarsat-2 system in C-band. The effect of regularization parameters and different dimensional fused features are analysed in visualization and quantitation performance. The experiment results demonstrate that the effectiveness and validity of proposed method are superior to other state-of-art methods.     

Lexicographical framework for image hashing with implementation based on DCT and NMF

Image hash is a content-based compact representation of an image for applications such as image copy detection, digital watermarking, and image authentication. This paper proposes a lexicographical-structured framework to generate image hashes. The system consists of two parts: dictionary construction and maintenance, and hash generation. The dictionary is a large collection of feature vectors called words, representing characteristics of various image blocks. It is composed of a number of sub-dictionaries, and each sub-dictionary contains many features, the number of which grows as the number of training images increase. The dictionary is used to provide basic building blocks, namely, the words, to form the hash. In the hash generation, blocks of the input image are represented by features associated to the sub-dictionaries. This is achieved by using a similarity metric to find the most similar feature among the selective features of each sub-dictionary. The corresponding features are combined to produce an intermediate hash. The final hash is obtained by encoding the intermediate hash. Under the proposed framework, we have implemented a hashing scheme using discrete cosine transform (DCT) and non-negative matrix factorization (NMF). Experimental results show that the proposed scheme is resistant to normal content-preserving manipulations, and has a very low collision probability.     

基于Word2vec的文档分类方法

文档的特征提取和文档的向量表示是文档分类中的关键,本文针对这两个关键点提出一种基于word2vec的文档分类方法.该方法根据DF采集特征词袋,以尽可能的保留文档集中的重要特征词,并且利用word2vec的潜在语义分析特性,将语义相关的特征词用一个主题词乘以合适的系数来代替,有效地浓缩了特征词袋,降低了文档向量的维度;该方法还结合了TF-IDF算法,对特征词进行加权,给每个特征词赋予更合适的权重.本文与另外两种文档分类方法进行了对比实验,实验结果表明,本文提出的基于word2vec的文档分类方法在分类效果上较其他两种方法均有所提高.     

基于高斯分布引导位置相关性权重的情感分类

针对当前情感分类方法通常忽略不同单词之间相对位置特征,导致模型难以学习到单词的最佳位置表示.为了解决这一问题,提出一种基于高斯分布引导位置相关性权重的情感分类算法.首先,计算每个单词与其他单词之间的位置相关性;其次,利用改进的高斯分布函数对位置相关性进行建模,并将其结果与单词的特征向量相乘,以生成单词的位置感知表示;最后,将算法集成到传统模型中以验证其有效性.实验结果表明,所提方法较传统模型获得了更高的准确率,在域内、域外和对抗评估指标上分别提高了2.98%、5.02%和10.55%,表明其具有较好的实用价值.     

Deep learning compact binary codes for fingerprint indexing

With the rapid growth in fingerprint databases, it has become necessary to develop excellent fingerprint indexing to achieve efficiency and accuracy. Fingerprint indexing has been widely studied with real-valued features, but few studies focus on binary feature representation, which is more suitable to identify fingerprints efficiently in large-scale fingerprint databases. In this study, we propose a deep compact binary minutia cylinder code (DCBMCC) as an effective and discriminative feature representation for fingerprint indexing. Specifically, the minutia cylinder code (MCC), as the state-of-the-art fingerprint representation, is analyzed and its shortcomings are revealed. Accordingly, we propose a novel fingerprint indexing method based on deep neural networks to learn DCBMCC. Our novel network restricts the penultimate layer to directly output binary codes. Moreover, we incorporate independence, balance, quantization-loss-minimum, and similarity-preservation properties in this learning process. Eventually, a multi-index hashing (MIH) based fingerprint indexing scheme further speeds up the exact search in the Hamming space by building multiple hash tables on binary code substrings. Furthermore, numerous experiments on public databases show that the proposed approach is an outstanding fingerprint indexing method since it has an extremely small error rate with a very low penetration rate.