Holistic context models for visual recognition

A novel framework to context modeling based on the probability of co-occurrence of objects and scenes is proposed. The modeling is quite simple, and builds upon the availability of robust appearance classifiers. Images are represented by their posterior probabilities with respect to a set of contextual models, built upon the bag-of-features image representation, through two layers of probabilistic modeling. The first layer represents the image in a semantic space, where each dimension encodes an appearance-based posterior probability with respect to a concept. Due to the inherent ambiguity of classifying image patches, this representation suffers from a certain amount of contextual noise. The second layer enables robust inference in the presence of this noise by modeling the distribution of each concept in the semantic space. A thorough and systematic experimental evaluation of the proposed context modeling is presented. It is shown that it captures the contextual “gist” of natural images. Scene classification experiments show that contextual classifiers outperform their appearance-based counterparts, irrespective of the precise choice and accuracy of the latter. The effectiveness of the proposed approach to context modeling is further demonstrated through a comparison to existing approaches on scene classification and image retrieval, on benchmark data sets. In all cases, the proposed approach achieves superior results.     

Music classification via the bag-of-features approach

A central problem in music information retrieval is audio-based music classification. Current music classification systems follow a frame-based analysis model. A whole song is split into frames, where a feature vector is extracted from each local frame. Each song can then be represented by a set of feature vectors. How to utilize the feature set for global song-level classification is an important problem in music classification. Previous studies have used summary features and probability models which are either overly restrictive in modeling power or numerically too difficult to solve. In this paper, we investigate the bag-of-features approach for music classification which can effectively aggregate the local features for song-level feature representation. Moreover, we have extended the standard bag-of-features approach by proposing a multiple codebook model to exploit the randomness in the generation of codebooks. Experimental results for genre classification and artist identification on benchmark data sets show that the proposed classification system is highly competitive against the standard methods.     

局部自适应的灰度图像彩色化

目的 现有的灰度图像彩色化方法为了保证彩色化结果在颜色空间上的一致性,往往采用全局优化的算法,使得图像边界区域易产生过渡平滑现象。为此提出一种局部自适应的灰度图像彩色化方法,在迁移过程中考虑局部邻域像素信息,同时自动调节邻域像素权重,在颜色正确迁移的同时保证清晰的边界信息。方法 首先结合SVM（support vector machine）和ISLIC（improved simple linear iterative clustering）算法获取彩色图像和灰度图像分类结果图;然后在分类基础上,确定灰度图像高置信度像素点,并根据图像纹理特征,在彩色图像中寻找灰度图像的像素匹配点;最后利用自适应权重均值滤波实现高置信度匹配像素点的颜色迁移,并利用迁移结果对低置信度像素点进行颜色扩散,以完成灰度图像彩色化。结果 实验结果显示,本文方法获得的彩色化迁移结果评分均高于3.5分,特别是局部放大区域评价结果均接近或高于4.0分,高于其他现有彩色化方法评价分数。表明本文方法不仅能够保证颜色迁移的准确性和颜色空间的一致性,同时也能获取颜色区分度高的边界细节信息。与现有的典型灰度图像彩色化方法相比,彩色化结果图在颜色迁移的正确性和抑制边界区域颜色的过渡平滑上都有更优的表现。结论 本文算法为灰度图像彩色化过程中抑制颜色越界问题提供了新的指导方法,能有效地应用于遥感、黑白图像/视频处理、医学图像着色等领域。     

Fast Image Correspondence with Global Structure Projection

This paper presents a method for recognizing images with flat objects based on global keypoint structure correspondence.This technique works by two steps:reference keypoint selection and structure projection.The using of global keypoint structure is an extension of an orderless bag-of-features image representation,which is utilized by the proposed matching technique for computation efficiency.Specifically,our proposed method excels in the dataset of images containing "flat objects" such as CD covers,books,newspaper.The efficiency and accuracy of our proposed method has been tested on a database of nature pictures with flat objects and other kind of objects.The result shows our method works well in both occasions.     

Integrated probability function and its application to content-based image retrieval by relevance feedback

In the last few years, we have seen an upsurge of interest in content-based image retrieval (CBIR)—the selection of images from a collection via features extracted from images themselves. Often, a single image attribute may not have enough discriminative information for successful retrieval. On the other hand when multiple features are used, it is hard to determine the suitable weighing factors for various features for optimal retrieval. In this paper, we present a relevance feedback framework with Integrated Probability Function (IPF) which combines multiple features for optimal retrieval. The IPF is based on a new posterior probability estimator and a novel weight updating approach. We perform experiments on 1400 monochromatic trademark images have been performed. The proposed IPF is shown to be more effective and efficient to retrieve deformed trademark images than the commonly used integrated dissimilarity function. The new posterior probability estimator is shown to be generally better than the existing one. The proposed novel weight updating approach by relevance feedback is shown to be better than both the existing scoring approach and the existing ratio approach. In experiments, 95% of the targets are ranked at the top five positions. By two iterations of relevance feedback, retrieval performance can be improved from 75% to over 95%. The IPF and its relevance feedback framework proposed in this paper can be effectively and efficiently used in content-based image retrieval.     

Bagged textural and color features for melanoma skin cancer detection in dermoscopic and standard images

Early detection of malignant melanoma skin cancer is crucial for treating the disease and saving lives. Many computerized techniques have been reported in the literature to diagnose and classify the disease with satisfactory skin cancer detection performance. However, reducing the false detection rate is still challenging and preoccupying because false positives trigger the alarm and require intervention by an expert pathologist for further examination and screening. In this paper, an automatic skin cancer diagnosis system that combines different textural and color features is proposed. New textural and color features are used in a bag-of-features approach for efficient and accurate detection. We particularly claim that the Histogram of Gradients (HG) and the Histogram of Lines (HL) are more suitable for the analysis and classification of dermoscopic and standard skin images than the conventional Histogram of Oriented Gradient (HOG) and the Histogram of Oriented Lines (HOL), respectively. The HG and HL are bagged separately using a codebook for each and then combined with other bagged color vector angles and Zernike moments to exploit the color information. The overall system has been assessed through intensive experiments using different classifiers on a dermoscopic image dataset and another standard dataset. Experimental results have shown the superiority of the proposed system over state-of-the-art techniques.     

General Framework for Rotation Invariant Texture Classification Through Co-occurrence of Patterns

The use of co-occurrences of patterns in image analysis has been recently suggested as one of the possible strategies to improve on the bag-of-features model. The intrinsically high number of features of the method, however, is a potential limit to its widespread application. Its extension into rotation invariant versions also requires careful consideration. In this paper we present a general, rotation invariant framework for co-occurrences of patterns and investigate possible solutions to the dimensionality problem. Using local binary patterns as bag-of-features model, we experimentally evaluate the potential advantages that co-occurrences can provide in comparison with bag-of-features. The results show that co-occurrences remarkably improve classification accuracy in some datasets, but in others the gain is negligible, or even negative. We found that this surprising outcome has an interesting explanation in terms of the degree of association between pairs of patterns in an image, and, in particular, that the higher the degree of association, the lower the gain provided by co-occurrences in comparison with bag-of-features.     

Images as sets of locally weighted features

This paper presents a generic framework in which images are modelled as order-less sets of weighted visual features. Each visual feature is associated with a weight factor that may inform its relevance. This framework can be applied to various bag-of-features approaches such as the bag-of-visual-word or the Fisher kernel representations. We suggest that if dense sampling is used, different schemes to weight local features can be evaluated, leading to results that are often better than the combination of multiple sampling schemes, at a much lower computational cost, because the features are extracted only once. This allows our framework to be a test-bed for saliency estimation methods in image categorisation tasks. We explored two main possibilities for the estimation of local feature relevance. The first one is based on the use of saliency maps obtained from human feedback, either by gaze tracking or by mouse clicks. The method is able to profit from such maps, leading to a significant improvement in categorisation performance. The second possibility is based on automatic saliency estimation methods, including Itti & Koch’s method and SIFT’s DoG. We evaluated the proposed framework and saliency estimation methods using an in house dataset and the PASCAL VOC 2008/2007 dataset, showing that some of the saliency estimation methods lead to a significant performance improvement in comparison to the standard unweighted representation.     

基于改进局部特征分布的图像分类方法

提出一种概率签名的图像分布描述及对应的图像分类算法．算法首先通过高斯混合模型建立图像局部特征分布,然后以混合模型中各个模式的均值为聚类中心,以图像中满足约束条件的局部特征对相应模式的后验概率之和为聚类大小来形成初始的概率签名,最后执行一个压缩过程确定最终的概率签名特征,并通过训练基于Earth Mover's Distance (EMD)核的SVM分类器完成图像分类．概率签名允许一个局部特征对多个聚类做出反映,可以编码更多判别信息以及从视觉感知上捕捉更多的相似性．通过与其它图像分类方法在场景识别和对象分类两项任务上的对比实验,验证了文中提出的分类方法的有效性．     

Non-Parametric Mixture Model Based Evolution of Level Sets and Application to Medical Images

We present a novel region-based curve evolution algorithm which has three primary contributions: (i) non-parametric estimation of probability distributions using the recently developed NP windows method; (ii) an inequality-constrained least squares method to model the image histogram with a mixture of nonparametric probability distributions; and (iii) accommodation of the partial volume effect, which is primarily due to low resolution images, and which often poses a significant challenge in medical image analysis (our primary application area). We first approximate the image intensity histogram as a mixture of non-parametric probability density functions (PDFs), justifying its use with respect to medical image analysis. The individual densities in the mixture are estimated using the recent NP windows PDF estimation method, which builds a continuous representation of discrete signals. A Bayesian framework is then formulated in which likelihood probabilities are given by the non-parametric PDFs and prior probabilities are calculated using an inequality constrained least squares method. The non-parametric PDFs are then learnt and the segmentation solution is spatially regularised using a level sets framework. The log ratio of the posterior probabilities is used to drive the level set evolution. As background to our approach, we recall related developments in level set methods. Results are presented for a set of synthetic and natural images as well as simulated and real medical images of various anatomical organs. Results on a range of images show the effectiveness of the proposed algorithm.     

Supervised Learning of Quantizer Codebooks by Information Loss Minimization

This paper proposes a technique for jointly quantizing continuous features and the posterior distributions of their class labels based on minimizing empirical information loss such that the quantizer index of a given feature vector approximates a sufficient statistic for its class label. Informally, the quantized representation retains as much information as possible for classifying the feature vector correctly. We derive an alternating minimization procedure for simultaneously learning codebooks in the euclidean feature space and in the simplex of posterior class distributions. The resulting quantizer can be used to encode unlabeled points outside the training set and to predict their posterior class distributions, and has an elegant interpretation in terms of lossless source coding. The proposed method is validated on synthetic and real data sets and is applied to two diverse problems: learning discriminative visual vocabularies for bag-of-features image classification and image segmentation.     

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。     

基于Contourlet域的隐马尔可夫树模型的图像融合算法

提出一种基于Contourlet域隐马尔可夫树(CHMT)的多聚焦图像融合方法。CHMT能有效捕获不同尺度系数之间、不同方向系数之间的相关性,能为图像融合提取更多的特征信息。算法对低频子带采用区域方差法,高频子带则依据训练后模型的每一系数的后验概率进行不同的融合处理,以减少融合图像边缘处的斑块模糊现象。仿真实验结果表明,该算法优于基于Contourlet域的常规融合算法,融合后的图像具有更好的主观视觉效果。     

图像内容感知缩放的检测方法研究

针对可用于图像篡改的内容感知缩放技术,本文提出了一种基于概率Map图统计特征的内容感知缩放检测算法.该算法利用概率Map图来反映图像是否经过内容感知缩放操作,并利用新提出的积分投影与局部统计特征来检测篡改图像.而后利用分类器进行分类训练,从而有效识别基于内容感知缩放操作的图像篡改.实验结果显示,所提算法能够区分出原始图像与篡改图像,并具有较高的正确检测率.     

Small object detection in cluttered image using a correlation based active contour model

This paper presents a novel energy function for active contour models based on autocorrelation function, which is capable of detecting small objects against a cluttered background. In the proposed method, image features are calculated using a combination of short-term autocorrelations (STA) computed from the image pixels to represent region information. The obtained features are exploited to define an energy function for the localized region-based active contour model called normalized accumulated short-term autocorrelation (NASTA). Minimizing this energy function, we can accurately detect small objects in images containing cluttered and textured backgrounds. Moreover, the proposed method provides high robustness against random noise and can precisely locate small objects in noisy backgrounds, difficult to be detected with naked eye. Experimental results indicate remarkable advantages of our approach comparing to existing methods.     

本征图像分解的可变尺度局部分析与集成方法

针对自然图像与磁共振图像,提出本征图像分解的统一的数学模型与算法,解决这两类图像中的重要问题:1)自然图像的光照和反射图像的估计,2)磁共振图像中的偏移场估计与分割.文中数学模型只需要一个基本的假设,即观察到的图像可近似为两个具有不同特性的本征图像的乘积:一个光滑的图像,简称为S-图像;一个近似为分片常量的图像,简称为L-图像.为了充分利用本征图像的特性,提出可变尺度局部分析与集成的方法.由于S-图像的光滑性,使用低阶泰勒展开式或更一般的光滑基函数的线性组合以局部逼近.得到的局部光滑逼近可通过整个感兴趣区域(ROI)的局部区域覆盖及其对应的单位分解扩展成整个ROI上的光滑图像,同时得到图像分割结果和L-图像.实验表明,文中方法对图像的两个本征因子的假设较弱,适用于更广泛的图像.目前方法已在磁共振图像及自然图像中进行测试,得到较优结果.     

一种基于小波与概率估计的医学图像配准方法

为提高医学图像配准效果,提出了一种基于小波变换和互信息的配准方法.以小波变换对源图像进行二级分解,并在每个分解层对其子带分量分别进行贝叶斯最大验后概率估计,求概率估计的回归参数,得到配准图像的各小波子带分量,再进行小波逆变换,实现对源医学图像的配准.     

基于潜语义主题加强的跨媒体检索算法

针对不同模态数据对相同语义主题表达存在差异性,以及传统跨媒体检索算法忽略了不同模态数据能以合作的方式探索数据的内在语义信息等问题,提出了一种新的基于潜语义主题加强的跨媒体检索（LSTR）算法。首先,利用隐狄利克雷分布（LDA）模型构造文本语义空间,然后以词袋（BoW）模型来表达文本对应的图像;其次,使用多分类逻辑回归对图像和文本分类,用得到的基于多分类的后验概率表示文本和图像的潜语义主题;最后,利用文本潜语义主题去正则化图像的潜语义主题,使图像的潜语义主题得到加强,同时使它们之间的语义关联最大化。在Wikipedia数据集上,文本检索图像和图像检索文本的平均查准率为57.0%,比典型相关性分析（CCA）、SM（Semantic Matching）、SCM（Semantic Correlation Matching）算法的平均查准率分别提高了35.1%、34.8%、32.1%。实验结果表明LSTR算法能有效地提高跨媒体检索的平均查准率。