Learning a hierarchical image manifold for Web image classification

Image classification is an essential task in content-based image retrieval.However,due to the semantic gap between low-level visual features and high-level semantic concepts,and the diversification of Web images,the performance of traditional classification approaches is far from users’ expectations.In an attempt to reduce the semantic gap and satisfy the urgent requirements for dimensionality reduction,high-quality retrieval results,and batch-based processing,we propose a hierarchical image manifold with novel distance measures for calculation.Assuming that the images in an image set describe the same or similar object but have various scenes,we formulate two kinds of manifolds,object manifold and scene manifold,at different levels of semantic granularity.Object manifold is developed for object-level classification using an algorithm named extended locally linear embedding(ELLE) based on intra-and inter-object difference measures.Scene manifold is built for scene-level classification using an algorithm named locally linear submanifold extraction(LLSE) by combining linear perturbation and region growing.Experimental results show that our method is effective in improving the performance of classifying Web images.     

A reconfigurable computing framework for multi-scale cellular image processing

Cellular computing architectures represent an important class of computation that are characterized by simple processing elements, local interconnect and massive parallelism. These architectures are a good match for many image and video processing applications and can be substantially accelerated with Reconfigurable Computers. We present a flexible software/hardware framework for design, implementation and automatic synthesis of cellular image processing algorithms. The system provides an extremely flexible set of parallel, pipelined and time-multiplexed components which can be tailored through reconfigurable hardware for particular applications. The most novel aspects of our framework include a highly pipelined architecture for multi-scale cellular image processing as well as support for several different pattern recognition applications. In this paper, we will describe the system in detail and present our performance assessments. The system achieved speed-up of at least 100× for computationally expensive sub-problems and 10× for end-to-end applications compared to software implementations.     

Detecting image orientation based on low-level visual content

Accurately and automatically detecting image orientation is of great importance in intelligent image processing. In this paper, we present automatic image orientation detection algorithms based on both the luminance (structural) and chrominance (color) low-level content features. The statistical learning support vector machines (SVMs) are used in our approach as the classifiers. The different sources of the extracted image features, as well as the binary classification nature of SVM, require our system to be able to integrate the outputs from multiple classifiers. Both static combiner (averaging) and trainable combiner (also based on SVMs) are proposed and evaluated in this work. Furthermore, two rejection options (regular and re-enforced ambiguity rejections) are employed to improve orientation detection accuracy by sieving out images with low confidence values during the classification. Large amounts of experiments have been conducted on a database of more than 14,000 images to validate our approaches. Discussions and future directions for this work are also addressed at the end of the paper.     

CUDA加速工业DR图像分割*

对DR ( Digtal Radiography数字辐射成像)图像进行分割是工业DR图像处理中一项重要内容。C-V算法对DR图像分割效果较好, 但该算法计算量大, 在工业应用中达不到实时处理要求。本文结合高性价比CUDA（计算机统一设备架构）技术实现C-V算法对DR图像分割并行化,并采用共享内存技术、独立计算与合并计算结合的方法,较大地提高了C-V方法的计算效率。对实际工业DR图像分割实验结果显示,本文方法加速比可达到32到44倍,表明使用CUDA并行化C-V方法分割DR图像高效可行。     

Statistics of natural image categories

In this paper we study the statistical properties of natural images belonging to different categories and their relevance for scene and object categorization tasks. We discuss how second-order statistics are correlated with image categories, scene scale and objects. We propose how scene categorization could be computed in a feedforward manner in order to provide top-down and contextual information very early in the visual processing chain. Results show how visual categorization based directly on low-level features, without grouping or segmentation stages, can benefit object localization and identification. We show how simple image statistics can be used to predict the presence and absence of objects in the scene before exploring the image.     

Multiple level visual semantic fusion method for image re-ranking

Mid-level semantic attributes have obtained some success in image retrieval and re-ranking. However, due to the semantic gap between the low-level feature and intermediate semantic concept, information loss is considerable in the process of converting the low-level feature to semantic concept. To tackle this problem, we tried to bridge the semantic gap by looking for the complementary of different mid-level features. In this paper, a framework is proposed to improve image re-ranking by fusing multiple mid-level features together. The framework contains three mid-level features (DCNN-ImageNet attributes, Fisher vector, sparse coding spatial pyramid matching) and a semi-supervised multigraph-based model that combines these features together. In addition, our framework can be easily extended to utilize arbitrary number of features for image re-ranking. The experiments are conducted on the a-Pascal dataset, and our approach that fuses different features together is able to boost performance of image re-ranking efficiently.     

Regularized Reconstruction of Shapes with Statistical a priori Knowledge

The reconstruction of geometry or, in particular, the shape of objects is a common issue in image analysis. Starting from a variational formulation of such a problem on a shape manifold we introduce a regularization technique incorporating statistical shape knowledge. The key idea is to consider a Riemannian metric on the shape manifold which reflects the statistics of a given training set. We investigate the properties of the regularization functional and illustrate our technique by applying it to region-based and edge-based segmentation of image data. In contrast to previous works our framework can be considered on arbitrary (finite-dimensional) shape manifolds and allows the use of Riemannian metrics for regularization of a wide class of variational problems in image processing.     

Joint semantics and feature based image retrieval using relevance feedback

Relevance feedback is a powerful technique for image retrieval and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been proposed for relevance feedback. In addition, methods that perform optimization on multilevel image content model have been formulated. However, these methods only perform relevance feedback on low-level image features and fail to address the images' semantic content. In this paper, we propose a relevance feedback framework to take advantage of the semantic contents of images in addition to low-level features. By forming a semantic network on top of the keyword association on the images, we are able to accurately deduce and utilize the images' semantic contents for retrieval purposes. We also propose a ranking measure that is suitable for our framework. The accuracy and effectiveness of our method is demonstrated with experimental results on real-world image collections.     

Locally affine patch mapping and global refinement for image super-resolution

This paper deals with the super-resolution (SR) problem based on a single low-resolution (LR) image. Inspired by the local tangent space alignment algorithm in [16] for nonlinear dimensionality reduction of manifolds, we propose a novel patch-learning method using locally affine patch mapping (LAPM) to solve the SR problem. This approach maps the patch manifold of low-resolution image to the patch manifold of the corresponding high-resolution (HR) image. This patch mapping is learned by a training set of pairs of LR/HR images, utilizing the affine equivalence between the local low-dimensional coordinates of the two manifolds. The latent HR image of the input (an LR image) is estimated by the HR patches which are generated by the proposed patch mapping on the LR patches of the input. We also give a simple analysis of the reconstruction errors of the algorithm LAPM. Furthermore we propose a global refinement technique to improve the estimated HR image. Numerical results are given to show the efficiency of our proposed methods by comparing these methods with other existing algorithms.     

Finding optimal least-significant-bit substitution in image hiding by dynamic programming strategy

The processing of simple least-significant-bit (LSB) substitution embeds the secret image in the least significant bits of the pixels in the host image. This processing may degrade the host image quality so significantly that grabbers can detect that there is something going on in the image that interests them. To overcome this drawback, an exhaustive least-significant-bit substitution scheme was proposed by Wang et al. but it takes huge computation time. Wang et al. then proposed another method that uses a genetic algorithm to search “approximate” optimal solutions and computation time is no longer so huge. In this paper, we shall use the dynamic programming strategy to get the optimal solution. The experimental results will show that our method consumes less computation time and also gets the optimal solution.     

Exploring statistical correlations for image retrieval

Bridging the cognitive gap in image retrieval has been an active research direction in recent years, of which a key challenge is to get enough training data to learn the mapping functions from low-level feature spaces to high-level semantics. In this paper, image regions are classified into two types: key regions representing the main semantic contents and environmental regions representing the contexts. We attempt to leverage the correlations between types of regions to improve the performance of image retrieval. A Context Expansion approach is explored to take advantages of such correlations by expanding the key regions of the queries using highly correlated environmental regions according to an image thesaurus. The thesaurus serves as both a mapping function between image low-level features and concepts and a store of the statistical correlations between different concepts. It is constructed through a data-driven approach which uses Web data (images, their surrounding textual annotations) as training data source to learn the region concepts and to explore the statistical correlations. Experimental results on a database of 10,000 general-purpose images show the effectiveness of our proposed approach in both improving search precision (i.e. filter irrelevant images) and recall (i.e. retrieval relevant images whose context may be varied). Several major factors which have impact on the performance of our approach are also studied.     

An improved image enhancement framework based on multiple attention mechanism

Image enhancement can accentuate image feature and is necessary process in image processing. This work focuses on fusing multi-exposure image sequences low-light image enhancement. Inspired by the classical non-local means in computer vision, we proposed an improved deep neural network framework with attentions for image enhancement. Firstly, the original image was preprocessed in different dimensions. we get the edge images using an edge extracted algorithm and fusion multi exposed images to get an better initial images based on fully convolutional neural network with position and channel attention mechanism. Secondly, the head network is constructed by fully convolutional neural network. For capturing long-range dependencies between features maps, we designed a non-local attention module for head network to get better enhancement image. Finally, emerging the original images, edge image and fusion image as the input of the head network, it can enhance the images to get high-quality images. Experiments show that our framework proposed in this paper is effective and the attention mechanism play a significant hole in the network.     

SVM-based active feedback in image retrieval using clustering and unlabeled data

In content-based image retrieval, relevance feedback is studied extensively to narrow the gap between low-level image feature and high-level semantic concept. However, most methods are challenged by small sample size problem since users are usually not so patient to label a large number of training instances in the relevance feedback round. In this paper, this problem is solved by two strategies: (1) designing a new active selection criterion to select images for user's feedback. It takes both the informative and the representative measures into consideration, thus the diversities between these images are increased while their informative powers are kept. With this new criterion, more information gain can be obtained from the feedback images; and (2) incorporating unlabeled images within the co-training framework. Unlabeled data partially alleviates the training data scarcity problem, thus improves the efficiency of support vector machine (SVM) active learning. Systematic experimental results verify the superiority of our method over existing active learning methods.     

Informative patches sampling for image classification by utilizing bottom-up and top-down information

In image classification based on bag of visual words framework, image patches used for creating image representations affect the classification performance significantly. However, currently, patches are sampled mainly based on processing low-level image information or just extracted regularly or randomly. These methods are not effective, because patches extracted through these approaches are not necessarily discriminative for image categorization. In this paper, we propose to utilize both bottom-up information through processing low-level image information and top-down information through exploring statistical properties of training image grids to extract image patches. In the proposed work, an input image is divided into regular grids, each of which is evaluated based on its bottom-up information and/or top-down information. Subsequently, every grid is assigned a saliency value based on its evaluation result, so that a saliency map can be created for the image. Finally, patch sampling from the input image is performed on the basis of the obtained saliency map. Furthermore, we propose a method to fuse these two kinds of information. The proposed methods are evaluated on both object categories and scene categories. Experiment results demonstrate their effectiveness.     

Boosted kernel for image categorization

Recent machine learning techniques have demonstrated their capability for identifying image categories using image features. Among these techniques, Support Vector Machines (SVM) present good results for example in Pascal Voc challenge 2011 [8], particularly when they are associated with a kernel function [28, 35]. However, nowadays image categorization task is very challenging owing to the sizes of benchmark datasets and the number of categories to be classified. In such a context, lot of effort has to be put in the design of the kernel functions and underlying semantic features. In the following of the paper we call semantic features the features describing the (semantic) content of an image. In this paper, we propose a framework to learn an effective kernel function using the Boosting paradigm to linearly combine weak kernels. We then use a SVM with this kernel to categorize image databases. More specifically, this method create embedding functions to map images in a Hilbert space where they are better classified. Furthermore, our algorithm benefits from boosting process to learn this kernel with a complexity linear with the size of the training set. Experiments are carried out on popular benchmarks and databases to show the properties and behavior of the proposed method. On the PASCAL VOC2006 database, we compare our method to simple early fusion, and on the Oxford Flowers databases we show that our method outperforms the best Multiple Kernel Learning (MKL) techniques of the literature.     

基于Nyström 低阶近似的半监督流形排序图像检索

实际图像检索过程中,用户提供的相关反馈有限,但存在大量未标记图像数据. 本文在前期半监督流形图像检索工作的基础上,提出一种基于Nystrm低阶 近似的半监督流形排序图像检索方法.通过采用半监督的流形正则化框架, 将图像数据嵌入到低维流形结构中进行分类排序,以充分利用大量未标记数据, 并兼顾分类误差、数据分布的几何结构以及分类函数的复杂性.针对半监督学习速度缓慢的问题, 基于Nystrm低阶近似对学习过程进行加速.在较大规模的Corel图像数据集上进行了检索实验, 实验结果表明该方法能获得较好的效果.