Ran Chang

Image retrieval using transaction-based and SVM-based learning in relevance feedback sessions

This paper introduces a composite relevance feedback approach for image retrieval using transaction-based and SVM-based learning. A transaction repository is dynamically constructed by applying these two learning techniques on positive and negative session-term feedback. This repository semantically relates each database image to the query images having been used to date. The query semantic feature vector can then be computed using the current feedback and the semantic values in the repository. The correlation measures the semantic similarity between the query image and each database image. Furthermore, the SVM is applied on the session-term feedback to learn the hyperplane for measuring the visual similarity between the query image and each database image. These two similarity measures are normalized and combined to return the retrieved images. Our extensive experimental results show that the proposed approach offers average retrieval precision as high as 88.59% after three iterations. Comprehensive comparisons with peer systems reveal that our system yields the highest retrieval accuracy after two iterations.

A fuzzy combined learning approach to content-based image retrieval

We propose a fuzzy combined learning approach to construct a relevance feedback-based content-based image retrieval (CBIR) system for efficient image search. Our system uses a composite short-term and long-term learning approach to learn the semantics of an image. Specifically, the short-term learning technique applies fuzzy support vector machine (FSVM) learning on user labeled and additional chosen image blocks to learn a more accurate boundary for separating the relevant and irrelevant blocks at each feedback iteration. The long-term learning technique applies a novel semantic clustering technique to adaptively learn and update the semantic concepts at each query session. A predictive algorithm is also applied to find images most semantically related to the query based on the semantic clusters generated in the long-term learning. Our extensive experimental results demonstrate the proposed system outperforms several state-of-the-art peer systems in terms of both retrieval precision and storage space.

A noise-resilient collaborative learning approach to content-based image retrieval

We propose to combine short‐term block‐based fuzzy support vector machine (FSVM) learning and long‐term dynamic semantic clustering (DSC) learning to bridge the semantic gap in content‐based image retrieval. The short‐term learning addresses the small sample problem by incorporating additional image blocks to enlarge the training set. Specifically, it applies the nearest neighbor mechanism to choose additional similar blocks. A fuzzy metric is computed to measure the fidelity of the actual class information of the additional blocks. The FSVM is finally applied on the enlarged training set to learn a more accurate decision boundary for classifying images. The long‐term learning addresses the large storage problem by building dynamic semantic clusters to remember the semantics learned during all query sessions. Specifically, it applies a cluster‐image weighting algorithm to find the images most semantically related to the query. It then applies a DSC technique to adaptively learn and update the semantic categories. Our extensive experimental results demonstrate that the proposed short‐term, long‐term, and collaborative learning methods outperform their peer methods when the erroneous feedback resulting from the inherent subjectivity of judging relevance, user laziness, or maliciousness is involved. The collaborative learning system achieves better retrieval precision and requires significantly less storage space than its peers.

Image authentication and tamper detection using two complementary watermarks

This paper presents a novel semi-fragile watermarking scheme for image authentication and tamper detection. The proposed scheme extracts content-based image features from the approximation subband in the wavelet domain to generate two complementary watermarks. Specifically, we generate an edge-based watermark sequence to detect any changes after manipulations. This edge-based watermark encodes the invariant relationship between quantized wavelet coefficients after incidental distortions. We also generate the content-based watermark to localize tampered regions. Both watermarks are embedded into the high frequency wavelet domain to ensure the watermark invisibility. Our extensive experimental results show that the proposed scheme outperforms the peer scheme and can successfully identify intentional tampering and incidental modification, and localize maliciously tampered regions.

Learning from Relevance Feedback Sessions using a K-Nearest-Neighbor-Based Semantic Repository

This paper introduces a flexible learning approach for image retrieval with relevance feedback. A semantic repository is constructed offline by applying the k-nearest-neighbor-based relevance learning on both positive and negative session-term feedback. This repository semantically relates each database image to a set of training images chosen from all semantic categories. The query semantic feature vector can then be computed using the current feedback and the semantic values in the repository. The dot product measures the semantic similarity between the query and each database image. Our extensive experimental results show that the semantic repository (6% size and 1/3 filling rate) based approach alone offers average retrieval precision as high as 94% on the first iteration. Comprehensive comparisons with peer systems reveal that our system yields the highest retrieval accuracy. Furthermore, the proposed approach can be easily incorporated into peer systems to achieve substantial improvement in retrieval accuracy for all feedback steps.

A retrieval pattern-based inter-query learning approach for content-based image retrieval

This paper presents a retrieval pattern-based inter-query learning approach for image retrieval with relevance feedback. The proposed system combines SVM-based low-level learning and semantic correlation-based high-level learning to construct a semantic matrix to store retrieval patterns of a certain number of randomly chosen query sessions. Users relevance feedback is utilized for updating high-level semantic features of the query image and each database image. Extensive experiments demonstrate our system outperforms three peer systems in the context of both correct and erroneous feedback. Our retrieval system also achieves high retrieval accuracy after the first iteration.

Inter-query semantic learning approach to image retrieval

This paper presents an inter-query semantic learning approach for image retrieval with relevance feedback. The proposed system combines the kernel biased discriminant analysis (KBDA) based low-level learning and semantic log file (SLF) based high-level learning to achieve high retrieval accuracy after the first iteration. Users relevance feedback is utilized for updating both low-level and high-level features of the query image. Extensive experiments demonstrate our system outperforms three peer systems.

A fuzzy statistical correlation-based approach to content-based image retrieval

This paper presents an effective fuzzy long-term semantic learning method for relevance feedback-based image retrieval. The proposed system uses a statistical correlation-based method to dynamically learn the semantic relations between any relevance feedback image pairs. The learned semantic relations are used to automatically expand the feedback set to balance the number of positive and negative images to improve the fuzzy SVM-based low-level learning. They are also used to more accurately estimate the semantic similarity between the query image and database images. The overall similarity score between query and database images is computed by combining both low-level visual and high-level semantic similarity measures. Our extensive experimental results show the proposed system achieves the best retrieval accuracy when compared with three peer systems.