Search

Image hashing is a useful technology of many multimedia systems, such as image retrieval, image copy detection, multimedia forensics and image authentication. Most of the existing hashing algorithms do not reach a good classification between robustness and discrimination and some hashing algorithms based on dimensionality reduction have high computational cost. To solve these problems, we propose a robust and fast image hashing based on two-dimensional (2D) principal component analysis (PCA) and saliency map. The saliency map determined by a visual attention model called LC (luminance contrast) method can ensure good robustness of our hashing. Since 2D PCA is a fast and efficient technique of dimensionality reduction, the use of 2D PCA helps to learn a compact and discriminative code and provide a fast speed of our hashing. Extensive experiments are carried out to validate the performances of our hashing. Classification comparison shows that our hashing is better than some state-of-the-art algorithms. Computational time comparison illustrates that our hashing outperforms some compared algorithms based on dimensionality reduction. [ABSTRACT FROM AUTHOR]

Image hashing is an efficient technology for processing digital images and has been successfully used in image copy detection, image retrieval, image authentication, image quality assessment, and so on. In this paper, we design a new image hashing with compressed sensing (CS) and ordinal measures. This hashing method uses a visual attention model called Itti model and Canny operator to construct an image representation, and exploits CS to extract compact features from the representation. Finally, the CS-based compact features are quantized via ordinal measures. L2 norm is used to judge similarity of hashes produced by the proposed hashing method. Experiments about robustness validation, discrimination test, block size discussion, selection of visual attention model, selection of quantization scheme, and effectiveness of the use of ordinal measures are conducted to verify performances of the proposed hashing method. Comparisons with some state-of-the-art algorithms are also carried out. The results illustrate that the proposed hashing method outperforms some compared algorithms in classification according to ROC (receiver operating characteristic) graph. [ABSTRACT FROM AUTHOR]

Color vector angle (CVA) is an important feature of processing color images and has been successfully developed and used in real applications, such as edge detection, indexing and retrieval of images. However, it is unsolved how to apply the CVA to efficiently generating an image hash. Also, most image hashing algorithms choose luminance component of color image for hash generation and cannot well capture the color information of images. To tackle these issues, we study efficient image hashing algorithms with the histogram of CVAs, called HCVA hashing. The histogram is first extracted from those angles that are in the biggest circle inscribed inside the normalized image. And then, it is compressed to make a short hash. We conducted some experiments to assess the performance, and illustrated that the DCT (Discrete Cosine Transform) is the best one of that cooperating with HCVA at generating hashes, as well as the HCVA hashing is robust and promising. [ABSTRACT FROM AUTHOR]

Colour space has been widely used in digital image processing, but its selection is rarely discussed in image hashing. Aiming at this problem, we discuss colour space selection by evaluating classification performances of typical hashing algorithms under YCbCr colour space, CIEL*a*b* colour space, HSV colour space, and HSI colour space. Our contributions are two sides. (1) We find that the regularly used YCbCr colour space cannot reach desirable classification performance and HSV colour space outperforms other colour spaces. (2) We analyse classification performances of D-DCT hashing, NMF-NMF-SQ hashing, RT-DCT hashing, and GF-LVQ hashing under different colour spaces, which are the first reports of these algorithms. Receiver operating characteristic graph is used to analyse classification experiments with large data-sets of 2220 similar image pairs and 19,900 different image pairs. [ABSTRACT FROM PUBLISHER]

Image hashing is a novel technology of multimedia processing, and finds many applications, such as image forensics, image retrieval and image indexing. Conventional image hashing algorithms have limitations in reaching desirable classification performances between rotation robustness and discrimination. Aiming at this issue, we propose a robust image hashing based on color vector angle and Canny operator. Specifically, our hashing firstly converts input image to a normalized image by interpolation and Gaussian low-pass filtering. And then, color vector angles and image edges are both extracted from the normalized image. Finally, statistical features incorporating color vector angles and image edges are calculated to form image hash. We conduct experiments with 2762 images to validate efficiency of our hashing. The experimental results show that our hashing is robust against normal digital processing, such as image rotation, brightness/contrast adjustment and JPEG compression, and reaches good discrimination. Receiver operating characteristics (ROC) curve comparisons with some state-of-the-art algorithms indicate that our hashing outperforms these compared algorithms in classification performances between robustness and discriminative capability. [ABSTRACT FROM AUTHOR]

Image hashing is an emerging technology of multimedia processing. This paper proposes a robust image hashing with dominant discrete cosine transform (DCT) coefficients. The proposed hashing converts the input image to a normalized image, divides it into non-overlapping blocks, extracts dominant DCT coefficients in the first row/column of each block to construct feature matrices, and finally conducts matrix compression by calculating and quantifying column distances. Many experiments are conducted and the results show that the proposed hashing is robust against normal digital operations and has desirable discrimination. Receiver operating characteristics (ROC) curve comparisons indicate that the proposed hashing is better than some notable image hashing. [ABSTRACT FROM AUTHOR]

Abstract: Conventional image hash functions only exploit luminance components of color images to generate robust hashes and then lead to limited discriminative capacities. In this paper, we propose a robust image hash function for color images, which takes all components of color images into account and achieves good discrimination. Firstly, the proposed hash function re-scales the input image to a fixed size. Secondly, it extracts local color features by converting the RGB color image into HSI and YCbCr color spaces and calculating the block mean and variance from each component of the HSI and YCbCr representations. Finally, it takes the Euclidian distances between the block features and a reference feature as hash values. Experiments are conducted to validate the efficiency of our hash function. Receiver operating characteristics (ROC) curve comparisons with two existing algorithms demonstrate that our hash function outperforms the assessed algorithms in classification performances between perceptual robustness and discriminative capability. [Copyright &y& Elsevier]

Structural image features are exploited to construct perceptual image hashes in this work. The image is first preprocessed and divided into overlapped blocks. Correlation between each image block and a reference pattern is calculated. The intermediate hash is obtained from the correlation coefficients. These coefficients are finally mapped to the interval [0, 100], and scrambled to generate the hash sequence. A key component of the hashing method is a specially defined similarity metric to measure the 'distance' between hashes. This similarity metric is sensitive to visually unacceptable alterations in small regions of the image, enabling the detection of small area tampering in the image. The hash is robust against content-preserving processing such as JPEG compression, moderate noise contamination, watermark embedding, re-scaling, brightness and contrast adjustment, and low-pass filtering. It has very low collision probability. Experiments are conducted to show performance of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: Semantic gap has become a bottleneck of content-based image retrieval in recent years. In order to bridge the gap and improve the retrieval performance, automatic image annotation has emerged as a crucial problem. In this paper, a hybrid approach is proposed to learn the semantic concepts of images automatically. Firstly, we present continuous probabilistic latent semantic analysis (PLSA) and derive its corresponding Expectation–Maximization (EM) algorithm. Continuous PLSA assumes that elements are sampled from a multivariate Gaussian distribution given a latent aspect, instead of a multinomial one in traditional PLSA. Furthermore, we propose a hybrid framework which employs continuous PLSA to model visual features of images in generative learning stage and uses ensembles of classifier chains to classify the multi-label data in discriminative learning stage. Therefore, the framework can learn the correlations between features as well as the correlations between words. Since the hybrid approach combines the advantages of generative and discriminative learning, it can predict semantic annotation precisely for unseen images. Finally, we conduct the experiments on three baseline datasets and the results show that our approach outperforms many state-of-the-art approaches. [Copyright &y& Elsevier]