Multiscale Edge Research Articles

Nondestructive imaging of hidden defects in aircraft sandwich composites using terahertz time-domain spectroscopy

Aircraft sandwich composites are superior to ordinary composites and have been largely used in the manufacture of military aircraft. This study attempts to investigate the efficacy of terahertz (THz) time-domain spectroscopy (TDS) imaging technology in detecting hidden defects in aircraft glass fiber (GF) sandwich composites. The defects of various sizes, such as debonding, delamination, and multi-delamination, at different depths in GF A-sandwich structure composites with foam core, C-sandwich structure composites with honeycomb core, and sheet-to-sheet cementing structure composites were evaluated. The THz frequency-domain amplitude and time-domain amplitude imaging algorithms were used to visualize the defects simulated by ultrathin double-layer Teflon inserts. And the suitable image processing methods which include wavelet-based fusion and multiscale edge representation were employed. With a combination of high-resolution THz C-scan and B-scan imaging, both the horizontal size and location, and the vertical depth and thickness of the defects were obtained in three dimensions. This study experimentally demonstrated that THz imaging technology can clearly detect various hidden defects in aircraft GF sandwich composites through reflection or transmission imaging mode.

On Detection of Faint Edges in Noisy Images.

A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected. In this paper we offer a formalism to study this question and subsequently introduce computationally efficient multiscale edge detection algorithms designed to detect faint edges in noisy images. In our formalism we view edge detection as a search in a discrete, though potentially large, set of feasible curves. First, we derive approximate expressions for the detection threshold as a function of curve length and the complexity of the search space. We then present two edge detection algorithms, one for straight edges, and the second for curved ones. Both algorithms efficiently search for edges in a large set of candidates by hierarchically constructing difference filters that match the curves traced by the sought edges. We demonstrate the utility of our algorithms in both simulations and applications involving challenging real images. Finally, based on these principles, we develop an algorithm for fiber detection and enhancement. We exemplify its utility to reveal and enhance nerve axons in light microscopy images.

Image Inpainting Based on Patch-GANs

In this paper, we propose a novel image inpainting framework that takes advantage of holistic and structure information of the broken input image. Different from the existing models that complete the broken pictures using the holistic features of the input, our method adopts Patch-generative adversarial networks (GANs) equipped with multi-scale discriminators and edge process function to extract holistic, structured features, and restore the damaged images. After pre-training our Patch-GANs, the proposed network encourages our generator to find the best encoding of the broken input images in the latent space using a combination of a reconstruction loss, an edge loss, and global and local guidance losses. Besides, the reconstruction and the global guidance losses ensure the pixel reliability of the generated images, and the remaining losses guarantee the contents consistency between the local and global parts. The qualitative and quantitative experiments on multiple public datasets show that our approach has the ability to produce more realistic images compared with some existing methods, demonstrating the effectiveness and superiority of our method.

Echocardiography image segmentation using feed forward artificial neural network (FFANN) with fuzzy multi-scale edge detection (FMED)

In the recent past Echocardiography image segmentation is one of the significant process describes about the segment out inner and outer walls or other parts of the organ boundaries. However, this kind of segmentation process is one of the difficult for physicians because of inexperience or subject specialists with the previous cases. To enhance the cardiac image segmentation accuracy and to minimise the segmentation time a machine learning method such as neural networks has been proposed in the segmentation process. In this research, feed forward artificial neural network (FFANN) has been utilised and fuzzy multi-scale edge detection (FMED) process has been applied to detect the segmented edges to define the detected texture boundary with the help of FFANN weights. An experimental result shows an efficient learning capacity of FFANN and this work deals with the segmentation of ultrasound images using MATLAB implementation.

Echocardiography image segmentation using feed forward artificial neural network (FFANN) with fuzzy multi-scale edge detection (FMED)

In the recent past Echocardiography image segmentation is one of the significant process describes about the segment out inner and outer walls or other parts of the organ boundaries. However, this kind of segmentation process is one of the difficult for physicians because of inexperience or subject specialists with the previous cases. To enhance the cardiac image segmentation accuracy and to minimise the segmentation time a machine learning method such as neural networks has been proposed in the segmentation process. In this research, feed forward artificial neural network (FFANN) has been utilised and fuzzy multi-scale edge detection (FMED) process has been applied to detect the segmented edges to define the detected texture boundary with the help of FFANN weights. An experimental result shows an efficient learning capacity of FFANN and this work deals with the segmentation of ultrasound images using MATLAB implementation.

Novel Methods for Near-Surface Hydrogeological Feature Enhancement from High-Resolution Airborne Magnetic Data

The delineation of near-surface (0-300m) hydrostratigraphy and tectonic features is essential for successful characterisation of groundwater systems and subsequent hydrogeological modeling. While most remote sensing of such systems is commonly achieved using high-resolution airborne electromagnetic data, validated by drilling data, and complemented by the use of terrain and multispectral data, it is shown that there is also a useful role for high-resolution magnetic survey data. Various filtering of gridded magnetic data, when image-enhanced and interrogated with other datasets, reveal features such as faults, dykes and other structures which may influence the distribution and movement of groundwater. One of the most useful enhancements of magnetic data is tilt, in which the range of data from ±90° acts as an automatic gain control to highlight both strong and weak source responses. While it is difficult to obtain accurate depth information from magnetic data, useful relative depth estimates can be obtained by using, for example, the Tilt-depth method, in which half the width between the ±45° contours of the tilt grid is a measure of the depth to source. These depth estimates can be calibrated, where possible, by comparison with other data. Dip directions of source contacts can be estimated by using the attitudes of multiscale edges, derived from the maxima of total horizontal derivative data. Examples of the utility of high-resolution magnetic data, in its complementary role, are presented for two groundwater assessment project areas - the Menindee Lakes region in western NSW and the Keep River catchment in the Northern Territory.

Single image super-resolution using multi-scale deep encoder–decoder with phase congruency edge map guidance

This paper presents an end-to-end multi-scale deep encoder (convolution) and decoder (deconvolution) network for single image super-resolution (SISR) guided by phase congruency (PC) edge map. Our system starts by a single scale symmetrical encoder–decoder structure for SISR, which is extended to a multi-scale model by integrating wavelet multi-resolution analysis into our network. The new multi-scale deep learning system allows the low resolution (LR) input and its PC edge map to be combined so as to precisely predict the multi-scale super-resolved edge details with the guidance of the high-resolution (HR) PC edge map. In this way, the proposed deep model takes both the reconstruction of image pixels’ intensities and the recovery of multi-scale edge details into consideration under the same framework. We evaluate the proposed model on benchmark datasets of different data scenarios, such as Set14 and BSD100 - natural images, Middlebury and New Tsukuba - depth images. The evaluations based on both PSNR and visual perception reveal that the proposed model is superior to the state-of-the-art methods.

Perceptual Hashing Based Forensics Scheme for the Integrity Authentication of High Resolution Remote Sensing Image

High resolution remote sensing (HRRS) images are widely used in many sensitive fields, and their security should be protected thoroughly. Integrity authentication is one of their major security problems, while the traditional techniques cannot fully meet the requirements. In this paper, a perceptual hashing based forensics scheme is proposed for the integrity authentication of a HRRS image. The proposed scheme firstly partitions the HRRS image into grids and adaptively pretreats the grid cells according to the entropy. Secondly, the multi-scale edge features of the grid cells are extracted by the edge chains based on the adaptive strategy. Thirdly, principal component analysis (PCA) is applied on the extracted edge feature to get robust feature, which is then normalized and encrypted with secret key set by the user to receive the perceptual hash sequence. The integrity authentication procedure is achieved via the comparison between the recomputed perceptual hash sequence and the original one. Experimental results have shown that the proposed scheme has good robustness to normal content-preserving manipulations, has good sensitivity to detect local subtle and illegal tampering of the HRRS image, and has the ability to locate the tampering area.

Framelet regularization for uneven intensity correction of color images with illumination and reflectance estimation

To solve the problem of simultaneously estimating the illumination and reflectance (IR) from a single image based on the Retinex theory, an effective way is utilizing a Maximum-a-Posterior (MAP) distribution as an approximation. However, the current MAP-based image enhancement methods fail to fully utilize the property of the reflectance, which leads to the loss of detailed structures of images. Through a large number of observations, it is found that the properties of reflectance can be effectively extracted by a powerful operator called framelet transform. Therefore, we propose a novel image enhancement scheme with framelet regularization on the reflectance, which is able to simultaneously estimate the IR while keeping image details. To be specific, a MAP distribution is adopted where a framelet regularization is proposed as a prior to exploiting the multi-scale edge information and sparsity of reflectance. Then the MAP problem is converted to a minimization of an energy function, which can be efficiently solved by an alternating direction method of multipliers with split Bregman iteration (ADMM-SBI). Furthermore, an adaptive Gamma correction operator is proposed to avoid over-enhancement of the illumination. Experiments show that the proposed approach outperforms the state-of-the-arts in terms of brightness improvement, contrast enhancement and details preservation.

Fast horizon detection in maritime images using region-of-interest

In this article, we propose a fast method for detecting the horizon line in maritime scenarios by combining a multi-scale approach and region-of-interest detection. Recently, several methods that adopt a multi-scale approach have been proposed, because edge detection at a single is insufficient to detect all edges of various sizes. However, these methods suffer from high processing times, requiring tens of seconds to complete horizon detection. Moreover, the resolution of images captured from cameras mounted on vessels is increasing, which reduces processing speed. Using the region-of-interest is an efficient way of reducing the amount of processing information required. Thus, we explore a way to efficiently use the region-of-interest for horizon detection. The proposed method first detects the region-of-interest using a property of maritime scenes and then multi-scale edge detection is performed for edge extraction at each scale. The results are then combined to produce a single edge map. Then, Hough transform and a least-square method are sequentially used to estimate the horizon line accurately. We compared the performance of the proposed method with state-of-the-art methods using two publicly available databases, namely, Singapore Marine Dataset and buoy dataset. Experimental results show that the proposed method for region-of-interest detection reduces the processing time of horizon detection, and the accuracy with which the proposed method can identify the horizon is superior to that of state-of-the-art methods.

A novel approach for detecting the horizon using a convolutional neural network and multi-scale edge detection

This paper proposes a novel method for horizon detection that combines a multi-scale approach and a convolutional neural network (CNN). The ability to detect the horizon is the first step toward situational awareness of autonomous ships, which have recently attracted interest, and greatly affects the performance of subsequent steps and that of the overall system. Since typical approaches for horizon detection mainly use edge information, two challenging issues need to be overcome: non-stability of edge detection and complex maritime scenes. The proposed method first detects line features by combining edge information from the various scales to reduce the computational time while mitigating the non-stability of edge detection. Subsequently, CNN is used to verify the edge pixels belonging to the horizon to process complex maritime scenes that contain line features similar to the horizon and changes in the sea status. Finally, linear curve fitting along with median filtering are iteratively used to estimate the horizon line accurately. We compared the performance of the proposed method with state-of-the-art methods using the largest database publicly available. The experimental results showed that the accuracy with which the proposed method can identify the horizon is superior to that of state-of-the-art methods. Our method has a median positional error of less than 1.7 pixels from the center of the horizon and a median angular error of approximately 0.1 $$^{\circ }$$ . Further, our results showed that our method is the only one capable of detecting the horizon at high speed with high accuracy, which is attractive for practical applications.

Automated Chest X-Ray Screening: Can Lung Region Symmetry Help Detect Pulmonary Abnormalities?

Our primary motivator is the need for screening HIV+ populations in resource-constrained regions for exposure to Tuberculosis, using posteroanterior chest radiographs (CXRs). The proposed method is motivated by the observation that radiological examinations routinely conduct bilateral comparisons of the lung field. In addition, the abnormal CXRs tend to exhibit changes in the lung shape, size, and content (textures), and in overall, reflection symmetry between them. We analyze the lung region symmetry using multi-scale shape features, and edge plus texture features. Shape features exploit local and global representation of the lung regions, while edge and texture features take internal content, including spatial arrangements of the structures. For classification, we have performed voting-based combination of three different classifiers: Bayesian network, multilayer perception neural networks, and random forest. We have used three CXR benchmark collections made available by the U.S. National Library of Medicine and the National Institute of Tuberculosis and Respiratory Diseases, India, and have achieved a maximum abnormality detection accuracy (ACC) of 91.00% and area under the ROC curve (AUC) of 0.96. The proposed method outperforms the previously reported methods by more than 5% in ACC and 3% in AUC.

Using marine magnetic survey data to identify a gold ore-controlling fault: a case study in Sanshandao fault, eastern China

The Jiaodong Peninsula has the greatest concentration of gold ore in China and is characterized by altered tectonite-type gold ore deposits. This type of gold deposit is mainly formed in fracture zones and is strictly controlled by faults. Three major ore-controlling faults occur in the Jiaodong Peninsula—the Jiaojia, Zhaoping and Sanshandao faults; the former two are located on land and the latter is located near Sanshandao and its adjacent offshore area. The discovery of the world's largest marine gold deposit in northeastern Sanshandao indicates that the shallow offshore area has great potential for gold prospecting. However, as two ends of the Sanshandao fault extend to the Bohai Sea, conventional geological survey methods cannot determine the distribution of the fault and this is constraining the discovery of new gold deposits. To explore the southwestward extension of the Sanshandao fault, we performed a 1:25 000 scale marine magnetic survey in this region and obtained high-quality magnetic survey data covering 170 km2. Multi-scale edge detection and three-dimensional inversion of magnetic anomalies identify the characteristics of the southwestward extension of the Sanshandao fault and the three-dimensional distribution of the main lithologies, providing significant evidence for the deployment of marine gold deposit prospecting in the southern segment of the Sanshandao fault. Moreover, three other faults were identified in the study area and faults F2 and F4 are inferred as ore-controlling faults: there may exist other altered tectonite-type gold ore deposits along these two faults.

Focus and Blurriness Measure Using Reorganized DCT Coefficients for an Autofocus Application

In this paper, two metrics for measuring image sharpness are presented and used for an autofocus (AF) application. Both measures exploit reorganized discrete cosine transform (DCT) representation. The first metric is a focus measure, which involves optimal high- and middle-frequency coefficients to evaluate relative sharpness. It is robust to noise while remaining sensitive to the best focus position. A psychometric function-based metric is introduced to quantify the focus measure. The second metric is a no-reference blurriness metric, which is used to measure absolute blurriness. It first constructs multiscale DCT edge maps using directional energy information and then determines image blurriness by combining change information in edge structures with image contrast. This metric gives predictions that are closely correlated with subjective perceived scores and shows performance comparable with that of state-of-the-art methods, especially for noisy images. For noisy situations, the two metrics are adjusted adaptively according to the estimated noise level. To prevent the introduction of extra computational load, an efficient noise-level estimation algorithm based on median absolute deviation is presented. This algorithm exploits only the available reorganized DCT coefficients. With the focus and blurriness measures, an AF method for which the two metrics play an important role was developed. Because of their high-quality performance, the realized AF function is able to locate the best focus position swiftly and reliably.

Interactive Image Segmentation on Multiscale Appearances

Interactive segmentation algorithms based on graph cuts can extract the foreground successfully from a simple scene. However, they are ineffective for complex-scene images. To improve the segmentation performance, we propose an interactive segmentation algorithm, which combines the segmentation and the multiscale smoothing into a unified model. This model consists of the segmentation and the smoothing. The segmentation relies on the multiscale appearances, which depend on the smoothing. In the smoothing part, the total variation is used to preserve the geometric shape of the foreground and captures different scale edges and appearances for segmentation. Combining the multiscale edges and appearances, we propose a novel Gibbs energy functional for segmentation. The exact global minima of the energy can be found by jointing the image smoothing and the optimization of segmentation. In this algorithm, the smoothing motivates that the foreground could be detected easily from a proper scale. Experimental results on the BSD300 data set and Weizmann horse’s database indicate that, compared with the existing interactive segmentation algorithms, the proposed algorithm provides competitive performance in terms of segmentation accuracy.

Reduced-reference quality assessment of DIBR-synthesized images based on multi-scale edge intensity similarity

Depth-image-based-rendering (DIBR) plays an important role in view synthesis for free-viewpoint videos. The warping process in DIBR causes geometric displacement, which distributes intensively around edges, and the subsequent rendering process results in the impairment of edges. Traditional 2D image quality metrics are limited in the quality evaluation of DIBR-synthesized images. In this paper, we present a reduced-reference quality metric for DIBR-synthesized images by only extracting several feature values, namely multi-scale Edge Intensity Similarity (EIS). The original and synthesized images are first downsampled to generate images with different resolutions. Then an edge detection process is conducted on each scale and the edge intensity is calculated. The similarity of the edge intensity between each downsampled original image and the corresponding synthesized image is computed. Finally, the average similarity is calculated as the quality score of the DIBR-synthesized image. Experiments conducted on IRCCyN/IVC DIBR image and video databases demonstrate that the proposed method overall outperforms traditional 2D and existing DIBR-targeted quality metrics.

An Advanced Multiscale Edge Detector Based on Gabor Filters for SAR Imagery

The ratio of averages is a robust edge detector which provides the property of constant false alarm rate for synthetic aperture radar (SAR) imagery. However, the rectangular window used in the calculation of local mean may cause numerous false maxima. The size of the processing window also has a significant effect on the detection performance, but it is difficult to determine the optimum window size. In this letter, we first propose a new ratio-based detector that is constructed by the Gabor odd filter. The scale of the proposed detector is related to the size of the processing window. Then, edge strength maps extracted by multiscale detectors are combined using an edge tracking algorithm to form a final response. We used the receiver operating characteristic curves to evaluate the performance of the proposed detector. The experimental results on simulated and real-world SAR images show that the proposed multiscale edge detector yields an accurate and consecutive edge response.

SAR Image Content Retrieval Based on Fuzzy Similarity and Relevance Feedback

This paper presents a new content-based synthetic aperture radar (SAR) image retrieval method to search out SAR image patches, which consists of two essential parts: an initial retrieval and later refined results. To obtain the proper initial retrievals, we develop a similarity measure named region-based fuzzy matching (RFM) to evaluate the similarities between SAR image patches. First, to reduce the negative influence of speckle noise, we segment the SAR image patches into brightness-texture regions at the superpixel level rather than the pixel level. Second, a multiscale edge detector is utilized to resolve the multiscale property of the SAR image patches, and then the edge regions of the SAR image patches are defined by those edge features. Third, to overcome the segmented uncertainty and the blurry boundaries, the obtained regions are described by fuzzy features. Finally, the RFM similarity between two SAR image patches is converted into the linear summation of the resemblance between different fuzzy feature sets. After we obtain the initial retrieval results, the multiple relevance feedback (MRF) scheme is proposed to refine the original ranked list. In this scheme, different relevance feedback approaches are carried out respectively, and then their results are fused to improve the initial retrieval. In addition, a new kernel function based on the RFM measure is developed for MRF. The encouraging experimental results counted on a manually constructed ground truth SAR image patch dataset demonstrate that our retrieval method is effective for SAR images compared with some existing approaches proposed in the remote sensing community

Built-up area detection based on a Bayesian saliency model

Built-up area detection is very important for applications such as urban planning, urban growth detection and land use monitoring. In this paper, we address the problem of built-up area detection from the perspective of visual saliency computation. Generally, areas containing buildings attract more attentions than forests, lands and other backgrounds. This paper explores a Bayesian saliency model to automatically detect urban areas. Firstly, prior probability is computed by using fast multi-scale edge distribution. Then the likelihood is obtained by modeling the distributions of color and orientation. Built-up areas are further detected by segmenting the final saliency map using Graph Cut algorithm. Experimental results demonstrate that the proposed method can extract built-up area efficiently and accurately.

Measurement of droplet sizes in bubbly oil-in-water flows using a fluid-sampling device

Abstract One important characteristic of bubbly oil-in-water two-phase flows is the droplet size distribution, which has a significant effect on the heat/mass transfer between phases and the turbulence characteristics. In this study, a sampling device of dynamic fluid is designed to trap the morphological structures of the bubbly oil-in-water flows with low flow rate and high water cut. In the experiment, oil droplets in vertical upward pipe are forced into a sampling slot which is specifically designed to ensure that the passing oil droplets are not overlapped. The images of the oil droplets are recorded using a high speed camera when the mixture flows through the sampling slot. The methods of multi-scale edge detection and watershed segmentation are employed to extract the edges of the solitary and adjoining oil droplets in the flow images. Based on the detected oil droplet edges the equivalent oil droplet diameters are derived and compared with a model of maximum droplet diameter. Additionally, time-frequency entropy and the total energy of measured conductance signals are extracted using Adaptive Optimal Kernel Time-Frequency Representation (AOK TFR) to characterize the droplet size distribution of bubbly oil-water two-phase flows.