In this paper, an improved lossless intracoding algorithm based on H.264/AVC framework is proposed. In the proposed algorithm, two contributions have been made. One is that samples in a macroblock (MB)/block are hierarchically predicted instead of using block-based prediction as a whole. More specifically, four groups are extracted from the samples in an macroblock/block. Samples in the first group are first predicted based on directional intraprediction method, and then the samples in other groups are predicted using the samples in the first group as the references. As a result, the information left in the residual block can be reduced since the samples can be accurately predicted by using nearer references. The other contribution is that two coding modes are designed to efficiently encode the resulting residual block. A better coding mode can be selected based on the rate optimization. Experimental results show that compared with other methods in the literature the proposed algorithm gives a much better compression performance.

Images are fundamental sources of information in modern medicine. The images stored in a database and divided in categories are an important step for image retrieval. For an automatic categorization process, detailed analysis is done regarding image representation and generalization method. The baseline method for this process, in the medical image context, is using thumbnails and K-nearest neighbor (KNN), which is easily implemented and has had satisfactory results in literature. This work addresses an alternative method for automatic categorization, which jointly uses discrete wavelet transform with Hu's moments for image representation and self-organizing maps (SOM) neural networks combined with the KNN classifier (SOM-KNN), for medical image categorization. Furthermore, extensive experiments are conducted, to define the best wavelet family and to select the best coefficients set, to consider the remaining wavelet coefficients set (not selected as the best ones) through their Hu's moments, and to carry out a contrastive study with other successful approaches for categorization. The categorization result from a database with 10,000 images in 116 categories yielded 81.8% of correct rate, which is much better than the 67.9% obtained by the baseline method; and the time consumed in classification processing with SOM-KNN is 100 times shorter than KNN.

Turbo codes adopt iterative decoding to increase the ability of error correction. However, the iterative method increases the decoding delay and power consumption. An effective approach is to decrease the number of iterations while tolerating slight performance degradation. We apply the clustered set partitioning in hierarchical trees for image coding. Different from other early stop criteria, we use the bit-error sensitivities from the image data. Then, the stop criterion is directly determined by the importance of image data. Simulation results show that our scheme can reduce more number of iterations with less degradation for peak-signal-to-noise ratio or structure similar performance.

Fourier volume rendering (FVR) is a volume rendering method based on the Fourier slice theorem. With an n × n × n volume data, the FVR algorithm requires O(n² log n) time to generate a result. Because it requires time less than O(n³) does, FVR is preferred for designing a real-time rendering algorithm with a preprocessing step. We improve upon our previous work. We demonstrate that a B-spline is significantly more useful when designing a transfer function. To design an appropriate transfer function with a spline function, additional control points are required. However, the memory space required for the proposed method increases in linear proportion to the number of control points. We show that the set of control points can be clustered into groups, ensuring the memory required is linearly proportional to the number of groups. The proposed technique supports real-time rendering after adjusting the transfer function for FVR.

The mixed raster content (MRC) document-compression standard (ITU T.44) specifies a multilayer representation of a document image. The model is very efficient for representing sharp text and graphics over a background. However, its binary selection layer compromises the representation of scanned data and soft edges. Typical segmentation algorithms that split up the document into layers tend to lift letter colors to the foreground, so that soft edge transitions may not fully belong either to the foreground or background layers, causing "halos" around objects that impair compression performance. We present a method that sharpens the document before compression and softens its edges after MRC-based reconstruction. It builds an edge-sharpening map and estimates the original edge softness at the encoder. The generated map and softness parameters are then used to reconstruct the original soft edges at the decoder. An MRC encoding and decoding scheme based on H.264/AVC and JBIG2 has been used. Experimental results show that, for lower bit rates, the proposed pre-/postprocessing method can improve both subjective and objective compression performance over regular MRC.

Color texture classification has been an area of intensive research activity. From the very onset, approaches to combining color and texture have been the subject of much discussion, and in particular, whether they should be considered joint or separately. We present a comprehensive comparison of the most prominent approaches both from a theoretical and experimental standpoint. The main contributions of our work are: (i) the establishment of a generic and extensible framework to classify methods for color texture classification on a mathematical basis, and (ii) a theoretical and experimental comparison of the most salient existing methods. Starting from an extensive set of experiments based on the Outex dataset, we highlight those texture descriptors that provide good accuracy along with low dimensionality. The results suggest that separate color and texture processing is the best practice when one seeks for optimal compromise between accuracy and limited number of features. We believe that our work may serve as a guide for those who need to choose the appropriate method for a specific application, as well as a basis for the development of new methods.

Reliably assessing overall quality of JPEG/JPEG2000 coded images without having the original image as a reference is still challenging, mainly due to our limited understanding of how humans combine the various perceived artifacts to an overall quality judgment. A known approach to avoid the explicit simulation of human assessment of overall quality is the use of a neural network. Neural network approaches usually start by selecting active features from a set of generic image characteristics, a process that is, to some extent, rather ad hoc and computationally extensive. This paper shows that the complexity of the feature selection procedure can be considerably reduced by using dedicated features that describe a given artifact. The adaptive neural network is then used to learn the highly nonlinear relationship between the features describing an artifact and the overall quality rating. Experimental results show that the simplified feature selection procedure, in combination with the neural network, indeed are able to accurately predict perceived image quality of JPEG/JPEG2000 coded images.

Detecting a vehicle to obtain traffic information at nighttime is difficult. This study proposes a vehicle detection algorithm, called the headlight extraction, pairing, and tracking (HLEPT) algorithm, which can acquire traffic information in the rain at nighttime by identifying vehicles through the location of their headlights and other indicative lights. A knowledge-based connected-component procedure, in which vehicles are located by grouping their lights and estimating their features, is proposed. The features of a complex nighttime traffic scene were also analyzed. The HLEPT algorithm includes a headlight extraction algorithm, as well as regulations for the pairing and grouping of lights and light tracking using a Kanade-Lucas-Tomasi tracker to measure traffic flow and velocity. Experimental results demonstrate the feasibility and effectiveness of the proposed approach on vehicle detection in the rain at nighttime.

Moving object detection in the presence of dynamic backgrounds remains a challenging problem in video surveillance. Earlier work established that the background subtraction technique based on a covariance matrix descriptor is effective and robust for dynamic backgrounds. The work proposed herein extends this concept further, using the covariance-matrix descriptor derived from local textural properties, instead of directly computing from the local image features. The proposed approach models each pixel with a covariance matrix and a mean feature vector and the model is dynamically updated. We made extensive studies with the proposed technique to demonstrate the effectiveness of statistics on local textural properties.

In this paper, a novel adaptive color image watermarking scheme based on the just noticeable distortion (JND) model in balanced multiwavelet domain is proposed. The balanced multiwavelet transform can achieve orthogonality, symmetry, and high order of approximation simultaneously without requiring any input prefiltering, which makes it a good choice for image processing. According to the properties of the human visual system, a novel multiresolution JND model is proposed in balanced multiwavelet domain. This model incorporates the spatial contrast sensitivity function, the luminance adaptation effect, and the contrast masking effect via separating the sharp edge and the texture. Then, based on this model, the watermark is adaptively inserted into the most distortion tolerable locations of the luminance and chrominance components without introducing the perceivable distortions. Experimental results show that the proposed watermarking scheme is transparent and has a high robustness to various attacks such as low-pass filtering, noise attacking, JPEG and JPEG2000 compression.

Color image watermarking with high imperceptibility and robustness capabilities is still an emerging topic in the field of multimedia copyright protection. A novel approach for robust and semiblind watermarking of still color images in the wavelet domain is proposed. The proposed technique utilizes the human visual system characteristics, and an innovative watermark weight-calibrating procedure to create various watermarks at different classes of the color image under consideration. It decomposes the input color image into specific classes where each class is applied to an appropriate watermarking procedure that takes into account its grayness and/or chromaticity behaviors on a pixel-wise and color permissibility basis. The experimental results have shown that the proposed technique exhibits very high imperceptibility (80.1 to 89.2 dB) and is sufficiently robust to guard against JPEG compression, additive noise, filtering, moderate cropping, scaling, and other common image manipulations.

This PDF file contains the errata for “JEI Vol. 20 Issue 04 Paper 3652695” for JEI Vol. 20 Issue 04

A book review of a recently released title.