Search

Image compression plays a vital role in various applications, such as the storage, transmission, and sharing of digital images. We present a symmetric image compression that leverages improved normalization and attention mechanisms to achieve superior compression performance. We focus on addressing the limitations of conventional normalization techniques in handling diverse image characteristics effectively. An adaptive normalization module is proposed to adjust normalization parameters dynamically based on the content of the input image; it ensures optimal data representation and contributes to improved compression efficiency. Furthermore, a windowed attention mechanism is integrated into the compression network to selectively focus on significant image regions while suppressing noise and redundancies by effectively capturing and preserving important visual features to enhance the overall compression quality and reconstruction fidelity. Comparative analysis with state-of-the-art methods demonstrates the superiority of the proposed symmetric image compression network in terms of compression ratio, reconstruction quality, and subjective visual perception. Moreover, the effects of different normalization and attention configurations on compression performance are thoroughly investigated and analyzed. The results of the experiments validate the effectiveness of the proposed symmetric image compression network with improved normalization and windowed attention, known as the Image Compression Attention Normalization Network. The integration of adaptive normalization and windowed attention mechanisms not only enhances the compression efficiency but also enables adaptability to diverse image characteristics. The proposed compression scheme results are as follows. The inference time for encoding and decoding is 0.152 and 0.163 s, respectively. The Bjøntegaard delta (BD) rate shows a reduction of 74.8936%, and the BD-peak signal-to-noise ratio increases by 6.425 dB. The computational load is measured in floating-point operations and totals 263.614G, with the model utilizing 68.1M parameters. Windowed attention preserves critical data, and adaptive normalization alters image processing, enhancing ablation studies. Despite differences, both modules contribute to emphasizing data retention and adjustments and optimizing image processing for improved results. [ABSTRACT FROM AUTHOR]

A shadow-removal algorithm based on cycle generative adversarial network is proposed. There are two networks in the proposed method. To increase the diversity of shadow images for improving the robustness in the shadow-removal process, the first network is used to add shadows in nonshadow images to increase the variation of training data. Then, the second network is trained for the shadow-removal task. Six different losses are calculated and combined in the loss function to increase the performance. Ablation experiments show that the resulting images suffer from some artifacts without any of the six losses in the loss function. The proposed method presents lower value of root-mean-squared error and the superior visual quality compared to the state-of-the-art image removal algorithms.© 2019 spie and is&t [doi: 10.1117/1.JEI.28.1.013034] [ABSTRACT FROM AUTHOR]

Remote sensing image pansharpening involves the fusing of multispectral (MS) images with a panchromatic (PAN) image to produce an image with high-spatial as well as high-spectral resolution. We propose an improved pansharpening algorithm based on deep learning. A four-layer residual network is used as a reconstructed model to enable the accurate estimation of high-frequency details. We consider two priors to take advantage of MS information. The first prior indicates interspectral similarity, wherein the relationship between high- and low-resolution PAN images is used in the estimation of high-resolution MS images. The second prior provides the location of edges and textures according to the gradient of the PAN image. Consistency in the spectral characteristic is used as the basis in creating a pretrained model with the aim of accelerating convergence. Multiple evaluation metrics were applied to simulated and real images in order to compare the efficacy of the proposed method with that of state-of-the-art image fusion methods. © 2018 SPIE and IS&T [DOI: 10.1117/1.JEI.27.3.033013] [ABSTRACT FROM AUTHOR]

This study proposes an interactively recurrent self-evolving fuzzy cerebellar model articulation controller (IRSFCMAC) classifier to solve face detection problems. The learning methods of the proposed classifier are based on simultaneous structure and parameter learning. The structure learning is used to decide the proper input space partition, while the parameter learning is based on gradient descent method. The online structure learning does not need to set any initial structure in advance. In other words, the online structure learning algorithm enables the network along of the problem to efficiently identify the required network structure. The advantages of our proposed IRSFCMAC classifier include (1) using a non-constant differentiable Gaussian basis function to model the hypercube structure; (2) applying an interactively recurrent structure to serve as external loops and internal feedbacks by feeding the hypercube cell (rule) firing strength to itself and other hypercube cells (rules); and (3) requiring fewer computing memory. Finally, experimental results show that the proposed IRSFCMAC classifier is a more adaptive and effective face detection than the other classifiers. [ABSTRACT FROM AUTHOR]

In real-time video transmission, the loss of packet results in visual quality degraded for the succeeding frames. This paper proposes an efficient full frame algorithm for depth-based 3-D videos. Each frame can be regarded as combination of objects. True motion estimation (TME) and depth map are exploited to calculate the motion vector (MV) for each object. In this paper, the object is defined as the pixels with the same MV and similar depth value. The object-based MV can extrapolate each object in reference frame to reconstruct the damage frame. In the consideration of computational complexity, in this method, only the high frequency regions need to execute TME. In this paper, we provide a new method to obtain the objects according to temporal and depth information. From the simulation results, our algorithm gives better visual quality and PSNR in most case with lower complexity. [ABSTRACT FROM AUTHOR]

The Consultative Committee for Space Data Systems proposed an efficient image compression standard that can do lossless compression (CCSDS-ICS). CCSDS-ICS is the most widely utilized standard for satellite communications. However, the original CCSDS-ICS is weak in terms of error resilience with even a single incorrect bit possibly causing numerous missing pixels. A restoration algorithm based on the neighborhood similar pixel interpolator is proposed to fill in missing pixels. The linear regression model is used to generate the reference image from other panchromatic or multispectral images. Furthermore, an adaptive search window is utilized to sieve out similar pixels from the pixels in the search region defined in the neighborhood similar pixel interpolator. The experimental results show that the proposed methods are capable of reconstructing missing regions with good visual quality. © 2016 SPIE and IS&T [DOI: 10.1117/1.JEI.25.4.043017] [ABSTRACT FROM AUTHOR]

In this paper, an Interactively Recurrent Self-evolving Fuzzy Cerebellar Model Articulation Controller (IRSFCMAC) model is developed for solving classification problems. The proposed IRSFCMAC classifier consists of internal feedback and external loops, which are generated by the hypercube cell firing strength to itself and other hypercube cells. The learning process of the IRSFCMAC gets started with an empty hypercube base, and then all of hypercube cells are generated and learned online via structure and parameter learning, respectively. The structure learning algorithm is based on the degree measure to determine the number of hypercube cells. The parameter learning algorithm, based on the gradient descent method, adjusts the shapes of the membership functions and the corresponding fuzzy weights of the IRSFCMAC. Finally, the proposed IRSFCMAC model is tested by four benchmark classification problems. Experimental results show that the proposed IRSFCMAC model has superior performance than traditional FCMAC and other models. [ABSTRACT FROM AUTHOR]

It is difficult for radiologists to identify the masses on a mammogram because they are surrounded by complicated tissues. In current breast cancer screening, radiologists often miss approximately 10–30% of tumors because of the ambiguous margins of lesions and visual fatigue resulting from long-time diagnosis. For these reasons, many computer-aided detection (CADe) systems have been developed to aid radiologists in detecting mammographic lesions which may indicate the presence of breast cancer. This study presents an automatic CADe system that uses local and discrete texture features for mammographic mass detection. This system segments some adaptive square regions of interest (ROIs) for suspicious areas. This study also proposes two complex feature extraction methods based on cooccurrence matrix and optical density transformation to describe local texture characteristics and the discrete photometric distribution of each ROI. Finally, this study uses stepwise linear discriminant analysis to classify abnormal regions by selecting and rating the individual performance of each feature. Results show that the proposed system achieves satisfactory detection performance. [ABSTRACT FROM PUBLISHER]

In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a cooling schedule is created. The main purpose is to embed an annealed cooling schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance. [ABSTRACT FROM AUTHOR]

In this paper, a facial expression recognition system based on cerebella model articulation controller with a clustering memory (CMAC-CM) is presented. Firstly, the facial expression features were automatically preprocessed and extracted from given still images in the JAFFE database in which the frontal view of faces were contained. Next, a block of lower frequency DCT coefficients was obtained by subtracting a neutral image from a given expression image and rearranged as input vectors to be fed into the CMAC-CM that can rapidly obtain output using nonlinear mapping with a look-up table in training or recognizing phase. Finally, the experimental results have demonstrated recognition rates with various block sizes of coefficients in lower frequency and cluster sizes of weight memory. A mean recognition rate of 92.86% is achieved for the testing images. CMAC-CM takes 0.028 seconds for test image in testing phase. [ABSTRACT FROM AUTHOR]

Provides information on a Block Truncation Coding (BTC) image compression technique. Advantages of conventional BTC compression in comparison with transform coding and vector quantization; Capabilities of the BTC image compression technique; Its features.

Describes two novel methods to improve the efficiency of the subband coding by means of the energy compactness in the frequency domain. Technique of QMF analysis and synthesis system; Basic coding concept of dynamic computerized tomography (DCT); Proposed coding scheme of variable block subband DCT (VB-SBCT) and IO-SBDT; System description of VB-SBCT.

Proposes a fast block-matching algorithm that uses three fast matching error measures besides the conventional mean-absolute error (MAE) or mean-square error (MSE). Fast full-search block-matching algorithm (FFBMA); Simulation results of the study; Conclusions.

Image denoising algorithms often require their parameters to be adjusted according to the noise level. We propose a fast and reliable method for estimating image noise. The input image is assumed to be contaminated by an additive white Gaussian noise process. To exclude structures or details from contributing to the estimation of noise variance, a Sobel edge detection operator with a self-determined threshold is first applied to each image block. Then a filter operation, followed by an averaging of the convolutions over the selected blocks, provides a very accurate estimation of noise variance. We successfully combine the effectiveness of filter-based approaches with the efficiency of block-based approaches, and the simulated results demonstrate that the proposed method performs well for a variety of images over a large range of noise variances. Performance comparisons against other approaches are also provided. [ABSTRACT FROM AUTHOR]