Search

Deep learning (DL) has recently changed the development of intelligent systems and is widely adopted in many real-life applications. Despite their various benefits and potentials, there is a high demand for DL processing in different computationally limited and energy-constrained devices. It is natural to study game-changing technologies such as Binary Neural Networks (BNN) to increase deep learning capabilities. Recently remarkable progress has been made in BNN since they can be implemented and embedded on tiny restricted devices and save a significant amount of storage, computation cost, and energy consumption. However, nearly all BNN acts trade with extra memory, computation cost, and higher performance. This article provides a complete overview of recent developments in BNN. This article focuses exclusively on 1-bit activations and weights 1-bit convolution networks, contrary to previous surveys in which low-bit works are mixed in. It conducted a complete investigation of BNN's development -from their predecessors to the latest BNN algorithms/techniques, presenting a broad design pipeline and discussing each module's variants. Along the way, it examines BNN (a) purpose: their early successes and challenges; (b) BNN optimization: selected representative works that contain essential optimization techniques; (c) deployment: open-source frameworks for BNN modeling and development; (d) terminal: efficient computing architectures and devices for BNN and (e) applications: diverse applications with BNN. Moreover, this paper discusses potential directions and future research opportunities in each section., Comment: accepted by journal of Artificial Intelligence Review

Copying the quantum states is contradictory to classical information processing since the fundamental difference between classical and quantum information is that while classical information can be copied perfectly, quantum information cannot. However, this statement does not rule out the risk of building a device that can reproduce a set of quantum states. This paper investigates the naturally arising question of how well or under what conditions one can copy and measure an arbitrary quantum superposition of states. The CNOT and XOR operation-based quantum circuit is presented that exhibits entanglement of states and allows for measuring the doubled qubits., Comment: 10 pages, 5 figures

Over the past century, a correlation has been an essential mathematical technique utilized in engineering sciences, including practically every signal/image processing field. This paper describes an effective method of calculating the correlation function of signals and color images in quaternion algebra. We propose using the quaternions with a commutative multiplication operation and defining the corresponding correlation function in this arithmetic. The correlation between quaternion signals and images can be calculated by multiplying two quaternion DFTs of signals and images. The complexity of the correlation of color images is three times higher than in complex algebra., Comment: 14 pages, 7 figures, 1 table

Sudoku puzzles are now popular among people in many countries across the world with simple constraints that no repeated digits in each row, each column, or each block. In this paper, we demonstrate that the Sudoku configuration provides us a new alternative way of matrix element representation by using block-grid pair besides the conventional row-column pair. Moreover, we discover six more matrix element representations by using row-digit pair, digit-row pair, column-digit pair, digit-column pair, block-digit pair, and digit-block pair associated with a Sudoku matrix. These parametric Sudoku associated matrix element representations not only allow us to denote matrix elements in secret ways, but also provide us new parametric two-dimensional bijective mappings. We study these two-dimensional bijections in the problem of image scrambling and propose a simple but effective Sudoku Associated Image Scrambler only using Sudoku associated two dimensional bijections for image scrambling without bandwidth expansion. Our simulation results over a wide collection of image types and contents demonstrate the effectiveness and robustness of the proposed method. Scrambler performance analysis with comparisons to peer algorithms under various investigation methods, including human visual inspections, gray degree of scrambling, autocorrelation coefficient of adjacent pixels, and key space and key sensitivities, suggest that the proposed method outperforms or at least reaches state-of-the-art. Similar scrambling ideas are also applicable to other digital data forms such as audio and video., Comment: 30 pages, 13 figures

A quantum computer directly manipulates information stored in the state of quantum mechanical systems. The available operations have many attractive features but also underly severe restrictions, which complicate the design of quantum algorithms. We present a divide-and-conquer approach to the design of various quantum algorithms. The class of algorithm includes many transforms which are well-known in classical signal processing applications. We show how fast quantum algorithms can be derived for the discrete Fourier transform, the Walsh-Hadamard transform, the Slant transform, and the Hartley transform. All these algorithms use at most O(log^2 N) operations to transform a state vector of a quantum computer of length N., Comment: 11 pages, LaTeX2e, 15 figures, not viewable as dvi. To appear in Image Processing: Algorithms and Systems, Electronic Imaging 2002, San Jose, SPIE, 2002. Odd title beyond our control

This work presents a methodology to optimize the selection of multiple parameter levels of an image acquisition, degradation, or post-processing process applied to stimuli intended to be used in a subjective image or video quality assessment (QA) study. It is known that processing parameters (e.g. compression bit-rate) or technical quality measures (e.g. peak signal-to-noise ratio, PSNR) are often non-linearly related to human quality judgment, and the model of either relationship may not be known in advance. Using these approaches to select parameter levels may lead to an inaccurate estimate of the relationship between the parameter and subjective quality judgments – the system’s quality model. To overcome this, we propose a method for modeling the relationship between parameter levels and perceived quality distances using a paired comparison parameter selection procedure in which subjects judge the perceived similarity in quality. Our goal is to enable the selection of evenly sampled parameter levels within the considered quality range for use in a subjective QA study. This approach is tested on two applications: (1) selection of compression levels for laparoscopic surgery video QA study, and (2) selection of dose levels for an interventional X-ray QA study. Subjective scores, obtained from the follow-up single stimulus QA experiments conducted with expert subjects who evaluated the selected bit-rates and dose levels, were roughly equidistant in the perceptual quality space - as intended. These results suggest that a similarity judgment task can help select parameter values corresponding to desired subjective quality levels.

Dynamic X-ray imaging systems are used for interventional cardiac procedures to treat coronary heart disease. X-ray settings are controlled automatically by specially-designed X-ray dose control mechanisms whose role is to ensure an adequate level of image quality is maintained with an acceptable radiation dose to the patient. Current commonplace dose control designs quantify image quality by performing a simple technical measurement directly from the image. However, the utility of cardiac X-ray images is in their interpretation by a cardiologist during an interventional procedure, rather than in a technical measurement. With the long term goal of devising a clinically-relevant image quality metric for an intelligent dose control system, we aim to investigate the relationship of image noise with clinical professionals’ perception of dynamic image sequences. Computer-generated noise was added, in incremental amounts, to angiograms of five different patients selected to represent the range of adult cardiac patient sizes. A two alternative forced choice staircase experiment was used to determine the amount of noise which can be added to a patient image sequences without changing image quality as perceived by clinical professionals. Twenty-five viewing sessions (five for each patient) were completed by thirteen observers. Results demonstrated scope to increase the noise of cardiac X-ray images by up to 21% ± 8% before it is noticeable by clinical professionals. This indicates a potential for 21% radiation dose reduction since X-ray image noise and radiation dose are directly related; this would be beneficial to both patients and personnel.

We have developed an end-to-end system for 3D scene sensing which combines a conventional high-resolution RGB camera with a low-resolution Time-of-Flight (ToF) range sensor. The system comprises modules for range data denoising, data re-projection and non-uniform to uniform up-sampling and aims at composing high-resolution 3D video output for driving auto-stereoscopic 3D displays in real-time. In our approach, the ToF sensor is set to work with short integration time with the aim to increase the capture speed and decrease the amount of motion artifacts. However, reduced integration time leads to noisy range images. We specifically address the noise reduction problem by performing a modification of the non-local means filtering in spatio-temporal domain. Time-consecutive range images are utilized not only for efficient de-noising but also for accurate non-uniform to uniform up-sampling on the high-resolution RGB grid. Use is made of the reflectance signal of the ToF sensor for providing a confidence-type of feedback to the denosing module where a new adaptive averaging is proposed to effectively handle motion artifacts. As of the non-uniform to uniform resampling of range data is concerned, we have developed two alternative solutions; one relying entirely on the GPU power and another being applicable to any general platform. The latter method employs an intermediate virtual range camera recentering after with the resamploing process degrades to a 2D interpolation performed within the lowresolution grid. We demonstrate a real-time performance of the system working in low-power regime. acceptedVersion

We present a methodology to assess objective visual quality of multi-view and light-field displays. We consider the display as a signal processing channel and study its ability to deliver a signal while introducing negligible distortions. We start by creating a model of a display, which represents its output as a set of rays in a specific (x, y, o) coordinate space. We created a simulation framework that can use the model and render the expected output of the display for a given observation position. The framework employs an image analysis block, which aims to predict the perceptual effect of the introduced distortions and judge if the original signal is still predominant in the output. Using the framework, we can try a large set of test signals against the display model and find the ones, which are represented with sufficiently low distortion levels. We use test signals, which contain gradually changing frequency components, and use the results of the tests to build the so-called 3D passband of the display. The 3D passband can be used as a quantitative measure of the display’s ability to faithfully represent image details. The size of the passband is indicative of the spatial and angular resolution of the display. We created two display models to serve as an example case for out framework. One model represents a typical multiview display, and the other is representing a typical projection-based light-field display. We estimate the passband for each display model and present the results. The resulting passbands suggest, that for a given “ray-budget”, the ray distribution typical for light-field displays results on a wider and more uniform passband than in the case with multiview displays.

Infrared Non-Destructive Testing (INDT) is known as an effective and rapid method for nondestructive inspection. It can detect a broad range of near-surface structuring flaws in metallic and composite components. Those flaws are modeled as a smooth contour centered at peaks of stored thermal energy, termed Regions of Interest (ROI). Dedicated methodologies must detect the presence of those ROIs. In this paper, we present a methodology for ROI extraction in INDT tasks. The methodology deals with the difficulties due to the non-uniform heating. The non-uniform heating affects low spatial/frequencies and hinders the detection of relevant points in the image. In this paper, a methodology for ROI extraction in INDT using multi-resolution analysis is proposed, which is robust to ROI low contrast and non-uniform heating. The former methodology includes local correlation, Gaussian scale analysis and local edge detection. In this methodology local correlation between image and Gaussian window provides interest points related to ROIs. We use a Gaussian window because thermal behavior is well modeled by Gaussian smooth contours. Also, the Gaussian scale is used to analyze details in the image using multi-resolution analysis avoiding low contrast, non-uniform heating and selection of the Gaussian window size. Finally, local edge detection is used to provide a good estimation of the boundaries in the ROI. Thus, we provide a methodology for ROI extraction based on multi-resolution analysis that is better or equal compared with the other dedicate algorithms proposed in the state of art.