A Locality Sensitive Low-Rank Model for Image Tag Completion.
Many visual applications have benefited from the outburst of web images, yet the imprecise and incomplete tags arbitrarily provided by users, as the thorn of the rose, may hamper the performance of retrieval or indexing systems relying on such data. In this paper, we propose a novel locality sensitive low-rank model for image tag completion, which approximates the global nonlinear model with a collection of local linear models. To effectively infuse the idea of locality sensitivity, a simple and effective pre-processing module is designed to learn suitable representation for data partition, and a global consensus regularizer is introduced to mitigate the risk of overfitting. Meanwhile, low-rank matrix factorization is employed as local models, where the local geometry structures are preserved for
the low-dimensional representation of both tags and samples. Extensive empirical evaluations conducted on three datasets demonstrate the effectiveness and efficiency of the proposed method, where our method outperforms pervious ones by a large margin.
Enhancing Sketch-Based Image Retrieval by Re-ranking and Relevance Feedback.
Sketch-based image retrieval often needs to optimize the trade-off between efficiency and precision. Index structures are typically applied to large-scale databases to realize efficient retrievals. However, the performance can be affected by quantization errors. Moreover, the ambiguousness of user-provided examples may also degrade the performance, when compared with traditional image retrieval methods. Sketch-based image retrieval systems that preserve the index structure are challenging. In this paper, we propose an effective sketch-based image retrieval approach with re-ranking and relevance feedback schemes. Our approach makes full use of the semantics in query sketches and the top ranked images of the initial results. We also apply relevance feedback to find more relevant images for the input query sketch. The integration of the two schemes results in mutual benefits and improves the performance of sketch-based image retrieval.
Nowadays, 2D barcodes have been widely used as an interface to connect potential customers and advertisement contents. However, the appearance of a conventional 2D barcode pattern is often too obtrusive for integrating into an aesthetically designed advertisement. Besides, no human readable information is provided before the barcode is successfully decoded. This paper proposes a new picture-embedding 2D barcode, called PiCode, which mitigates these two limitations by equipping a scannable 2D barcode with a picturesque appearance. PiCode is designed with careful considerations on both the perceptual quality of the embedded image and the decoding robustness of the encoded message. Comparisons with existing beautified 2D barcodes show that PiCode achieves one of the best perceptual quality for the embedded image, and maintains a better trade-off between image quality and decoding robustness in various application conditions. PiCode has been implemented in Matlab on a PC and some key building blocks have also been ported to Android and iOS platforms. Its practicality for real-world applications have been successfully demonstrated.
Social media sharing websites like Flickr allow users to annotate images with free tags, which significantly contribute to the development of the web image retrieval and organization. Tag-based image search is an important method to find images contributed by social users in such social websites. However, how to make the top ranked result relevant and with diversity is challenging. In this paper, we propose a social re-ranking system for tag-based image retrieval with the consideration of image’s relevance and diversity. We aim at re-ranking images according to their visual information, semantic information and social clues. The initial results include images contributed by different social users. Usually each user contributes several images. First we sort these images by inter-user re-ranking. Users that have higher contribution to the given query rank higher. Then we sequentially implement intra-user re-ranking on the ranked user’s image set, and only the most relevant image from each user’s image set is selected. These selected images compose the final retrieved results. We build an inverted index structure for the social image dataset to accelerate the searching process. Experimental results on Flickr dataset show that our social re-ranking method is effective and efficient.
A Methodology for Visually Lossless JPEG2000 Compression of Monochrome Stereo Images.
A methodology for visually lossless compression of monochrome stereoscopic 3D images is proposed. Visibility thresholds are measured for quantization distortion in JPEG2000. These thresholds are found to be functions of not only spatial frequency, but also of wavelet coefficient variance, as well as the gray level in both the left and right images. To avoid a daunting number of measurements during subjective experiments, a model for visibility thresholds is developed. The left image and right image of a stereo pair are then compressed jointly using the visibility thresholds obtained from the proposed model to ensure that quantization errors in each image are imperceptible to both eyes. This methodology is then
demonstrated via a particular 3D stereoscopic display system with an associated viewing condition. The resulting images are visually lossless when displayed individually as 2D images, and also when displayed in stereoscopic 3D mode.
An Efficient DCT-Based Image Compression System Based on Laplacian Transparent Composite Model.
Recently, a new probability model dubbed the Laplacian transparent composite model (LPTCM) was developed for DCT coefficients, which could identify outlier coefficients in addition to providing superior modeling accuracy. In this paper,
we aim at exploring its applications to image compression. To this end, we propose an efficient nonpredictive image compression system, where quantization (including both hard-decision quantization (HDQ) and soft-decision quantization (SDQ)) and entropy coding are completely redesigned based on the LPTCM. When tested over standard test images, the proposed system achieves overall coding results that are among the best and similar to those of H.264 or HEVC intra (predictive) coding, in terms of rate versus visual quality. On the other hand, in terms of rate versus objective quality, it significantly outperforms baseline JPEG by more than 4.3 dB in PSNR on average, with a moderate increase on complexity, and ECEB, the state-of-the-art nonpredictive image coding, by 0.75 dB when SDQ is OFF (i.e., HDQ case), with the same level of computational complexity, and by 1 dB when SDQ is ON, at the cost of slight increase in complexity. In comparison with H.264 intracoding, our system provides an overall 0.4-dB gain or so, with dramatically reduced computational complexity; in comparison with HEVC intracoding, it offers comparable coding performance in the high-rate region
or for complicated images, but with only less than 5% of the HEVC intracoding complexity. In addition, our proposed system also offers multiresolution capability, which, together with its comparatively high coding efficiency and low complexity, makes it a good alternative for real-time image processing applications.
This paper presents a technique for content-based image retrieval (CBIR) by exploiting the advantage of lowcomplexity ordered-dither block truncation coding (ODBTC) for the generation of image content descriptor. In the encoding step, ODBTC compresses an image block into corresponding quantizers and bitmap image. Two image features are proposed to index an image, namely, color co-occurrence feature (CCF) and bit pattern features (BPF), which are generated directly from the ODBTC encoded data streams without performing the decoding process. The CCF and BPF of an image are simply derived from the two ODBTC quantizers and bitmap, respectively, by involving the visual codebook. Experimental results show that the proposed method is superior to the block truncation coding image retrieval systems and the other earlier methods, and thus prove that the ODBTC scheme is not only suited for image compression, because of its simplicity, but also offers a simple and effective descriptor to index images in CBIR system.
The use of local prediction in difference expansion reversible watermarking provides very good results, but at the cost of computing for each pixel a least square predictor in a square block centered on the pixel. This correspondence investigates the reduction of the mathematical complexity by computing distinct predictors not for pixels, but for groups of pixels. The same predictors are recovered at detection. Experimental results for the case of prediction on the rhombus defined by the four horizontal and vertical neighbors are provided. It is shown that by computing a predictor for a pair of pixels, the computational cost is halved without any loss in performance. A small loss appears for groups of three and four pixels with the advantage of reducing the mathematical complexity to a third and a fourth, respectively.
Statistical Model of JPEG Noises and Its Application in Quantization Step Estimation.
In this paper, we present a statistical analysis of JPEG noises, including the quantization noise and the rounding noise during a JPEG compression cycle. The JPEG noises in the first compression cycle have been well studied; however, so far less attention has been paid on the statistical model of JPEG noises in higher compression cycles. Our analysis reveals that the noise distributions in higher compression cycles are different from those in the first compression cycle, and they are dependent on the quantization parameters used between two successive cycles. To demonstrate the benefits from the analysis, we apply the statistical model in JPEG quantization step estimation. We construct a sufficient statistic by exploiting the derived noise distributions, and justify that the statistic has several special properties to reveal the ground-truth quantization step. Experimental results demonstrate that the proposed estimator can uncover JPEG compression history with a satisfactory performance.
An Attribute-assisted Re-ranking Model for Web Image Search.
In this paper, we present a Image search re-ranking is an effective approach to refine the text-based image search result. Most existing re-ranking approaches are based on low-level visual features. In this paper, we propose to exploit semantic attributes for image search re-ranking. Based on the classifiers for all the pre-defined attributes, each image is represented by a attribute feature consisting of the responses from these classifiers. A hyper-graph is then used to model the relationship between images by integrating low-level visual features and attribute features. Hyper-graph ranking is performed to order the images. Its basic principle is that visually similar images should have similar ranking scores. We conduct experiments on 300 queries in MSRA-MM V2.0 dataset. The experimental results demonstrate the effectiveness of our approach.
An Hybrid Distance Metric Learning for Image Ranking.
In this paper, we present a Image ranking technique that is useful for retrieve the related image present in the image database. Using Query image the distance is calculated for each image in database. Based on the distance the image will be ranked. The distance is calculated using distance metric learning (DML). First we present linear distance metric learning model that tries to preserve both the local geometry information and the ordinal relationship of the data. Next we develop single kernel and multiple kernel based distance metric leaning that performs different kernel operators on different kinds of image features. Finally we propose a hybrid distance approach for image ranking. The hybrid approach contains the local, linear and non-linear distance metric learning.
Query Adaptive Image Search System using Image Ranking.
In this paper, we present a statistical analysis of Scalable image search based on visual similarity has been an active topic of research in recent years. This paper first model retrieval ranks as graphs of candidate images and propose a graph-based query specific fusion approach, where multiple graphs are merged and re-ranked by conducting a link analysis on a fused graph. Next it proposed a query-adaptive image search system. Query adaptive weights are computed between query image and data base images. Based on the weights the images are ranked. The sorted ranked images are retrieved for user.
Web Image Re-Ranking Using Query-Specific Semantic Signatures.
In this paper, a new technique is proposed for web-scale image re-ranking. The mentioned technique is very useful in giving specific results to users in just one click. In this, different semantic spaces for different query keywords can be found offline independently and automatically. Semantic signatures of the images are acquired by projecting their visual features into their related semantic spaces and these semantic signatures are compacted using Hashing techniques. At the online stage, these compacted semantic signatures of images are to be compared to re-rank images. It considerably betters the efficiency and accuracy of web-image search and re-ranking.