It is shown that the watermarking algorithm presented in another paper [Ganic and Eskicioglu, J. Electron. Imaging 14, 043004 (2005)] has a very high probability of a false-positive answer and has its limitations in practice. Furthermore, the intrinsic reasons of the high false-alarm probability are as follows: the basis space of singular value decomposition is image content dependent, there is no one-to-one correspondence between singular value vector and image content, because singular value vectors have no information on the structure of image. Thus, the most important reason is a result of a false conception to insert watermark singular value vectors without information on the structure of the watermark. Finally, some examples are given to prove our results of theoretical analysis.

A new procedure for watermarking in the 8×8 block-based discrete cosine transform (DCT) domain (used for JPEG compression) is proposed. The influence of JPEG quantization on watermarked coefficients and on watermark is considered. The criterion for coefficients selection is derived, providing robustness for an arbitrary quantization degree. The modified form of coefficients probability density function (pdf) leads to the class of modified optimal detectors. Theoretical results are illustrated on various examples. Efficiency of the proposed procedure is shown in the presence of different quantization degrees, and other common attacks.

We present different computational strategies for colorimetric characterization of scanners using multidimensional polynomials. The designed strategies allow us to determine the coefficients of an a priori fixed polynomial, taking into account different color error statistics. Moreover, since there is no clear relationship between the polynomial chosen for the characterization and the intrinsic characteristics of the scanner, we show how genetic programming could be used to generate the best polynomial. Experimental results on different devices are reported to confirm the effectiveness of our methods with respect to others in the state of the art.

An algorithm is presented for the detection of textured areas in natural images. Texture detection has potential application to image enhancement, tone correction, defect detection, content classification, and image segmentation. For example, texture detection may be useful for object detection when combined with color models and other descriptors. Sky, e.g., is generally smooth, and foliage is textured. The texture detector presented here is based on the intuition that texture in a natural image is comprised of many components. The measure we develop examines the structure of local regions of the image. This structural approach enables us to detect both structured and unstructured textures at many scales. Furthermore, it distinguishes between edges and texture, and also between texture and noise. Automatic detection results are shown to match human classification of corresponding image areas.

H.264 adopts multiple reference frames for motion estimation. This new feature significantly improves the prediction accuracy of intercoding blocks, but it results in a considerable increase in encoder complexity. The reference software JM adopts the full search scheme of which the increased computation is in proportion to the number of searched reference frames. However, the reduction of prediction residues is highly dependent on the nature of sequences, not on the number of searched frames. We propose a fast multiframe selection algorithm to deduct unnecessary reference frame searches, where the nearest reference frame (ref₀) is first searched, and the motion vectors from ref₀ compose motion field distribution. Based on the spatial and temporal consistencies of the motion field, only a small number of MBs select multiframe motion estimation. Simulation results show that the proposed algorithm can reduce more than 50% motion estimation computation cost on average and still maintain similar coding efficiency.

A new fuzzy-rule-based algorithm for the denoising of video sequences corrupted with additive Gaussian noise is presented. The proposed method constitutes a fuzzy-logic-based improvement of a recent detail and motion adaptive multiple class averaging filter (MCA). The method is first explained in the pixel domain for grayscale sequences, and is later extended to the wavelet domain and to color sequences. Experimental results show that the noise in digital image sequences is efficiently removed by the proposed fuzzy motion and detail adaptive video filter (FMDAF), and that the method outperforms other state of the art filters of comparable complexity on different video sequences.

We present an order-statistics-based vector filter for the removal of impulsive noise from color images. The filter preserves the edges and fine image details by switching between the identity (no filtering) operation and the vector median filter operation based on the robust univariate median operator. Experiments on a diverse set of images and comparisons with state of the art filters shows that the proposed filter combines simplicity, flexibility, excellent filtering quality, and low computational requirements.

We propose a system with image authentication and cross-recovery ability to protect a group of n given digital images. The system is a (r,n) threshold scheme (r is a prespecified threshold satisfying 2≤r<n). Any r of these images can reconstruct the whole group of n images, but less than r images cannot. Therefore, the system has cross-recovery ability because if some [up to (n-r)] images in the group are destroyed or lost in a distributed storage scheme or transmission mission, the destroyed or lost can be rebuilt vividly by the mutual support of r survived members. The design is composed of compression, a two-layer sharing, cryptographic hash function, and information hiding.

An integrated computer-aided detection (CAD) scheme was developed for detecting and classifying metaphase chromosomes. The CAD scheme's performance and robustness is assessed. This scheme includes an automatic metaphase-finding module and a karyotyping module, and it was applied to a testing database with 200 digital microscopic images. The automatic metaphase-finding module detects analyzable metaphase cells using a feature-based artificial neural network (ANN). The ANN-generated outputs are analyzed by a receiver operating characteristics (ROC) method, and the area under the ROC curve is 0.966. Then, the automatic karyotyping module classifies individual chromosomes of this cell into 24 types. In this module, a two-layer decision tree-based classifier with eight ANNs established in its connection nodes was optimized by a genetic algorithm. Chromosomes are first classified into seven groups by the ANN in the first layer. The chromosomes in these groups are then separately classified by seven ANNs into 24 types in the second layer. The classification accuracy is 94.5% in the first layer. Six ANNs achieved the accuracy above 95% and only one had lessened performance (80.6%) in the second layer. The overall classification accuracy is 91.5% as compared with 86.7% in the previous study using two independent datasets randomly acquired from our genetic laboratory. The results demonstrate that this automated scheme achieves high and robust performance in identification and classification of metaphase chromosomes.

Liquid crystal displays (LCDs) are replacing analog film in radiology and reducing diagnosis times. Their typical dynamic range, however, can be too low for some applications, and their poor ability to reproduce low-luminance areas represents a critical drawback. The black level of an LCD can be drastically improved by stacking two liquid crystal panels in series. In this way the global transmittance is the pointwise product of the transmittances of the two panels and the theoretical dynamic range is squared. Such a high dynamic range (HDR) display also permits the reproduction of a larger number of gray levels, increasing the bit depth of the device. The two panels, however, are placed at a small distance from each other due to mechanical constraints, and this introduces a parallax error when the display is observed off-axis. A complex, spatially adaptive algorithm is therefore necessary to generate the images used to drive the two panels. We describe the characteristics of a prototype dual-layer HDR display and discuss the issues involved in the image-splitting algorithms. We propose some solutions and analyze their performance, giving a measure of the capabilities and limitations of the device.

This paper presents a low-cost and high-speed architecture of bicubic convolution interpolation for high-quality digital image scaling. This architecture reduces the computational complexity of generating weighting coefficients and number of memory access times. Furthermore, it attempts to minimize the error propagation that results from the fraction truncations when calculating pixel coordinates under fixed-point operations. Error propagation significantly diminishes the output image quality for hardware interpolation. In order to avoid the inaccuracy accumulation, a simple periodical compensation technique is presented to improve the average root-mean-square error significantly. From the perspective of hardware cost, the presented architecture has ~50% saving compared to the latest bi-cubic hardware design work. Finally, this architecture has been successfully designed and implemented with Taiwan Semiconductor Manufacturing Company (TSMC) 0.13 µm complimentary metal oxide semiconductor technology. The simulation results demonstrate that the high-performance architecture of bicubic convolution interpolation at 279 MHz with 30643 gates in a 498×498 µm chip is able to process various-ratio image scaling for full high-definition display device in real time.

We develop real-time, low-complexity image classification algorithms suitable for a copy mode selector embedded in a low-end copier. The algorithms classify scanned images represented in RGB or in an opponent color space. Classes are the eight combinations of mono/color and text/mix/picture/photo. Classification is 30–98% accurate with misclassifications tending to be benign. The algorithms provide for improved copy quality, a simplified user interface, and increased copy rate.

We evaluated the performance of a novel procedure for segmenting mammograms and detecting clustered microcalcifications in two types of image sets obtained from digitization of mammograms using either a laser scanner, or a conventional “optical” scanner. Specific regions forming the digital mammograms were identified and selected, in which clustered microcalcifications appeared or not. A remarkable increase in image intensity was noticed in the images from the optical scanner compared with the original mammograms. A procedure based on a polynomial correction was developed to compensate the changes in the characteristic curves from the scanners, relative to the curves from the films. The processing scheme was applied to both sets, before and after the polynomial correction. The results indicated clearly the influence of the mammogram digitization on the performance of processing schemes intended to detect microcalcifications. The image processing techniques applied to mammograms digitized by both scanners, without the polynomial intensity correction, resulted in a better sensibility in detecting microcalcifications in the images from the laser scanner. However, when the polynomial correction was applied to the images from the optical scanner, no differences in performance were observed for both types of images.

The problem of 3-D shape recovery from image focus can be described as the problem of determining the shape of the focused image surface (FIS)—the surface formed by the best focused points. The shape from focus (SFF) methods in the literature are fast but inaccurate because of the piecewise constant approximation of FIS. The SFF method based on FIS has shown better results by exhaustive search of FIS shape using a planar surface approximation at the cost of a considerably higher number of computations. We present a method to search FIS shape as an optimization problem, i.e., maximization of focus measure in the 3-D image volume. Each image frame in the image volume (sequence) is divided into subimage frames, and the whole image volume is divided into a number of subimage volumes. A rough depth map at only the central pixel of each subimage frame is determined using one of the traditional SFF methods. A few image frames around the image frame, whose image number in the image volume is obtained from the rough depth at the central pixel of subimage frame, are selected for the subimage volumes. The search of FIS shape is now performed in the subimage volumes using a dynamic programming optimization technique. The final depth map is obtained by collecting the depth map of the subimage volumes. The new algorithm considerably decreases the computational complexity by searching FIS shape in subimage volumes and shows better results.

Automatic segmentation and analysis of ancient mosaic images can help archaeologists and experts build digital collections and automatically compare mosaics by means of image database indexing and content-based retrieval tools. However, ancient mosaics are characterized by low contrast colors and irregular tessella shape, orientation, and positioning, making automatic segmentation difficult. We propose a tessella-oriented strategy whose first step consists of isolating tessellas from their cemented network by computing the watershed transformation of a criterion image generated to exhibit the cement network as watershed crests. Then a simple k-means algorithm is used to classify tessellas and segment mosaic images with more accuracy than with a pixel-oriented strategy. Additionally, we propose a method to automatically obtain the main directional guidelines of mosaics by estimating tessella orientation. This is done by minimizing a contextual energy computed from gray-level means of neighboring tessellas and the orientation of their borders. Several examples of cartographies show the effectiveness of the method.

In general, an inevitable side effect of the block-based transform coding includes grid noise in the monotone area, staircase noise along the edges, ringing around the strong edges, corner outliers, and edge corruption near the block boundaries. We propose a comprehensive postprocessing method for removing all the blocking-related artifacts in block-based discrete cosine transfer compressed image in the framework of overcomplete wavelet expansion (OWE) proposed by Mallat and Zhong [IEEE Trans. Pattern Anal. Mach. Intell 14(7), 710–732 (1992)], which is translationally invariant and can efficiently characterize signal singularities. We propose to use the wavelet transform modulus maxima extension (WTMME) to represent the image. The WTMME is extracted from the wavelet coefficients of three-level OWE of the blocky image. The artifacts related to blockiness are modeled and detected through multiscale edge analysis of the image using the information of both modulus and angle. Both the WTMME and the angle image are reconstructed accordingly using inter-/intraband correlation to suppress the influence of the distortions. Finally, the inverse OWE transform is performed for the processed image. Because the algorithm takes no assumption that the blockiness occurs at block boundaries, it is also applicable to video, where due to motion estimation and compensation, the grid noise may propagate into blocks. Extensive simulation and comparative study with 21 exiting relevant algorithms have demonstrated the effectiveness of the proposed algorithm in terms of subjective and objective quality of the resultant images.

We propose a technique for viewpoint and illumination-independent digital archiving of art paintings in which the painting surface is regarded as a 2-D rough surface with gloss and shading. Surface materials like oil paints are inhomogeneously dielectric with the dichromatic reflection property. The procedure for total digital archiving is divided into three main steps: acquisition, analysis, and rendering. In the first stage, we acquire images of a painting using a multiband imaging system with six spectral channels at different illumination directions. In the second stage, we estimate the surface properties of surface-spectral reflectance functions, surface normal vectors, and 3-D reflection model parameters. The principal component analysis suggests that the estimated spectral reflectances have the potential for high data compression. In the third stage, we combine all the estimates for rendering the painting under arbitrary illumination and viewing conditions. We confirm the feasibility of the proposed technique in experiments using oil paintings.

An encoded video bitstream is composed of two main components: the coefficient bits representing the discrete cosine transform coefficients, and the header bits representing the header information (e.g., motion vectors, prediction modes, etc.). Compared with previous video standards, the H.264 Advanced Video Coding (AVC) standard has some unique features: (1) the header bits take up a considerable portion of the encoded bitstream; (2) the header bits vary significantly across macroblocks (MBs); and (3) a large number of MBs are quantized to zero and produce zero coefficient bits (zero-coefficient MB). These unique features make most existing rate estimators inaccurate for decision-making processes related to rate-distortion calculation for rate control. This paper analyzes the characteristics of the H.264/AVC bitstream, and reveals that both the header bits and the occurrence of the zero-coefficient MBs are strongly related with motion-compensated residues obtained by INTER16×16. Therefore, two statistical models are proposed for estimating the header bits and separating the zero-coefficient MBs. Based on the proposed models, a rate control scheme is developed for buffer-constrained constant-bit-rate video coding. Experimental results show that the resultant scheme achieves an average of 0.53 dB peak signal-to-noise ratio (PSNR) gain over the original JM6.1e, and less than 2% bit-rate inaccuracy.

We present an object-oriented method for watermarking stereo images. Since stereo images are characterized by the perception of depth, the watermarking scheme we propose relies on the extraction of a depth map from the stereo pairs to embed the mark. The watermark embedding is performed in the wavelet domain using the quantization index modulation method. Experimental results show that the proposed method is a semifragile one that is robust toward JPEG and JPEG2000 compression and fragile with respect to other signal manipulations.

We present the development of an objective evaluation method based on the integration of X-illumination, morphological fractal analysis and Bayes classifier that aims at characterizing the seam-puckering appearance. The experimental results in our research demonstrate that a highly significant correlation coefficient can be achieved between the estimated grades and the technician-generated grades; the presented method is insensitive to the color/texture of fabrics, thus showing the potential use of our newly developed method to evaluate the seam-puckering appearance objectively and quantitatively.

An efficient texture classification method is proposed that considers the effects of both the rotation and scale of texture images. In our method, the Gabor wavelets are adopted to extract local features of an image and the statistical properties of its gray-level intensities are used to represent the global features. Then, an adaptive, circular orientation normalization scheme is proposed to make the feature invariant to rotation, and an elastic cross-frequency searching mechanism is devised to reduce the effect of scaling. Our method is evaluated based on the Brodatz album and the Outex database, and the experimental results show that it outperforms the traditional algorithms.

This paper presents a robust method for iris segmentation. To detect the inner boundary of the iris, the method introduces a circular filter, which is specially designed to detect circular shapes in iris images. The inner boundary detection process consists of two steps. First, the coarse center of the pupil is detected via the proposed filter. Then, a set of inner boundary points is found by using the Radon transform to detect segment lines in the rectangular areas, which are converted from extracted arc regions with the coarse center. The inner boundary is finally determined by fitting the set of points to a circle using the least-mean-squares method. In addition, the proposed method includes a process for extracting the outer boundary of the iris by applying a linear filter to the rectangular areas transformed from arc regions around the iris. Furthermore, a fast method for detecting eyelids after iris segmentation is presented. Experimental results over the CASIA iris databases show that the performance of the proposed methods is promising for iris images captured in unconstrained environments.

This PDF file contains the editorial “Book Review: Multimedia Data Mining and Knowledge Discovery” for JEI Vol. 17 Issue 04