Search

Scene classification is a fundamental task in the remote sensing (RS) field, assigning semantic labels to RS images. Multispectral (MS) images play an essential role in scene classification as they contain richer spectral information than red, green, blue (RGB) images. However, MS images are not always available due to the higher cost and complexity of MS sensors compared to RGB sensors. To improve scene classification performance using only RGB images, in this letter, we propose a novel MS-to-RGB knowledge distillation (MS2RGB-KD) framework that transfers MS knowledge from a teacher model to a student model. Specifically, our MS2RGB-KD drives a student model that requires only an RGB image as input to mimic the feature representations of different modalities extracted by the teacher model. Moreover, we introduce novel loss functions that encourage the student model to preserve intramodal and intermodal relationships of the feature representations in the teacher model. Experiments on the EuroSAT dataset demonstrate the effectiveness of MS2RGB-KD compared with other KD baselines. [ABSTRACT FROM AUTHOR]

Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these approaches need a mask image to infer pixel-wise affine transformation parameters, they are not applicable to general image generation models having no paired mask images. To resolve this problem, this paper presents a novel normalization method, called self pixel-wise normalization (SPN), which effectively boosts the generative performance by carrying out the pixel-adaptive affine transformation without an external guidance map. In our method, the transforming parameters are derived from a self-latent mask that divides the feature map into foreground and background regions. The visualization of the self-latent masks shows that SPN effectively captures a single object to be generated as the foreground. Since the proposed method produces the self-latent mask without external data, it is easily adaptable to existing generative models. Extensive experiments on various datasets reveal that our SPN significantly improves the performance of image generation technique in terms of Frechet inception distance (FID) and Inception score (IS). [ABSTRACT FROM AUTHOR]

Deep-learning-based survival prediction can assist doctors by providing additional information for diagnosis by estimating the risk or time of death. The former focuses on ranking deaths among patients based on the Cox model, whereas the latter directly predicts the survival time of each patient. However, it is observed that survival time prediction for the patients, particularly with close observation times, possibly has incorrect orders, leading to low prediction accuracy. Therefore, in this paper, we present a whole slide image (WSI)-based survival time prediction method that takes advantage of both the risk as well as time prediction. Specifically, we propose to combine these two approaches by extracting the risk prediction features and using them as guides for the survival time prediction. Considering the high resolution of WSIs, we extract tumor patches from WSIs using a pre-trained tumor classifier and apply the graph convolutional network to aggregate information across these patches effectively. Extensive experiments demonstrate that the proposed method significantly improves the time prediction accuracy when compared with direct prediction of the survival times without guidance and outperforms existing methods. [ABSTRACT FROM AUTHOR]

The autonomous positioning of a vehicle predominantly relies on the global positioning system (GPS). However, in indoor environments, such as tunnels and indoor parking lots, the accuracy of GPS-based positioning can be significantly reduced due to weak GPS signals. To this end, we develop an accurate indoor vehicle positioning system using multiple fish-eye surveillance cameras. Our system first extracts vehicle segments from the top-view image of each fish-eye camera. These segments are then integrated into a common undistorted coordinate system. The center of the vehicle is finally determined using our simple but effective box fitting method. Moreover, a 1/18 scale indoor parking lot is designed to evaluate the performance of the proposed system. Throughout our experiments, we obtained average positioning errors of 30 or 24 cm in the regions covered by a single camera or multiple cameras, respectively. [ABSTRACT FROM AUTHOR]

In 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT. [ABSTRACT FROM AUTHOR]

Due to the projective nature of a single camera, monocular visual simultaneous localization and mapping (vSLAM) algorithms suffer from scale drift. Recent studies have addressed the scale drift by estimating the height of the camera from the fitted ground plane. However, the low accuracy of 3D ground point (3DGP) reconstruction and the insufficient number of 3DGPs from the textureless ground region make the fitted plane inaccurate for scale estimation. In this paper, we introduce a novel accuracy measure of the fitted plane. From the previous keyframe, we first obtain the 3D points from the intersection of the fitted plane with a ray passing through the camera center and the 2D feature points on the ground region. We then transform the 3D points and 2D feature points to the current keyframe using their respective planar homography. Finally, we project the transformed 3D points onto the image plane of the current keyframe and measure the average Euclidean distance between the projected points and the transformed feature points. The proposed method achieves the average translation error of 1.03% on the KITTI dataset, which outperforms the state-of-the-art monocular vSLAM methods. [ABSTRACT FROM AUTHOR]

In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze trackers utilize the pupil center and corneal reflection (CR) obtained from an infrared (IR) light source to estimate the point of regard (POR). However, false CRs are often generated due to extraneous light sources such as sunlight or lamps. In this study, we propose a method of improving the robustness of gaze tracking under unconstrained illumination conditions. First, the proposed method generates a coded CR pattern by utilizing time-multiplexed IR light sources. Next, the CR candidates are detected in eye images, and their coordinates are compensated based on the head and eye movements of the user. Finally, true CRs are selected from the motion-compensated CR candidates by utilizing a novel cost function. Experimental results indicate that the gaze-tracking performance of the proposed method under various light conditions is considerably better than those of the conventional methods. [ABSTRACT FROM AUTHOR]

Various power-constrained contrast enhancement (PCCE) techniques have been applied to an organic light emitting diode (OLED) display for reducing the power demands of the display while preserving the image quality. In this paper, we propose a new deep learning-based PCCE scheme that constrains the power consumption of the OLED displays while enhancing the contrast of the displayed image. In the proposed method, the power consumption is constrained by simply reducing the brightness a certain ratio, whereas the perceived visual quality is preserved as much as possible by enhancing the contrast of the image using a convolutional neural network (CNN). Furthermore, our CNN can learn the PCCE technique without a reference image by unsupervised learning. Experimental results show that the proposed method is superior to conventional ones in terms of image quality assessment metrics such as a visual saliency-induced index (VSI) and a measure of enhancement (EME). [ABSTRACT FROM AUTHOR]

We propose a new image-interpolation technique using a combination of an adaptive directional wavelet transform (ADWT) and discrete cosine transform (DCT). In the proposed method, we use ADWT to decompose the low-resolution image into different frequency subband images. The high-frequency subband images are further transformed to DCT coefficients, and the zero-padding method is used for interpolation. Simultaneously, the low-frequency subband image is replaced by the original low-resolution image. Finally, we generate the interpolated image by combining the original low-resoultion image and the interpolated subband images by using inverse DWT. Experimental results demonstrate that the proposed algorithm yields better quality images in terms of subjective and objective quality metrics compared to the other methods considered in this paper. [ABSTRACT FROM AUTHOR]

Quadtree-based partitioning (i.e., recursively dividing a picture into square blocks) is one of the most popular partitioning-based image coding schemes because of its computational simplicity and efficient representation of partitioning. However, the rate-distortion performance of quadtree-based partitioning reaches a limit because the dependence between child blocks of different parents is not exploited. In this paper, a new bottom-up-based block partitioning method called split-and-merge is proposed. This method splits an image into multiple square blocks and merges them into nonsquare blocks to exploit the dependence between split blocks. Moreover, a modification of the conventional intra prediction and transform is employed for nonsquare blocks. The experimental results indicate that the proposed method results in an average and maximum bit rate reduction of 3.1% and 8.3%, respectively, relative to High Efficiency Video Coding intra coding. [ABSTRACT FROM PUBLISHER]

Recently, with the increased demand for low-power displays regarding portable devices, the RGBG PenTile display is popularly utilized. However, unlike the traditional RGB-stripe display with its three color channels, each pixel of the RGBG PenTile display comprises only two color channels, thereby causing the color leakage image distortion. To cope with this problem, most of the conventional methods employ a preprocessing filter for subpixel rendering; however, these filters cannot remove the color leakage completely, and they also result in the blurring artifacts. In this paper, a novel approach to obtain the preprocessing filter is presented. We formulate a filter design method as a minimum mean square error problem and derive an optimal preprocessing filter that is based on the human visual system (HVS) as follows; first, two perceived images indicating how human recognizes the images on the RGB and RGBG displays are generated and then the difference between the two perceived images is minimized to derive the optimal filter. In addition, in order to prevent the blurring artifact, the proposed filter is applied to the previously detected color-leakage region only. Experimental results demonstrate that the proposed method outperforms the conventional methods in terms of both the subjective and objective image quality. [ABSTRACT FROM PUBLISHER]

To assist the visually impaired (VI), a variety of collision detection methods using monocular vision have been developed. Most conventional collision detection methods for the VI utilize feature points and their corresponding motion vectors. However, when the VI subject approaches a non-textured object/obstacle, such as a door or wall, the conventional methods often fail to detect the collision on account of insufficient feature points and inaccurate motion vectors. To address this problem, this paper presents a collision detection method using image segmentation. In the proposed method, the input frame is over-segmented into superpixels by using the superpixel lattices algorithm. The segmentation result is then obtained by applying a graph-based region merging algorithm to the superpixels. Finally, the collision is detected using the geometric relationship between the size variation of the image segment and the distance variation from the camera to that segment in a real-world environment. Experimental results demonstrate that the proposed method handles a variety of scenarios, including a non-textured object, while outperforming conventional methods in terms of accuracy. [ABSTRACT FROM PUBLISHER]

In this paper, a novel content-preserving video stitching method is proposed. Video stitching has to deal with moving objects in the overlapped area (OA) which often cause problems of structural misalignment or ghost effect. To this end, the proposed method first finds an optimal seam that does not pass through the moving objects, by using the extended dynamic programing (DP) technique based on the energy minimization. Then the content-aware adaptive blending is performed which effectively reduces the color discontinuity while restricting the ghost effect caused by moving objects in the OA. In addition, to reduce the computational complexity, a partial seam-update (PSU) scheme is proposed, in which the seam is re-calculated only for a part of the seam passing through the moving object. Experimental results demonstrate that the proposed method is superior to the conventional ones in terms of both subjective quality and computational complexity. In addition, this method achieves real-time performance on mobile platform, making it applicable to consumer electronic devices. [ABSTRACT FROM PUBLISHER]

Various obstacle avoidance (OA) methods with the monocular vision have been studied to assist visually impaired people. Recently, a method that effectively locates obstacles at a risk of collision using the shape variation of a grid, called deformable grid (DG), was introduced [11]. To further improve the detection performance of the previous work, a vertex deformation function representing the displacement of each vertex in the DG is firstly defined employing the perspective projection geometry. Then, the collision risk is accurately estimated based on the shape variation of the DG that is measured using the vertex deformation function. Experimental results show that the proposed method outperforms other conventional methods as well as the previous work in terms of both the accuracy and processing time, and clearly detects obstacles that present a risk of collision in a variety of scenarios. This method is suitable for application to electronic travel aid (ETA) systems using consumer devices, such as smart-phones, tablets, and wearable devices. [ABSTRACT FROM PUBLISHER]

Multiple flat-panel displays have been widely used as business and consumer electronic equipment. Although stereo or multiple display units are of the same brand and model, users often experience temporary visual fatigue due to the color differences between flat-panel displays. Therefore, color calibration between multiple display units displayed at the same time has been receiving attention from display manufacturers. In this paper, a camera-based color calibration method for multiple flat-panel displays that uses a portable smartphone camera is proposed. The color calibration algorithm used in the proposed method consists of three parts: geometric registration based on a chessboard detector, camera parameter optimization based on the distortion model of camera's optical system and environmental factors, and color matching for fast calibration. Experimental tests proved the practicality and the reliable calibration performance of the proposed color calibration method for the aftermarket [ABSTRACT FROM PUBLISHER]

Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a highdimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance. [ABSTRACT FROM PUBLISHER]

In this paper, a novel real-time edge-guided interpolation method is presented to produce the high resolution image without any disturbing artifacts such as blurring, jagging, and overshooting. The proposed method computes the first- and second-order derivatives of an input image to measure the geometry of edges in the image. Based on these measures, the value of a pixel to be interpolated is estimated along four directions using Taylor series approximation. The four directional estimates are adaptively fused based on the orientation of a local edge to obtain the edge-guided interpolation output. Experimental results demonstrate that the proposed interpolation method outperforms the conventional ones both in terms of objective and subjective image qualities with low computational complexity1. [ABSTRACT FROM PUBLISHER]

This paper presents a novel quality assessment method for flat panel display (FPD) defects, often called Muras, that employs the characteristics of the human visual system (HVS). Given a Mura image, the brightness difference between the Mura and its surrounding region is first adjusted to reflect the HVS’s property of background-adaptive perception. Then, the resulting adjusted Mura image is further processed using multiscale defect saliency acquisition (MDSA) to obtain a final Mura image with human perception characteristics. In the experiments, the quality scores of Mura test images are measured using the conventional and proposed methods. The results demonstrate that the quality of Mura evaluated by the proposed method correlates with the subjective quality to a much higher degree compared with the conventional methods. [ABSTRACT FROM PUBLISHER]

The two-dimensional (2D) discrete Fourier transform (DFT) in the sliding window scenario has been successfully used for numerous applications requiring consecutive spectrum analysis of input signals. However, the results of conventional sliding DFT algorithms are potentially unstable because of the accumulated numerical errors caused by recursive strategy. In this letter, a stable 2D sliding fast Fourier transform (FFT) algorithm based on the vector radix (VR) 2 × 2 FFT is presented. In the VR-2 × 2 FFT algorithm, each 2D DFT bin is hierarchically decomposed into four sub-DFT bins until the size of the sub-DFT bins is reduced to 2 × 2; the output DFT bins are calculated using the linear combination of the sub-DFT bins. Because the sub-DFT bins for the overlapped input signals between the previous and current window are the same, the proposed algorithm reduces the computational complexity of the VR-2 × 2 FFT algorithm by reusing previously calculated sub-DFT bins in the sliding window scenario. Moreover, because the resultant DFT bins are identical to those of the VR-2 × 2 FFT algorithm, numerical errors do not arise; therefore, unconditional stability is guaranteed. Theoretical analysis shows that the proposed algorithm has the lowest computational requirements among the existing stable sliding DFT algorithms. [ABSTRACT FROM AUTHOR]

To assist visually impaired people, a variety of obstacle detection (OD) methods with the monocular vision have been developed. Most conventional OD methods detect the obstacle by using the variation of the motion vector or the object size between two consecutive image frames. However, the OD performance using the short-term variation is significantly affected by the tracking error, which leads to inaccurate OD results. To cope with this problem, this paper presents a novel OD method based on a new structure, called Deformable Grid (DG). The DG is initially a regular gridshaped, but it can be deformed gradually depending on the motion of the object in the scene. The proposed method detects the object at risk of collision based on the degree of the deformation of the DG. Experimental results demonstrate that the proposed OD method outperforms the conventional ones in terms of processing time as well as accuracy. [ABSTRACT FROM AUTHOR]

It is a challenging work to reproduce the high resolution (HR) image from a noisy low resolution input while preserving its edge structures. In this paper, a fast noise-robust interpolation method is proposed. In the proposed method, the edge information of a pixel to be interpolated is first estimated using a local curvature (LC), which is a second-order directionalderivative obtained from its local neighborhoods. Based on the edge information of the pixel, edge-adaptive interpolation with noise reduction is performed using the proposed LC adaptive filter whose kernel is adaptively determined by comparing the LC values along the two orthogonal directions. A refinement procedure is adopted to further enhance the edge information of the HR image by applying a Laplacian subtraction method using the precomputed LC values. Experimental results show that the proposed method can preserve the edge sharpness while suppressing noise, with low computational complexity. [ABSTRACT FROM AUTHOR]

Among various infrared (IR) image based remote eye gaze tracking (REGT) methods, 2-D interpolation based methods, e.g., the cross ratio-based and homography normalization (HN)-based methods, have been widely researched owing to their highly accurate performance and simplicity with respect to hardware setup. These methods, however, can be employed only when user utilizes more than four IR light sources to obtain multiple corneal reflections projected on the image plane, i.e. glints. In this paper, a novel 2-D interpolation-based REGT method with a single IR light source is proposed, which attains both accuracy and headpose robustness. In the proposed method, the virtual glint (VG), which can substitute for the actual glint, is first estimated by utilizing the mathematical and geometrical principles established between the 3-D location of an IR light source and the corresponding glint in the image plane, and then the point of gaze (POG) is calculated by employing the HN method using the estimated VGs. The experimental results indicate that the proposed REGT method is highly competitive with conventional ones requiring multiple IR light sources, in terms of accuracy and robustness against head movements. [ABSTRACT FROM AUTHOR]

In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods. [ABSTRACT FROM PUBLISHER]

A visible image?based face recognition system can be seriously degraded in real-life environments by various factors including illumination changes, expression changes, occlusion, and disguise. In this paper, a novel feature descriptor for robust face recognition, Eigen Directional Bit-Plane (EDBP), is introduced to address these issues. It is observed that Local Binary Pattern (LBP) can be decomposed into 8 directional bit-planes (DBP), each of which represents certain directional information of the facial image. Principal Component Analysis (PCA) is then applied to the DBP space to obtain a more compact feature, the EDBP. For face recognition, the proposed EDBP is integrated into conventional state-of-the-art classification methods. Simulation results demonstrate that classifiers with EDBP outperform those with existing feature descriptors under illumination changes, expression changes, occlusion, and disguise. [ABSTRACT FROM PUBLISHER]

Conventional robotic vacuum cleaners (RVCs) with ultrasonic or infrared (IR) sensors present problems in detecting obstacles when they clean the floor in complex situations, for example, under tables or chairs with thin legs. This paper presents a robust obstacle detection (OD) method based on the triangulation principle for RVCs operating in various home environments. The proposed method uses the IR emitter of the RVC to project a horizontal IR beam toward the floor, following which the RVC?s wide-angle vision camera captures an image that includes the IR line reflected by the floor or an obstacle. Obstacles are detected by using the image coordinates of the pixels that belong to the IR line in the captured image. Accurate separation of the IR line from the image background is accomplished by defining and minimizing an energy function based on the characteristics of the IR line. The proposed method was tested on the embedded RVC system and was shown capable of achieving OD performance compared with existing methods. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods. [ABSTRACT FROM AUTHOR]

The overexposed region (OR) usually appears in the image due to the limited dynamic range of digital camera and low dynamic range display. In this paper, we present a novel overexposure correction method composed of the lightness correction and the chrominance restoration. In proposed method, the corrected lightness of the OR is obtained by minimizing a proposed energy functional with two terms; one for retaining the lightness modeled by a twodimensional Gaussian function and the other for preserving the gradients of the original lightness. In chrominance restoration, color stretching is first performed to compensate a faded color around the OR. Then, the color of the OR is recovered by propagating the stretched color of the neighboring non-overexposed region (non-OR). Experimental results demonstrate that the proposed method more effectively improves the visual quality of the overexposed image compared with the state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

The discrete Fourier transform (DFT) produces a Fourier representation for finite-duration data sequences. In addition to its theoretical importance, the DFT plays a key role in the implementation of a variety of digital signal-?processing algorithms. Several algorithms including the fast Fourier transform (FFT) and the Goertzel algorithm have been introduced for the fast implementation of the DFT [1], [2]. [ABSTRACT FROM PUBLISHER]

The performance of video stabilization is dependent on the accuracy of global motion estimation between two successive frames. In this paper, we propose a novel method to estimate the global motion accurately using the classified background (BG) feature points (FPs). In the proposed method, global motion estimation and FP classification are jointly performed using both the FP correspondences and the global motion parameters of the previous frame. The experimental results show that video stabilization using the proposed method outperforms the conventional stabilization methods, especially when the moving foreground (FG) objects occupy a large part of the image1. [ABSTRACT FROM PUBLISHER]

In this paper, we present a novel depth sensation enhancement algorithm considering the behavior of human visual system toward stereoscopic image displays. On the basis of the recent studies on the just noticeable depth difference (JNDD), which represents a threshold at which a human can perceive the depth difference between objects, we modify the depth image such that neighboring objects in the depth image can have a depth value difference of at least the JNDD. This modification is modeled via an energy minimization framework using three energy terms defined as depth data preservation, depth order preservation, and depth difference expansion. The depth data term enforces minimal changes in the depth image with an additional weighting function that controls the direction of depth changes. The depth order term restricts the inversion of the local and global depth orders among objects, and the JNDD term leads to an increase in the depth differences between segments. Throughout subjective quality evaluation on a stereoscopic image display, it is demonstrated that the human depth sensation is effectively improved by the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a novel robust people counting system based on fusing the depth and vision data. Conventional algorithms utilize the monoscopic or stereoscopic vision data to count people. However, these vision-based people counting methods often fail due to occasional illumination change and crowded environment. In the proposed algorithm, both the top-view vision and depth images are captured by a video-plus-depth camera mounted on the ceiling. The depth image is first processed by a morphological operator to alleviate depth artifacts such as the optical noise and lost data. Then the human object is extracted using a human model from the preprocessed depth image. Finally, the trajectory of the detected object is established by applying the bidirectional matching algorithm. Experimental results show that the proposed algorithm achieves over 98% accuracy in various testing environments. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a new sharpness enhancement algorithm for stereo images. Although the stereo image and its applications are becoming increasingly prevalent, there has been very limited research on specialized image enhancement solutions for stereo images. Recently, a binocular just-noticeable-difference (BJND) model that describes the sensitivity of the human visual system to luminance changes in stereo images has been presented. We introduce a novel application of the BJND model for the sharpness enhancement of stereo images. To this end, an overenhancement problem in the sharpness enhancement of stereo images is newly addressed, and an efficient solution for reducing the overenhancement is proposed. The solution is found within an optimization framework with additional constraint terms to suppress the unnecessary increase in luminance values. In addition, the reliability of the BJND model is taken into account by estimating the accuracy of stereo matching. Experimental results demonstrate that the proposed algorithm can provide sharpness-enhanced stereo images without producing excessive distortion. [ABSTRACT FROM AUTHOR]

In this letter, we propose an improved histogram modification based reversible data hiding technique. In the proposed algorithm, unlike the conventional reversible techniques, a data embedding level is adaptively adjusted for each pixel with a consideration of the human visual system (HVS) characteristics. To this end, an edge and the just noticeable difference (JND) values are estimated for every pixel, and the estimated values are used to determine the embedding level. This pixel level adjustment can effectively reduce the distortion caused by data embedding. The experimental results and performance comparison with other reversible data hiding algorithms are presented to demonstrate the validity of the proposed algorithm. [ABSTRACT FROM PUBLISHER]