Multi-scale Contrast Research Articles

Salient object detection based on multi-scale contrast

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks.

No-reference high-dynamic-range image quality assessment based on tensor decomposition and manifold learning.

The practical applications of the full-reference image quality assessment (IQA) method are limited. Here, we propose a new no-reference quality assessment method for high-dynamic-range (HDR) images. First, tensor decomposition is used to generate three feature maps of an HDR image, considering color and structure information of the HDR image. Second, for a given HDR image, because its first feature map contains its main energy and important structural feature information, manifold learning is used in the first feature map to find the inherent geometric structure of high-dimensional data in a low-dimensional manifold. In addition, the corresponding multi-scale manifold structure features are extracted from the first feature map. For the second and third feature maps of the HDR image, multi-scale contrast features are extracted, as they reflect the perceived detail contrast information of the HDR image. Finally, the extracted features are aggregated by support vector regression to obtain the objective quality prediction score of the HDR image. Experimental results show that the proposed method is superior to some representative full- and no-reference methods, and even superior to the full-reference HDR IQA method, HDR-VDP-2.2, on the Nantes database. The proposed method has a higher consistency with human visual perception.

Detection of cropland field parcels from Landsat imagery

A slowdown in global agricultural expansion, spurred by land limitations, improved technologies, and demand for specific crops has led to increased agricultural intensification. While agricultural expansion has been heavily scrutinized, less attention has been paid to changes within cropland systems. Here we present a method to detect individual cropland field parcels from temporal Landsat imagery to improve cropland estimates and better depict the scale of farming across South America. The methods consist of multi-spectral image edge extraction and multi-scale contrast limited adaptive histogram equalization (CLAHE) and adaptive thresholding using Landsat Surface Reflectance Climate Data Record (CDR) products. We tested our methods across a South American region with approximately 82% of the 2000/2001 total cropland area, using a Landsat time series composite with a January 1, 2000 to August 1, 2001 timeframe. A thematic accuracy assessment revealed an overall cropland f-score of 91%, while an object-based assessment of 5480 fields showed low geometric errors. The results illustrate that Landsat time series can be used to accurately estimate cropland in South America, and the low geometric errors of the per-parcel estimates highlight the applicability of the proposed methods over a large area. Our approach offers a new technique of analyzing agricultural changes across a broad geographic scale. By using multi-temporal Landsat imagery with a semi-automatic field extraction approach, we can monitor within-agricultural changes at a high degree of accuracy, and advance our understanding of regional agricultural expansion and intensification dynamics across South America.

Detecting Saliency in Infrared Images via Multiscale Local Sparse Representation and Local Contrast Measure

For infrared images, it is a formidable challenge to highlight salient regions completely and suppress the background noise effectively at the same time. To handle this problem, a novel saliency detection method based on multiscale local sparse representation and local contrast measure is proposed in this paper. The saliency detection problem is implemented in three stages. First, a multiscale local sparse representation based approach is designed for detecting saliency in infrared images. Using it, multiple saliency maps with various scales are obtained for an infrared image. These maps are then fused to generate a combined saliency map, which can highlight the salient region fully. Second, we adopt a local contrast measure based technique to process the infrared image. It divides the image into a number of image blocks. Then these blocks are utilized to calculate the local contrast to generate a local contrast measure based saliency map. In this map, the background noise can be suppressed effectually. Last, to make full use of the advantages of the above two saliency maps, we propose combining them together using an adaptive fusion scheme. Experimental results show that our method achieves better performance than several state-of-the-art algorithms for saliency detection in infrared images.

Efficient visual attention driven framework for key frames extraction from hysteroscopy videos

Recent years have shown enthusiastic research interests in diagnostic hysteroscopy (DH), where various regions of the female reproductive system are visualized for diagnosing uterine disorders. Currently, the hysteroscopy videos produced during various sessions of patients are stored in medical libraries, which are usually browsed by medical specialists Gynecologists to visualize previous videos of a patient or to study similar cases. However, the abundant redundancy of frames in DH videos make this searching relatively more difficult for gynecologists, wasting their time browsing such large libraries. In this context, video summarization can be used to reduce this redundancy by extracting key frames, thus making the process of browsing and indexing DH videos more efficient. In this letter, we propose an efficient domain-specific visual attention-driven framework for summarizing DH videos. For key frames extraction, multi-scale contrast, texture, curvature, and motion based saliency features are computed for each frame using integral image, which are then fused by a linear weighted fusion scheme to acquire a final saliency map. Experimental results in comparison with other related state-of-the-art schemes confirm the effectiveness and efficiency of the proposed framework.

Multi-scale contrast enhancement of oriented features in 2D images using directional morphology

This paper presents a multi-scale contrast enhancement scheme for improving the visual quality of directional features present in 2D gray scale images. Directional morphological filters are employed to locate and extract the scale-specific image features with different orientations which are subsequently stored in a set of feature images. The final enhanced image is constructed by weighted combination of these feature images with the original image. While construction, the feature images corresponding to progressively smaller scales are made to have higher proportion of contribution through the use of progressively larger weights. The proposed method has been formulated, implemented and executed on a set of real 2D gray scale images with oriented features. The experimental results visually establish the efficacy of the method. The proposed method has been compared with other similar methods both on subjective and objective basis and the overall performance is found to be satisfactory.

Multiscale contrast similarity deviation: An effective and efficient index for perceptual image quality assessment

Perceptual image quality assessment (IQA) uses a computational model to assess the image quality in a fashion consistent with human opinions. A good IQA model should consider both the effectiveness and efficiency. To meet this need, a new model called multiscale contrast similarity deviation (MCSD) is developed in this paper. Contrast is a distinctive visual attribute closely related to the quality of an image. To further explore the contrast features, we resort to the multiscale representation. Although the contrast and the multiscale representation have already been used by other IQA indices, few have reached the goals of effectiveness and efficiency simultaneously. We compared our method with other state-of-the-art methods using six well-known databases. The experimental results showed that the proposed method yielded the best performance in terms of correlation with human judgments. Furthermore, it is also efficient when compared with other competing IQA models.

ANAlyte: A modular image analysis tool for ANA testing with indirect immunofluorescence

Background and objectivesThe automated analysis of indirect immunofluorescence images for Anti-Nuclear Autoantibody (ANA) testing is a fairly recent field that is receiving ever-growing interest from the research community. ANA testing leverages on the categorization of intensity level and fluorescent pattern of IIF images of HEp-2 cells to perform a differential diagnosis of important autoimmune diseases. Nevertheless, it suffers from tremendous lack of repeatability due to subjectivity in the visual interpretation of the images. The automatization of the analysis is seen as the only valid solution to this problem. Several works in literature address individual steps of the work-flow, nonetheless integrating such steps and assessing their effectiveness as a whole is still an open challenge. MethodsWe present a modular tool, ANAlyte, able to characterize a IIF image in terms of fluorescent intensity level and fluorescent pattern without any user-interactions. For this purpose, ANAlyte integrates the following: (i) Intensity Classifier module, that categorizes the intensity level of the input slide based on multi-scale contrast assessment; (ii) Cell Segmenter module, that splits the input slide into individual HEp-2 cells; (iii) Pattern Classifier module, that determines the fluorescent pattern of the slide based on the pattern of the individual cells. ResultsTo demonstrate the accuracy and robustness of our tool, we experimentally validated ANAlyte on two different public benchmarks of IIF HEp-2 images with rigorous leave-one-out cross-validation strategy. We obtained overall accuracy of fluorescent intensity and pattern classification respectively around 85% and above 90%. We assessed all results by comparisons with some of the most representative state of the art works. ConclusionsUnlike most of the other works in the recent literature, ANAlyte aims at the automatization of all the major steps of ANA image analysis. Results on public benchmarks demonstrate that the tool can characterize HEp-2 slides in terms of intensity and fluorescent pattern with accuracy better or comparable with the state of the art techniques, even when such techniques are run on manually segmented cells. Hence, ANAlyte can be proposed as a valid solution to the problem of ANA testing automatization.

Salient object detection using biogeography-based optimization to combine features

Salient object detection aims to automatically localize a foreground object with respect to its background in an image. It plays a crucial role in a wide range of computer vision and multimedia applications. In this work, we propose an improved salient object detection method based on biogeography-based optimization, a relatively new bio-inspired metaheuristic algorithm that searches for the global optimum using a migration model. Our approach consists of two steps. In the first step, a set of local (multi-scale contrast), regional (center-surround histogram), and global (color spatial distribution) salient feature maps are extracted and normalized. In the second step, an optimal weight vector for combining these feature maps into one saliency map is determined using biogeography-based optimization and improved variants of this algorithm. As a result, a salient objects were identified and labeled as distinct from the image background. We implemented our method using three biogeography-based optimization variants, and compared our results for three popular databases against two other state-of-the-art approaches. The experimental results demonstrate that our method exhibits refined and consistent detection of salient objects.

Robust visual saliency detection method for infrared small target

As a key technique in automatic target detection,robust detection of small infrared target at low signal-to-noise ratio has received a lot of attentions. In order to detect infrared( IR) small targets efficaciously,the apparent characteristics and visual saliency of infrared small target were both analyzed. Thereafter,a robust saliency detection algorithm for infrared small target based on multiscale ordered contrast of image patch( MOCIP) was proposed. The cascaded MOCIP was developed to detect the saliency of infrared small target by suppressing the background and noise and enhancing the infrared small target in two consecutive steps. Consequently,the salient target can be detected with an adaptive threshold in the saliency map obtained by cascaded MOCIP. The robust saliency detection algorithm was presented in details and the efficacy was analyzed. Verification and comparison experiments of detecting the saliency of infrared small target were both conducted. All experiments results show that the proposed MOCIP method is effective and robust in overcoming the impact of noise and complex background and in detecting the saliency of infrared small target at low signal-to-noise( SNR) ratio.

Hydrogen-assisted damage in austenite/martensite dual-phase steel

For understanding the underlying hydrogen embrittlement mechanism in transformation-induced plasticity steels, the process of damage evolution in a model austenite/martensite dual-phase microstructure following hydrogenation was investigated through multi-scale electron channelling contrast imaging and in situ optical microscopy. Localized diffusible hydrogen in martensite causes cracking through two mechanisms: (1) interaction between {1 1 0}M localized slip and {1 1 2}M twin and (2) cracking of martensite–martensite grain interfaces. The former resulted in nanovoids along the {1 1 2}M twin. The coalescence of the nanovoids generated plate-like microvoids. The latter caused shear localization on the specific plane where the crack along the martensite/martensite boundary exists, which led to additional martensite/martensite boundary cracking.

基于多尺度区域对比的显著目标识别

基于多尺度区域对比的显著目标识别

A flexible patch based approach for combined denoising and contrast enhancement of digital X-ray images.

Denoising and contrast enhancement play key roles in optimizing the trade-off between image quality and X-ray dose. However, these tasks present multiple challenges raised by noise level, low visibility of fine anatomical structures, heterogeneous conditions due to different exposure parameters, and patient characteristics. This work proposes a new method to address these challenges. We first introduce a patch-based filter adapted to the properties of the noise corrupting X-ray images. The filtered images are then used as oracles to define non parametric noise containment maps that, when applied in a multiscale contrast enhancement framework, allow optimizing the trade-off between improvement of the visibility of anatomical structures and noise reduction. A significant amount of tests on both phantoms and clinical images has shown that the proposed method is better suited than others for visual inspection for diagnosis, even when compared to an algorithm used to process low dose images in clinical routine.

Divide-and-conquer based summarization framework for extracting affective video content

Recent advances in multimedia technology have led to tremendous increases in the available volume of video data, thereby creating a major requirement for efficient systems to manage such huge data volumes. Video summarization is one of the key techniques for accessing and managing large video libraries. Video summarization can be used to extract the affective contents of a video sequence to generate a concise representation of its content. Human attention models are an efficient means of affective content extraction. Existing visual attention driven summarization frameworks have high computational cost and memory requirements, as well as a lack of efficiency in accurately perceiving human attention. To cope with these issues, we propose a divide-and-conquer based framework for an efficient summarization of big video data. We divide the original video data into shots, where an attention model is computed from each shot in parallel. Viewer's attention is based on multiple sensory perceptions, i.e., aural and visual, as well as the viewer's neuronal signals. The aural attention model is based on the Teager energy, instant amplitude, and instant frequency, whereas the visual attention model employs multi-scale contrast and motion intensity. Moreover, the neuronal attention is computed using the beta-band frequencies of neuronal signals. Next, an aggregated attention curve is generated using an intra- and inter-modality fusion mechanism. Finally, the affective content in each video shot is extracted. The fusion of multimedia and neuronal signals provides a bridge that links the digital representation of multimedia with the viewer’s perceptions. Our experimental results indicate that the proposed shot-detection based divide-and-conquer strategy mitigates the time and computational complexity. Moreover, the proposed attention model provides an accurate reflection of the user preferences and facilitates the extraction of highly affective and personalized summaries.

Perceived assessment metrics for visible and infrared color fused image quality without reference image

Designing objective quality assessment of color-fused image is a very demanding and challenging task. We propose four no-reference metrics based on human visual system characteristics for objectively evaluating the quality of false color fusion image. The perceived edge metric (PEM) is defined based on visual perception model and color image gradient similarity between the fused image and the source images. The perceptual contrast metric (PCM) is established associating multi-scale contrast and varying contrast sensitivity filter (CSF) with color components. The linear combination of the standard deviation and mean value over the fused image construct the image colorfulness metric (ICM). The color comfort metric (CCM) is designed by the average saturation and the ratio of pixels with high and low saturation. The qualitative and quantitative experimental results demonstrate that the proposed metrics have a good agreement with subjective perception.

Exploring Human Vision Driven Features for Pedestrian Detection

Motivated by the center-surround mechanism in the human visual attention system, we propose to use average contrast maps for the challenge of pedestrian detection in street scenes due to the observation that pedestrians indeed exhibit discriminative contrast texture. Our main contributions are first to design a local, statistical multi-channel descriptorin order to incorporate both color and gradient information. Second, we introduce a multi-direction and multi-scale contrast scheme based on grid-cells in order to integrate expressive local variations. Contributing to the issue of selecting most discriminative features for assessing and classification, we perform extensive comparisons w.r.t. statistical descriptors, contrast measurements, and scale structures. This way, we obtain reasonable results under various configurations. Empirical findings from applying our optimized detector on the INRIA and Caltech pedestrian datasets show that our features yield state-of-the-art performance in pedestrian detection.

Automated Aesthetic Analysis of Photographic Images.

We present a perceptually calibrated system for automatic aesthetic evaluation of photographic images. Our work builds upon the concepts of no-reference image quality assessment, with the main difference being our focus on rating image aesthetic attributes rather than detecting image distortions. In contrast to the recent attempts on the highly subjective aesthetic judgment problems such as binary aesthetic classification and the prediction of an image's overall aesthetics rating, our method aims on providing a reliable objective basis of comparison between aesthetic properties of different photographs. To that end our system computes perceptually calibrated ratings for a set of fundamental and meaningful aesthetic attributes, that together form an "aesthetic signature" of an image. We show that aesthetic signatures can still be used to improve upon the current state-of-the-art in automatic aesthetic judgment, but also enable interesting new photo editing applications such as automated aesthetic analysis, HDR tone mapping evaluation, and providing aesthetic feedback during multi-scale contrast manipulation.

CR(Computed Radiography)에서 초점 크기와 디지털영상후처리에 따른 공간분해능의 정량적 분석

Abstract The aim of the present study was to carry out quantitative analysis of spatial resolution for the influence of the focus size and digital image post-processing on the Computed Radiography (CR). The modulation transfer functions of an edge measuring method (MTF) was used for the evaluation of the spatial resolution. The focus size of X-ray tube was used the small focus (0.6 mm) and the large focus (1.2 mm). We evaluated the 50% and 10% of MTF for the enhancement of edge and contrast by using multi-scale image contrast amplification (MUSICA) in digital image post-processing. As a results, the edge enhancement than the contrast enhancement were significantly higher the spatial resolution of MTF 50% in all focus. Also the spatial resolution of the obtained images in a large focus were improved by digital image processing. In conclusion, the results of this study should serve as a basic data for obtain the high resolution clinical images, such as skeletal and chest images on the CR.

Video summarization based tele-endoscopy: a service to efficiently manage visual data generated during wireless capsule endoscopy procedure.

Wireless capsule endoscopy (WCE) has great advantages over traditional endoscopy because it is portable and easy to use. More importantly, WCE combined with mobile computing ensures rapid transmission of diagnostic data to hospitals and enables off-site senior gastroenterologists to offer timely decision making support. However, during this WCE process, video data are produced in huge amounts, but only a limited amount of data is actually useful for diagnosis. The sharing and analysis of this video data becomes a challenging task due the constraints such as limited memory, energy, and communication capability. In order to facilitate efficient WCE data collection and browsing tasks, we present a video summarization-based tele-endoscopy service that estimates the semantically relevant video frames from the perspective of gastroenterologists. For this purpose, image moments, curvature, and multi-scale contrast are computed and are fused to obtain the saliency map of each frame. This saliency map is used to select keyframes. The proposed tele-endoscopy service selects keyframes based on their relevance to the disease diagnosis. This ensures the sending of diagnostically relevant frames to the gastroenterologist instead of sending all the data, thus saving transmission costs and bandwidth. The proposed framework also saves storage costs as well as the precious time of doctors in browsing patient's information. The qualitative and quantitative results are encouraging and show that the proposed service provides video keyframes to the gastroenterologists without discarding important information.

Evaluation of relative speed of latent images in relation to changes in fading time and storage temperature of imaging plates in computed radiography systems

This study aimed to evaluate the relative speed (RS) of latent images in relation to changes in the fading time and storage temperature of imaging plates (IPs) in computed radiography systems. The storage temperatures adopted were 20, 30, and 40°C, while the fading times employed were 0, 4, 8, 12, and 24 hours. The X-ray exposure factors were 50 kVp, 10 mAs, and a 150 cm distance from an IP to an X-ray source. In the processing of each image, the parameters used for multi-scale image contrast amplification were multiscale image contrast, noise reduction, edge enhancement, and latitude reduction, all assigned a value of 0. Image sensitivity was used to convert linear properties. The RS used for the characteristic curve was evaluated using a uniform aluminum 11-step wedge. Results show that the RS values of IPs with changing fading time were 17.8 ± 0.9 at 20°C, 13.9 ± 1.1 at 30°C, and 13.4 ± 0.9 at 40°C. On the basis of these findings, we conclude that IPs should be stored in the long term at temperatures as low as 20°C.