Lei Ye

Content Based Image Retrieval Using Unclean Positive Examples

Conventional content-based image retrieval (CBIR) schemes employing relevance feedback may suffer from some problems in the practical applications. First, most ordinary users would like to complete their search in a single interaction especially on the Web. Second, it is time consuming and difficult to label a lot of negative examples with sufficient variety. Third, ordinary users may introduce some noisy examples into the query. This correspondence explores solutions to a new issue that image retrieval using unclean positive examples. In the proposed scheme, multiple feature distances are combined to obtain image similarity using classification technology. To handle the noisy positive examples, a new two-step strategy is proposed by incorporating the methods of data cleaning and noise tolerant classifier. The extensive experiments carried out on two different real image collections validate the effectiveness of the proposed scheme.

Image Content Annotation Based on Visual Features

Automatic image content annotation techniques attempt to explore structural visual features of images that describe image content and associate them with image semantics. In this paper, two types of concept spaces, atomic concept and collective concept spaces, are defined and the annotation problems in those spaces are formulated as feature classification and Bayesian inference, respectively. A scheme of image content annotation in this framework is presented and evaluated as an application of photo categorization using MPEG-7 VCE2 dataset and its ground truth. The experimental results show a promising performance

Secure Image Retrieval Based on Visual Content and Watermarking Protocol

As an interesting application on cloud computing, content-based image retrieval (CBIR) has attracted a lot of attention, but the focus of previous research work was mainly on improving the retrieval performance rather than addressing security issues such as copyrights and user privacy. With an increase of security attacks in the computer networks, these security issues become critical for CBIR systems. In this paper, we propose a novel two-party watermarking protocol that can resolve the issues regarding user rights and privacy. Unlike the previously published protocols, our protocol does not require the existence of a trusted party. It exhibits three useful features: security against partial watermark removal, security in watermark verification and non-repudiation. In addition, we report an empirical research of CBIR with the security mechanism. The experimental results show that the proposed protocol is practicable and the retrieval performance will not be affected by watermarking query images.

Watermarking protocol of secure verification

The secure verification is important for watermarking pro- tocols. A malicious arbitrator is able to remove an original watermark from an unauthorized copy of the digital content as a result of a security breach in the phase of arbitration and resell multiple copies of it with impunity. We propose a novel buyer-seller watermarking protocol of secure verification. In this scheme, a seller permutes an original watermark provided by a trusted Watermarking Certification Authority (WCA) and embeds it into digital content in an encrypted domain. In case an unauthorized copy is found, the seller can re- cover the original watermark from the watermark extracted from the copy and sends it to an arbitrator. Without the knowledge of permu- tations applied by the seller, the arbitrator is unable to remove the permuted watermark from the digital content. Hence, verification is secured. As an additional advantage of the proposed protocol, arbi- tration can be conducted without the need for the cooperation of the

Robust image retrieval with hidden classes

HighlightsWe address a new robust problem, named hidden classes, in content-based image retrieval (CBIR).We propose a new robust CBIR scheme using multi-image queries to tackle the difficule problem.We develop a novel query detection technique to separate queries as common or novel according to their underlying classes.We apply a self-adaptive retrieval strategy to handle different types of queries automatically.We design and carry out a number of experiments to demonstrate the effectiveness of our scheme. For the purpose of content-based image retrieval (CBIR), image classification is important to help improve the retrieval accuracy and speed of the retrieval process. However, the CBIR systems that employ image classification suffer from the problem of hidden classes. The queries associated with hidden classes cannot be accurately answered using a traditional CBIR system. To address this problem, a robust CBIR scheme is proposed that incorporates a novel query detection technique and a self-adaptive retrieval strategy. A number of experiments carried out on the two popular image datasets demonstrate the effectiveness of the proposed scheme.

Watermarking protocol for protecting user's right in content based image retrieval

Content based image retrieval (CBIR) is a technique to search for images relevant to the users query from an image collection. In last decade, most attention has been paid to improve the retrieval performance. However, there is no significant effort to investigate the security concerning in CBIR. Under the query by example (QBE) paradigm, the user supplies an image as a query and the system returns a set of retrieved results. If the query image includes users private information, an untrusted server provider of CBIR may distribute it illegally, which leads to the users right problem. In this paper, we propose an interactive watermarking protocol to address this problem. A watermark is inserted into the query image by the user in encrypted domain without knowing the exact content. The server provider of CBIR will get the watermarked query image and uses it to perform image retrieval. In case where the user finds an unauthorized copy, a watermark in the unauthorized copy will be used as evidence to prove that the users legal right is infringed by the server provider.

An Unified Framework Based on p-Norm for Feature Aggregation in Content-Based Image Retrieval

Feature aggregation is a critical technique in content- based image retrieval systems that employ multiple visual features to characterize image content. In this paper, the p-norm is introduced to feature aggregation that provides a framework to unify various previous feature aggregation schemes such as linear combination, Euclidean distance, Boolean logic and decision fusion schemes in which previous schemes are instances. Some insights of the mechanism of how various aggregation schemes work are discussed through the effects of model parameters in the unified framework. Experiments show that performances vary over feature aggregation schemes that necessitates an unified framework in order to optimize the retrieval performance according to individual queries and user query concept. Revealing experimental results conducted with IAPR TC-12 ImageCLEF2006 benchmark collection that contains over 20,000 photographic images are presented and discussed.

Image retrieval based on bag of images

Conventional relevance feedback schemes may not be suitable to all practical applications of content-based image retrieval (CBIR), since most ordinary users would like to complete their search in a single interaction, especially on the web search. In this paper, we explore a new approach to improve the retrieval performance based on a new concept, bag of images, rather than relevance feedback. We consider that image collection comprises of image bags instead of independent individual images. Each image bag includes some relevant images with the same perceptual meaning. A theoretical case study demonstrates that image retrieval can benefit from the new concept. A number of experimental results show that the CBIR scheme based on bag of images can improve the retrieval performance dramatically.

Image retrieval using noisy query

In conventional content based image retrieval (CBIR) employing relevance feedback, one implicit assumption is that both pure positive and negative examples are available. However it is not always true in the practical applications of CBIR. In this paper, we address a new problem of image retrieval using several unclean positive examples, named noisy query, in which some mislabeled images or weak relevant images present. The proposed image retrieval scheme measures the image similarity by combining multiple feature distances. Incorporating data cleaning and noise tolerant classifier, a twostep strategy is proposed to handle noisy positive examples. Experiments carried out on a subset of Corel image collection show that the proposed scheme outperforms the competing image retrieval schemes.

Ranking Method for Optimizing Precision/Recall of Content-Based Image Retrieval

The ranking method is a key element of Content-based Image Retrieval (CBIR) system, which can affect the final retrieval performance. In the literature, previous ranking methods based on either distance or probability do not explicitly relate to precision and recall, which are normally used to evaluate the performance of CBIR systems. In this paper, a novel ranking method based on relative density is proposed to improve the probability based approach by ranking images in the class. The proposed method can achieve optimal precision and recall. The experiments conducted on a large photographic collection show significant improvements of retrieval performance.