交互式图像推荐系统研究

随着互联网信息的快速发展,图像信息已经成了一个重要的信息来源,但是对用户来说很难找到自己需要的特定的图像,构建了一个交互式的图像推荐系统,用颜色直方图特征或者Gabor纹理特征来表示图像的内容,根据图像的视觉特征采用一种基于核的K均值聚类方法将图像聚成多类,采用hyperbolic显示技术,将图像按照视觉特征显示在屏幕的不同区域。结果显示该方法可以有效快速地帮助用户在图像数据库中找到自己需要的图像。     

一种交互式图像去雾方法

在二色大气散射模型的基础上,根据雾对景物退化与景物深度的指数关系,采用交互方式,通过附加一些主观判断作为先验信息,从单幅图像中估计出景物深度,进行对比度增强,有效实现了彩色图像去雾。同时针对浓雾退化图像处理结果较暗的情况,进行了正态截取拉伸,提高了图像亮度,获得了较好的视觉效果。     

Object density-based image segmentation and its applications in biomedical image analysis

In many applications of medical image analysis, the density of an object is the most important feature for isolating an area of interest (image segmentation). In this research, an object density-based image segmentation methodology is developed, which incorporates intensity-based, edge-based and texture-based segmentation techniques. The proposed method consists of three main stages: preprocessing, object segmentation and final segmentation. Image enhancement, noise reduction and layer-of-interest extraction are several subtasks of preprocessing. Object segmentation utilizes a marker-controlled watershed technique to identify each object of interest (OI) from the background. A marker estimation method is proposed to minimize over-segmentation resulting from the watershed algorithm. Object segmentation provides an accurate density estimation of OI which is used to guide the subsequent segmentation steps. The final stage converts the distribution of OI into textural energy by using fractal dimension analysis. An energy-driven active contour procedure is designed to delineate the area with desired object density. Experimental results show that the proposed method is 98% accurate in segmenting synthetic images. Segmentation of microscopic images and ultrasound images shows the potential utility of the proposed method in different applications of medical image processing.     

Quantum computation for large-scale image classification

Due to the lack of an effective quantum feature extraction method, there is currently no effective way to perform quantum image classification or recognition. In this paper, for the first time, a global quantum feature extraction method based on Schmidt decomposition is proposed. A revised quantum learning algorithm is also proposed that will classify images by computing the Hamming distance of these features. From the experimental results derived from the benchmark database Caltech 101, and an analysis of the algorithm, an effective approach to large-scale image classification is derived and proposed against the background of big data.     

Interactive and automatic image recognition system

We have developed a vision system which learns to recognize many kinds of two-dimensional objects in many kinds of images. Image processing program modules are classified based on functions in the library. First, the user can teach the system the way to recognize objects in the image interactively testing the effectiveness of each program by trial and error. The system stores what it learns in the long-term memory calledmodel. The model is improved by analyzing training images in the same way. Once the model is completed, the system can automatically analyze images in the same category and recognize the expected objects in a top-down way driven by the model. Since a model is built for images in each category, the system can recognize various kinds of images simply by retrieving the corresponding models.     

Interactive image segmentation using probabilistic hypergraphs

This paper introduces a novel interactive framework for segmenting images using probabilistic hypergraphs which model the spatial and appearance relations among image pixels. The probabilistic hypergraph provides us a means to pose image segmentation as a machine learning problem. In particular, we assume that a small set of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels by learning on a hypergraph via minimizing a quadratic smoothness term formed by a hypergraph Laplacian matrix subject to the known label constraints. We derive a natural probabilistic interpretation of this smoothness term, and provide a detailed discussion on the relation of our method to other hypergraph and graph based learning methods. We also present a front-to-end image segmentation system based on the proposed method, which is shown to achieve promising quantitative and qualitative results on the commonly used GrabCut dataset.     

Interactive image completion with perspective correction

We present an interactive system for fragment-based image completion which exploits information about the approximate 3D structure in a scene in order to estimate and apply perspective corrections when copying a source fragment to a target position. Even though implicit 3D information is used, the interaction is strictly 2D, which makes the user interface very simple and intuitive. We propose different interaction metaphors in our system for providing 3D information interactively. Our search and matching procedure is done in the Fourier domain, and hence it is very fast and it allows us to use large fragments and multiple source images with high resolution while still obtaining interactive response times. Our image completion technique also takes user-specified structure information into account where we generalize the concept of feature curves to arbitrary sets of feature pixels. We demonstrate our technique on a number of difficult completion tasks.     

Interactive image segmentation via kernel propagation

In this paper, we propose a new approach to interactive image segmentation via kernel propagation (KP), called KP Cut. The key to success in interactive image segmentation is to preserve characteristics of the user?s interactive input and maintain data-coherence effectively. To achieve this, we employ KP which is very effective in propagating the given supervised information into the entire data set. KP first learns a small-size seed-kernel matrix, and then propagates it into a large-size full-kernel matrix. It is based on a learned kernel, and thus can fit the given data better than a predefined kernel. Based on KP, we first generate a small-size seed-kernel matrix from the user?s interactive input. Then, the seed-kernel matrix is propagated into the full-kernel matrix of the entire image. During the propagation, foreground objects are effectively segmented from background. Experimental results demonstrate that KP Cut effectively extracts foreground objects from background, and outperforms the state-of-the-art methods for interactive image segmentation.     

Interactive image enhancement by fuzzy relaxation

In this paper,an interactive image enhancement(IIE)technique based on fuzzy relaxation is presented,which allows the user to select different intensity levels for enhancement and intermit the enhancement process according to his/her preference in applications.First,based on an analysis of the convergence of a fuzzy relaxation algorithm for image contrast enhancement,an improved version of this algorithm,which is called FuzzIIE Method 1,is suggested by deriving a relationship between the convergence regions and the parameters in the transformations defined in the algorithm.Then a method called FuzzIIE Method 2 is introduced by using a different fuzzy relaxation function,in which there is no need to re-select the parameter values for interactive image enhancement. Experimental results are presented demonstrating the enhancement capabilities of the proposed methods under different conditions.     

A flexible mixed-signal image processing pipeline using 3D chip stacks

This work presents a highly flexible mixed-signal CMOS image sensor suitable for smart camera applications. These systems need to fit different constraints regarding power consumption, speed and quality, and the optimal compromise may differ depending on the application. Moreover, the best implementation of a desired image processing task may be in the analog or the digital domain, or even a combined computation. Different aspects starting from the image sensor and signal acquisition up to the pre-processing in analog and digital domain are investigated in this paper to optimize not just one part of the system, but the whole system altogether. Moreover, it is shown that analog processing algorithms can improve signal quality, processing speed and latency while being able to save power, which is important for real-time systems. In order to be able to carry out spatial operations, the state-of-the-art sensor is modified to be able to read out multiple pixels at the same time. This allows analog spatial filter operations which consume significantly less power. As an example, an averaging filter is described which needs less than 5.3 % of the power–time product of a digital implementation for one computation. To enhance data throughput and flexibility, 3D chip stacking is proposed to partition the sensor in smaller units and enable massively parallel processing.     

Interactive search and browsing interface for large-scale visual repositories

Due to the rapid proliferation of both user-generated and broadcasted content, the interfaces for search and browsing of visual media have become increasingly important. This paper presents a novel intuitive interactive interface for browsing of large-scale image and video collections. It visualises underlying structure of the dataset by the size and spatial relations of displayed images. In order to achieve this, images or video key-frames are initially clustered using an unsupervised graph-based clustering algorithm. By selecting images that are hierarchically laid out on the screen, user can intuitively navigate through the collection or search for specific content. The extensive experimental results based on user evaluation of photo search, browsing and selection as well as interactive video search demonstrate good usability of the presented system and improvement when compared to the standard methods for interaction with large-scale image and video collections.     

Fuzzy modified cuckoo search for biomedical image segmentation

Knowledge and Information Systems - In this article, a new method is proposed for biomedical image segmentation. The proposed method for biomedical image segmentation will be known as fuzzy...     

Adaptive relevance feedback for large-scale image retrieval

Content-based image retrieval aims at substituting traditional indexing based on manual annotation by using automatically-extracted visual indexing features. Novel techniques are needed however to efficiently deal with the semantic gap (i.e. the partial match between the low-level features and the visual content). Here, we investigate a query-free retrieval approach first proposed by Ferecatu and Geman. This approach relies solely on an iterative relevance feedback mechanism that drives a heuristic sampling of the collection, and aims to take explicitly into account the semantic gap. Our contributions are related to three complementary aspects. First, we formalize a large-scale approach based on a hierarchical tree-like organization of the images computed off-line. Second, we propose a versatile modulation of the exploration/exploitation trade-off based on the consistency of the system internal states between successive iterations. Third, we elaborate a long-term optimization of the similarity metric based on the user searching session logs accumulated off-line. We implemented a web-application that integrates all our contributions, and distribute it under the AGPL Version 3 free software license. We organized user-based evaluation campaigns using ImageNet dataset, and show empirically that our contributions significantly improve the retrieval performance of the original framework, that they are complementary to each other, and that their overall integration is consistently beneficial.     

Discrete semi-supervised learning for multi-label image classification and large-scale image retrieval

Multimedia Tools and Applications - Multi-label image classification is a critical problem in image semantic learning. Traditional semi-supervised multi-label learning methods are mainly based on...     

一种用于大规模图像分类的可扩展学习算法

随着大规模图像分类数据集的出现,设计一种可扩展的、高效的多类分类算法成为目前一个重要的挑战。基于迹范数正则惩罚函数,提出了一种新的大规模多类图像分类的可扩展学习算法。把具有挑战性的非光滑优化问题重构为一个带l1正则惩罚的无穷维优化问题,进而设计了一个简单而有效的加速坐标下降算法。展示了如何在量化的密集视觉特征的压缩域中进行高效的矩阵计算,该压缩域有100000个例子,1000多维特征和100多类图片。在图像网的子集“Fungeus”,“Ungulate”和“Vehicles”上的实验结果表明,提出方法的性能明显优于目前最先进的16高斯Fisher向量方法。     

基于颜色融合的交互式图像二次着色方法*

针对灰度图像彩色化技术应用于彩色图像二次着色时往往忽略掉原始图像所带的色彩信息的问题,提出了一种基于最短距离颜色融合的交互式彩色图像二次着色方法,通过有效利用原始图像中的色彩信息降低用户交互复杂度。计算过程中采用分层采样与随机采样相结合的策略,确保种子像素合理分布,在颜色融合过程中增加动态权值调整,减少笔画位置对着色结果的影响。实验结果说明该方法与现有颜色扩展着色方法相比较,其结果不再过度依赖于初始用户标记的位置,不需要用户进行复杂的彩色线条标记就能够得到不错的着色效果。     

Interactive motion photography from a single image

In this paper, we present an interactive and computational method of creating a motion photograph from a single image. Inspired by cartoon arts, a motion photograph is a still image in which moving objects are depicted as informative and motion-evocative. With a still image that contains moving objects, the user can add and edit various motion effects by a simple but efficient user interface. As a result, the edited object conveys an effective motion effect without blurring the object. The proposed system is so user-friendly that novices can create motion photographs without any special skills. Furthermore, the extensible nature of the system means that new effects can be developed and plugged in. The experimental results and user study show that the proposed motion photography system can produce a variety of interesting motion photographs. Compared with general image editing tools (such as Photoshop), the proposed system can create high-quality motion photographs in a significantly shorter time.     

Interactive color image segmentation with linear programming

Image segmentation is an important and fundamental task for image and vision understanding. This paper describes a linear programming (LP) approach for segmenting a color image into multiple regions. Compared with the recently proposed semi-definite programming (SDP)-based approach, our approach has a simpler mathematical formulation, and a far lower computational complexity. In particular, to segment an image of M × N pixels into k classes, our method requires only O((M N k) ^m ) complexity—a sharp contrast to the complexity of O((M N k)²ⁿ ) if the SDP method is adopted, where m and n are the polynomial complexity of the corresponding LP solver and SDP solver, respectively (in general we have m≪ n). Such a significant reduction in computation readily enables our algorithm to process color images of reasonable sizes. For example, while the existing SDP relaxation algorithm is only able to segment a toy-size image of, e.g., 10 × 10 to 30 × 30 pixels in hours time, our algorithm can process larger color image of, say, 100 × 100 to 500 × 500 image in much shorter time.     

基于超像素的多主体图像交互分割

目的 为解决多主体图像的交互分割问题,在保证分割效果的前提上,提高分割的效率,达到实时交互修改分割结果的目的, 提出基于超像素的图像多主体交互分割算法.方法 基于图像的超像素构造一个多层流网络,利用用户交互绘制的简单笔画给出多主体分割的指导信息.流网络的边权值保证利用图割算法将图像分割成多个部分后,每个部分代表图像的一个主体.允许用户交互给出标记,实时修改分割结果,直到得到满意的多主体分割.结果 通过实验显示,本文方法能得到的满意多主体分割结果,而且时间效率较高.对分辨率为449×275的图像,算法能在1 s内给出结果,满足实时修改的要求.结论 基于超像素建立的图规模较小,能大大减少图割算法的运行时间,达到用户实时交互添加新笔画信息,交互地修正分割结果的目的.利用超像素的边界信息,用户只需输入比较简单的笔画信息,分割算法就能得到正确的多主体分割结果.