Low-level Image Research Articles

Assessment of Image Quality of Dual Energy 256 MDCT Technique Focused on keV Changes for MCA Stroke in Cerebral Angiography : Single Energy CT Standard Reference Mode

The purpose of this study was to evaluate the usefulness of cerebral angiography in each energy level by using dual energy technique in CT. Methods were performed on 15 DE images and SE images of CT angiography. For the analysis of images, mean value, standard deviation, SNR and CNR value were determined by setting ROI on MCA, brain parenchyma tissue, and back ground. As a result of concurrent visual evaluation with Likert 5 point scale, the clearest MCA image was confirmed at DE 40 keV and SE 120 kVp(p>0.05). The SNR value of the SE image was measured to be similar to the 40 keV energy level of the DE image. The low energy level image of 40 keV and 50 keV was measured with a high SNR and the contrast ratio was higher than that of the high energy image.

An Improvement to a Class of Intensity based Spatial Domain Corner Detection Algorithms using Image Fission and Fusion

Corners of an object are important as features for the representation and analysis of its shape in computer vision. Corner detection, particularly in real scenes, is still a challenge. Most of the corner detectors found in the literature generate a number of false corners, which is not acceptable in real-life applications. In this paper, an improvement to a class of corner detection algorithms is presented using image fission/fusion. In this approach, a grayscale image is first divided into several bit-planes. A corner detector is applied on all the bit-planes simultaneously and a threshold (bitplane) is obtained using the concept of information gain. Finally, all the higher bit-plane corners are recombined (up to some thresholded bit-plane) to obtain the final set of corners. Here the corner detection algorithm is considered as a binary classification problem. Experimental results show that this improved approach reduces the number of erroneous corner detection relative to existing spatial domain corner detection algorithms. The improvements are established with the help of a number of performance measures proposed by various researchers. The proposed approach works better with respect to computational time also. This approach can easily be utilized in different low-level image processing applications.

Düşük Seviye Görsel Öznitelikler ile Basit Bir Konvolüsyonel Sinir Ağından Elde Edilen Özniteliklerin Birleştirilmesi

In the traditional image processing approaches, first low-level image features are extracted and then they are sent to a classifier or a recognizer for further processing. While the traditional image processing techniques employ this step-by-step approach, majority of the recent studies prefer layered architectures which both extract features and do the classification or recognition tasks. These architectures are referred as deep learning techniques and they are applicable if sufficient amount of labeled data is available and the minimum system requirements are met. Nevertheless, most of the time either the data is insufficient or the system sources are not enough. In this study, we experimented how it is still possible to obtain an effective visual representation by combining low-level visual features with features from a simple deep learning model. As a result, combinational features gave rise to 0.80 accuracy on the image data set while the performance of low-level features and deep learning features were 0.70 and 0.74 respectively.

PNEN: Pyramid Non-Local Enhanced Networks.

Existing neural networks proposed for low-level image processing tasks are usually implemented by stacking convolution layers with limited kernel size. Every convolution layer merely involves in context information from a small local neighborhood. More contextual features can be explored as more convolution layers are adopted. However it is difficult and costly to take full advantage of long-range dependencies. We propose a novel non-local module, Pyramid Non-local Block, to build up connection between every pixel and all remain pixels. The proposed module is capable of efficiently exploiting pairwise dependencies between different scales of low-level structures. The target is fulfilled through first learning a query feature map with full resolution and a pyramid of reference feature maps with downscaled resolutions. Then correlations with multi-scale reference features are exploited for enhancing pixel-level feature representation. The calculation procedure is economical considering memory consumption and computational cost. Based on the proposed module, we devise a Pyramid Non-local Enhanced Networks for edge-preserving image smoothing which achieves state-of-the-art performance in imitating three classical image smoothing algorithms. Additionally, the pyramid non-local block can be directly incorporated into convolution neural networks for other image restoration tasks. We integrate it into two existing methods for image denoising and single image super-resolution, achieving consistently improved performance.

FoGDbED: Fractional-order Gaussian derivatives-based edge-relevant structure detection using Caputo-Fabrizio definition

Edge-relevant structure features (ERSFs), e.g., object edges, boundaries and contours, junctions, etc. play an important role in low and middle level image processing tasks, such as image segmentation, as well as in higher-level computer vision tasks, such as scene analysis and content understanding. Commonly-used ERSF detection methods employ the integer-order differential-based methods, which are noise-sensitive and have less selectivity of ERSFs. Hence, they are difficult to effectively extract object edges or boundaries, especially in natural images with rich fractal-like structures. This paper presents a highly selective and noise-robust ERSF detection approach based on the fractional-order Gaussian derivatives (FoGDs) by using the definition of Caputo-Fabrizio derivative, termed FoGDbED. FoGDbED is constructed based on the concept of robust edge feature selection and inflexion point localization, whose detection mask can be designed with a close-form expression of FoGDs. Theoretical analysis and experimental results show that the proposed FoGDbED operator is capable of extracting complex ERSFs in natural images especially detecting object edges and junctions in natural images with serious noises to achieve a better visual effect.

Content based image retrieval using fusion of multilevel bag of visual words

Content based image retrieval (CBIR) is the art of finding visually and conceptually similar pictures to the given query picture. Usually, there is a semantic gap between low-level image features and high-level concepts perceived by viewers. Although features such as intensity and color enforce a good distinction between the images in terms of greater detail, they convey little semantic information. Therefore, employing higher-level features such as properties of regions and objects within the image could improve the retrieval performance. In this study, features are extracted at the pixel, region, object, and concept levels. The fusion step concatenates the four feature vectors and maps it to a lower-dimensional space using auto-encoders. The experiments confirm the efficiency of the proposed method over the individual feature groups and also the state of the art methods.

A fusion network for road detection via spatial propagation and spatial transformation

In this paper, we address the fusion of image and point cloud data for road detection. To take advantage of both deep network and multi-modal data fusion, we propose an end-to-end road segmentation network called SPSTFN (Spatial Propagation and Spatial Transformation Fusion Network). Our method considers the model-level fusion and dual-view fusion in the network simultaneously for the first time. Specifically, the proposed SPSTFN contains three parts: the point cloud branch, the image branch, and the fusion block. Firstly, we design a simple but efficient lightweight network to handle the unordered and sparse point cloud to obtain a coarse representation of the road area. Then, an equal-resolution convolutional block is adopted to capture the low-level features of the image which are used to produce the heat diffusion coefficients of the joint anisotropic diffusion based spatial propagation model. Thirdly, we conduct the diffusion process on the coarse representation under the guidance of the learned low-level image features, both in the perspective and bird views, via the spatial transformation in the network. Finally, the diffusion results of the two views are then integrated to generate the final refined representation of the road area. The proposed fusion method is totally data-driven and parameter-free, and the whole fusion network can be trained with the standard BP (Back Propagation) algorithm. Without any additional process steps and pre-training, the proposed method obtains competitive results on the KITTI Road Benchmark.

Generate Structured Radiology Report from CT Images Using Image Annotation Techniques: Preliminary Results with Liver CT.

A medical annotation system for radiology images extracts clinically useful information from the images, allowing the machines to infer useful abstract semantics and become capable of automatic reasoning and making diagnostic decision. It also supplies human-interpretable explanation for the images. We have implemented a computerized framework that, given a liver CT image, predicts radiological annotations with high accuracy, in order to generate a structured report, which includes predicting very specific high-level semantic content. Each report of a liver CT image is related to different inhomogeneous parts like the liver, lesion, and vessel. We put forward a claim that gathering all kinds of features is not suitable for filling all parts of the report. As a matter of fact, for each group of annotations, one should find and extract the best feature that results in the best answers for that specific annotation. To this end, the main challenge is discovering the relationships between these specific semantic concepts and their association with the low-level image features. Our framework was implemented by combining a set of the state-of-the-art low-level imaging features. In addition, we propose a novel feature (DLBP (deep local binary pattern)) based on LBP that incorporates multi-slice analysis in CT images and further improves the performance. In order to model our annotation system, two methods were used, namely multi-class support vector machine (SVM) and random subspace (RS) which is an ensemble learning method. Applying this representation leads to a high prediction accuracy of 93.1% despite its relatively low dimension in comparison with the existing works.

High-order Feature Learning for Multi-atlas based Label Fusion: Application to Brain Segmentation with MRI.

Multi-atlas based segmentation methods have shown their effectiveness in brain regions-of-interesting (ROIs) segmentation, by propagating labels from multiple atlases to a target image based on the similarity between patches in the target image and multiple atlas images. Most of the existing multiatlas based methods use image intensity features to calculate the similarity between a pair of image patches for label fusion. In particular, using only low-level image intensity features cannot adequately characterize the complex appearance patterns (e.g., the high-order relationship between voxels within a patch) of brain magnetic resonance (MR) images. To address this issue, this paper develops a high-order feature learning framework for multi-atlas based label fusion, where high-order features of image patches are extracted and fused for segmenting ROIs of structural brain MR images. Specifically, an unsupervised feature learning method (i.e., means-covariances restricted Boltzmann machine, mcRBM) is employed to learn high-order features (i.e., mean and covariance features) of patches in brain MR images. Then, a group-fused sparsity dictionary learning method is proposed to jointly calculate the voting weights for label fusion, based on the learned high-order and the original image intensity features. The proposed method is compared with several state-of-the-art label fusion methods on ADNI, NIREP and LONI-LPBA40 datasets. The Dice ratio achieved by our method is 88:30%, 88:83%, 79:54% and 81:02% on left and right hippocampus on the ADNI, NIREP and LONI-LPBA40 datasets, respectively, while the best Dice ratio yielded by the other methods are 86:51%, 87:39%, 78:48% and 79:65% on three datasets, respectively.

Privileged Modality Distillation for Vessel Border Detection in Intracoronary Imaging.

Intracoronary imaging is a crucial imaging technology in coronary disease diagnosis as it visualizes the internal tissue morphologies of coronary arteries. Vessel border detection in intracoronary images (VBDI) is desired because it can help the succeeding procedures of computer-aided disease diagnosis. However, existing VDBI methods suffer from the challenge of vessel-environment variability (i.e. high intra- and inter-subject diversity of vessels and their surrounding tissues appeared in images). This challenge leads to the ineffectiveness in the vessel region representation for hand-crafted features, in the receptive field extraction for deeply-represented features, as well as performance suppression derived from clinical data limitation. To solve this challenge, we propose a novel privileged modality distillation (PMD) framework for VBDI. PMD transforms the single-input-single-task (SIST) learning problem in the single-mode VBDI to a multiple-input-multiple-task (MIMT) problem by using the privileged image modality to help the learning model in the target modality. This learns the enriched high-level knowledge with similar semantics and generalizes PMD on diversity-increased low-level image features for improving the model adaptation to diverse vessel environments. Moreover, PMD refines MIMT to SIST by distilling the learned knowledge from multiple to one modality. This eliminates the reliance on privileged modality in the test phase, and thus enables the applicability to each of different intracoronary modalities. A structure-deformable neural network is proposed as an elaborately-designed implementation of PMD. It expands a conventional SIST network structure to the MIMT structure, and then recovers it to the final SIST structure. The PMD is validated on intravascular ultrasound imaging and optical coherence tomography imaging. One modality is the target, and the other one can be considered as the privileged modality owing to their semantic relatedness. The experiments show that our PMD is effective in VBDI (e.g. the Dice index is larger than 0.95), as well as superior to six state-of-the-art VBDI methods.

Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking

Tracking-by-detection is one of the most popular approaches to tracking multiple objects in which the detector plays an important role. Sometimes, detector failures caused by occlusions or various poses are unavoidable and lead to tracking failure. To cope with this problem, we construct a heterogeneous association graph that fuses high-level detections and low-level image evidence for target association. Compared with other methods using low-level information, our proposed heterogeneous association fusion (HAF) tracker is less sensitive to particular parameters and is easier to extend and implement. We use the fused association graph to build track trees for HAF and solve them by the multiple hypotheses tracking framework, which has been proven to be competitive by introducing efficient pruning strategies. In addition, the novel idea of adaptive weights is proposed to analyze the contribution between motion and appearance. We also evaluated our results on the MOT challenge benchmarks and achieved state-of-the-art results on the MOT Challenge 2017.

Comparative analysis of Median filter family for Removing High-Density Noise in Magnetic Resonance Images

Magnetic Resonance Imaging (MRI) is a medical indicative test utilized for taking images of the tissue points of interest of the human body. During image acquisition, MRI images can be damaged by many noise signals such as impulse noise. One reason for this noise may be a sharp or sudden disturbance in the image signal. The removal of impulse noise is one of the real difficulties. As of late, numerous image de-noising methods were produced for removing the impulse noise from images. Comparative analysis of known and modern methods of median filter family is presented in this paper. These filters can be categorized as follows: Standard Median Filter; Adaptive Median Filter; Progressive Switching Median Filter; Noise Adaptive Fuzzy Switching Median Filter; and Different Applied Median Filter. The de-noising technique performance for each one is evaluated and compared using Peak Signal Noise Ratio, Structural Similarity index Metric, and Beta metric as quantitative metrics. The experimental results showed that the latest de-noising technique, Different Applied Median Filter (DAMF), produced better results in removing impulse noise compared with the other de-noising techniques. However, this filter produced de-noised image with nonlinear edges in high-density noise. As a result, noise removal from images is one of the low-level images processing which is considered as a first step in many image applications. Therefore, the efficiency of any image processed depends on the efficiency of noise removal technique.

Ekstrasi Fitur Berbasis Tekstur Menggunakan Distribusi Statistik Pada Sistem Temu Balik Citra

Feature extraction is a method to capturing visual content of images for indexing and retrieval. This research using texture, low level image feature as gernal (visual) feature for extracting feature of images. Image texture measurement using selected histogram based features such as mean (average of grey level), standard deviation, skewness, energy and smoothness. The basis of measure of similarity in this research is Canberra distance. Performance of CBIR system used precision and recall.

Local Regression Ranking for Saliency Detection.

Saliency detection is an important and challenging research topic due to the variety and complex of the background and saliency regions. In this paper, we present a novel unsupervised saliency detection approach by exploiting a learning-based ranking framework. First, the local linear regression model is adopted to simulate the local manifold structure of every image element, which is approximately linear. Using the background queries from the boundary prior, we construct a unified objective function to globally minimize all the errors of the local models for the whole image element points. The Laplacian matrix is learned via optimizing the unified objective function. Low-level image features as well as high-level semantic information extracted from deep neural networks are used for the Laplacian matrix learning. Based on the learnt Laplacian matrix, the saliency of the image element is measured as the relevance ranking to the background queries. The foreground queries are obtained from the background-based saliency and the relevance ranking to the foreground queries is calculated in the same way as the background-based saliency. Second, we calculate an enhanced similarity matrix by fusing two different-level deep feature metrics through cross diffusion. A propagation algorithm uses this enhanced similarity matrix to better exploit the intrinsic relevance of similar regions and improve the saliency ranking results effectively. Results on four benchmark datasets with pixel-wise accurate labelling demonstrate that the proposed unsupervised method shows better performance compared with the newest state-of-the-art methods and is competitive with deep learning-based methods.

An Enhanced Framework for Content Based Medical Image Retrieval using Deep Neural Network

As the technology growth fuelled by low cost tech in the areas of compute, storage the need for faster retrieval and processing of data is becoming paramount for organizations. The medical domain predominantly for medical image processing with large size is critical for making life critical decisions. Healthcare community relies upon technologies for faster and accurate retrieval of images. Traditional, existing problem of efficient and similar medical image retrieval from huge image repository are reduced by Content Based Image Retrieval (CBIR) . The major challenging is an semantic gap in CBIR system among low and high level image features. This paper proposed, enhanced framework for content based medical image retrieval using DNN to overcome the semantic gap problem. It is outlines the steps which can be leveraged to search the historic medical image repository with the help of image features to retrieve closely relevant historic image for faster decision making from huge volume of database. The proposed system is assessed by inquisitive amount of images and the performance efficiency is calculated by precision and recall evaluation metrics. Experimental results obtained the retrieval accuracy is 79% based on precision and recall and this approach is preformed very effectively for image retrieval performance.

Quality assessment of images with multiple distortions based on phase congruency and gradient magnitude

In image communication systems, images are often contaminated by multiple types of distortions. However, most existing image quality assessment (IQA) methods mainly focused on a single type of distortions. In this paper, we proposed a no-reference (NR) IQA method for images with multiple distortions. Image distortions not only destroy the intensity of low-level image features, but also alter their distribution, to both of which the human vision system (HVS) is sensitive. Based on these observations, low-level features are represented by phase congruency (PC) which is consistent with human perception. The distribution of low-level features is extracted using local binary pattern (LBP) in PC domain at multiple scales, which can effectively characterize the impact of multiple distortions on images. Given that PC is contrast invariant while the contrast does affect perceptual image quality of the HVS, image gradient magnitude (GM) is employed as a weighting factor for LBP histogram creation. Finally a support vector regression model is trained to map the gradient-weighted LBP histograms in PC domain at multi-scale to quality scores. Experimental results on two benchmark databases demonstrate that the proposed method achieves high consistency with subjective perception and performs better than other state-of-the-art full-reference (FF) and NR IQA methods.

Perception of human skin conditions and imagestatistics.

The color and texture of human skin provide useful information in evaluating a person's health, emotion, attractiveness, and so on. Whereas the appearance of skin is a product of optical properties originating from its own biophysical substrates, recent psychophysical studies of surface material perception indicate a possibility that humans can perceive skin conditions from relatively simple image features such as texture statistics. The present study investigated the structure of multidimensional perceptual rating data for 289 female skin images and analyzed diagnostic low-level image statistics. We found that various skin appearances can be summarized into two dimensions, pleasantness and glossiness, and either dimension is well correlated with a small set of subband luminance and color statistics. We confirmed that manipulations of these critical image statistics significantly alter the appearance of skin in the expected direction. The results support a notion that humans perceive skin properties essentially based on two cardinal dimensions as predicted by simple image statistics.

Deep Visible and Thermal Image Fusion for Enhanced Pedestrian Visibility.

Reliable vision in challenging illumination conditions is one of the crucial requirements of future autonomous automotive systems. In the last decade, thermal cameras have become more easily accessible to a larger number of researchers. This has resulted in numerous studies which confirmed the benefits of the thermal cameras in limited visibility conditions. In this paper, we propose a learning-based method for visible and thermal image fusion that focuses on generating fused images with high visual similarity to regular truecolor (red-green-blue or RGB) images, while introducing new informative details in pedestrian regions. The goal is to create natural, intuitive images that would be more informative than a regular RGB camera to a human driver in challenging visibility conditions. The main novelty of this paper is the idea to rely on two types of objective functions for optimization: a similarity metric between the RGB input and the fused output to achieve natural image appearance; and an auxiliary pedestrian detection error to help defining relevant features of the human appearance and blending them into the output. We train a convolutional neural network using image samples from variable conditions (day and night) so that the network learns the appearance of humans in the different modalities and creates more robust results applicable in realistic situations. Our experiments show that the visibility of pedestrians is noticeably improved especially in dark regions and at night. Compared to existing methods we can better learn context and define fusion rules that focus on the pedestrian appearance, while that is not guaranteed with methods that focus on low-level image quality metrics.

Center bias outperforms image salience but not semantics in accounting for attention during scene viewing.

How do we determine where to focus our attention in real-world scenes? Image saliency theory proposes that our attention is 'pulled' to scene regions that differ in low-level image features. However, models that formalize image saliency theory often contain significant scene-independent spatial biases. In the present studies, three different viewing tasks were used to evaluate whether image saliency models account for variance in scene fixation density based primarily on scene-dependent, low-level feature contrast, or on their scene-independent spatial biases. For comparison, fixation density was also compared to semantic feature maps (Meaning Maps; Henderson & Hayes, Nature Human Behaviour, 1, 743-747, 2017) that were generated using human ratings of isolated scene patches. The squared correlations (R2) between scene fixation density and each image saliency model's center bias, each full image saliency model, and meaning maps were computed. The results showed that in tasks that produced observer center bias, the image saliency models on average explained 23% less variance in scene fixation density than their center biases alone. In comparison, meaning maps explained on average 10% more variance than center bias alone. We conclude that image saliency theory generalizes poorly to real-world scenes.

Automatic liver segmentation by integrating fully convolutional networks into active contour models.

Automatic and accurate three-dimensional (3D) segmentation of liver with severe diseases from computed tomography (CT) images is a challenging task. Fully convolutional networks (FCNs) have emerged as powerful tools for automatic semantic segmentation, with multiple potential applications in medical imaging. However, the use of a large receptive field and multiple pooling layers in the network leads to poor localization around object boundaries. The network usually makes pixel-wise prediction independently, making it difficult to respect local label consistency and enforce the smoothness of the object boundary. We have developed an automatic liver segmentation method based on a novel framework that integrates fully convolutional network predictions into active contour models (ACM). We use only a single network architecture to generate a pixel label map containing spatial regional information (foreground and background) as well as layered boundary information. We exploit the structured network outcome to define an external constraint force of active contour models. A unique property of the designed force is that both its strength and direction are adaptive to its position and relative distance to the object boundary. The resulting integrated active contour models have the advantages of incorporating both high-level and low-level image information simultaneously, while enforcing the smoothness of the contour. Because the external constraint force can push the evolving contour to the liver boundary and exists everywhere in the image domain, it allows us to place the initial contour far away from the liver boundary. It potentially allows us to control the evolution of the contour in order to preserve the topology of the liver. We have trained and evaluated our model on 73 liver CT scans from a clinic study. The integrated ACM model yields mean dice coefficients (DICE) 95.8±1.4 (%). Without further fine-tuning the network weights for two independent datasets, it yields mean DICE 96.2±0.9 (%) for the SLIVER07 training dataset, and mean DICE 94.3±2.7 (%) for the LiTS training dataset. In comparison with FCN alone model, the integrated ACM model yields improvements in terms of surface distance and DICE values for almost all the cases. Furthermore, the initialization of the active contour can be very far away from the liver boundary. Experimental results for segmenting livers (with severe diseases on CT images resulting in shape and density abnormalities) have revealed that our proposed model improves segmentation results in comparison with FCN alone. Without further fine-tuning the network weights for two independent datasets, the model is capable of handling image variations from different datasets due to its inherent deformable nature. It is relatively easy to integrate more advanced (either existing or future) FCN architecture into our framework to further improve the segmentation performance.