Illumination Distortion Research Articles

Efficient Contrast Adjustment and Fusion Method for Underexposed Images in Industrial Cyber-Physical Systems

Owing to imaging equipment's environment and limitations, the images obtained in industrial cyber-physical systems (ICPSs) are degraded and available in various visual appearances. The process of highlighting the hidden contents in night-time contrast-distorted images is complex. Earlier approaches have solved this problem from a different perspective and achieved remarkable results that are generally unsatisfactory for images with diverse illumination distortions in ICPSs. Hence, an effective visibility enhancement model is proposed to eliminate inconsistent color casts while highlighting more hidden content for improved inspection, safety in large spaces, and monitoring of large systems. Our proposed model has four steps: 1) removal of the unnatural color cast via a white balance technique, 2) use of probability density and softplus functions to process the images with the actual color cast, 3) using an optimization algorithm to estimate the illumination and adjusting it using a nonlinear function, and 4) blending by multiscale fusion to obtain the most effective visual result. Evaluation of ten benchmark datasets using 14 quality metrics for 22 conventional and modern algorithms shows that our approach is robust, flexible, and applicable to numerous vision-based applications, such as ICPSs, autonomous vehicles, smart cameras, smart mobility, and transportation, especially in low-light environments.

Normalization of series of fundus images to monitor the geographic atrophy growth in dry age-related macular degeneration

Background and ObjectiveAge-related macular degeneration (ARMD) is a degenerative disease that affects the retina, and the leading cause of visual loss. In its dry form, the pathology is characterized by the progressive, centrifugal expansion of retinal lesions, called geographic atrophy (GA). In infrared eye fundus images, the GA appears as localized bright areas and its growth can be observed in series of images acquired at regular time intervals. However, illumination distortions between the images make impossible the direct comparison of intensities in order to study the GA progress. Here, we propose a new method to compensate for illumination distortion between images. MethodsWe process all images of the series so that any two images have comparable gray levels. Our approach relies on an illumination/reflectance model. We first estimate the pixel-wise illumination ratio between any two images of the series, in a recursive way; then we correct each image against all the others, based on those estimates. The algorithm is applied on a sliding temporal window to cope with large changes in reflectance. We also propose morphological processing to suppress illumination artefacts. ResultsThe corrected illumination function is homogeneous in the series, enabling the direct comparison of grey-levels intensities in each pixel, and so the detection of the GA growth between any two images. To demonstrate that, we present numerous experiments performed on a dataset of 18 series (328 images), manually segmented by an ophthalmologist. First, we show that the normalization preprocessing dramatically increases the contrast of the GA growth areas. Secondly, we apply segmentation algorithms derived from Otsu's thresholding to detect automatically the GA total growth and the GA progress between consecutive images. We demonstrate qualitatively and quantitatively that these algorithms, although fully automatic, unsupervised and basic, already lead to interesting segmentation results when applied to the normalized images. Colored maps representing the GA evolution can be derived from the segmentations. ConclusionTo our knowledge, the proposed method is the first one which corrects automatically and jointly the illumination inhomogeneity in a series of fundus images, regardless of the number of images, the size, shape and progression of lesion areas. This algorithm greatly facilitates the visual interpretation by the medical expert. It opens up the possibility of treating automatically each series as a whole (not just in pairs of images) to model the GA growth.

Local Water-Filling Algorithm for Shadow Detection and Removal of Document Images.

Shadow detection and removal is an important task for digitized document applications. It is hard for many methods to distinguish shadow from printed text due to the high darkness similarity. In this paper, we propose a local water-filling method to remove shadows by mapping a document image into a structure of topographic surface. Firstly, we design a local water-filling approach including a flooding and effusing process to estimate the shading map, which can be used to detect umbra and penumbra. Then, the umbra is enhanced using Retinex Theory. For penumbra, we propose a binarized water-filling strategy to correct illumination distortions. Moreover, we build up a dataset called optical shadow removal (OSR dataset), which includes hundreds of shadow images. Experiments performed on OSR dataset show that our method achieves an average of 0.685 with a computation time of 0.265 s to process an image size of pixels on a desktop. The proposed method can remove the shading artifacts and outperform some state-of-the-art methods, especially for the removal of shadow boundaries.

Square-Heating Thermography for Quantitative 3D Evaluation of Large Ancient Murals

This work presents recent results of nondestructive health evaluation of the large Buddhist mural “Qifo shuofa tu” (seven Buddha sermon illustration) in the Palace Museum in Beijing, China. In this work, a square-heating thermography system and a thermal tomography method were developed for quantitative 3D evaluation of murals. In particular an image correction method was developed for removing all geometric and illumination distortions. This significantly helped for the seamless combination of all individual images into a single complete image and facilitated quantitative identification and locations of subsurface defects and re-patch pieces from an entire painting image. The thermography results show that this new method has great potential and capability in nondestructive testing and evaluation of large ancient murals.

Video-Based Person Re-Identification Using Unsupervised Tracklet Matching

Despite the significant improvement in accuracy supervised learning has brought into person re-identification (re-id), the availability of sufficient fully annotated data from concerned camera-views poses a problem for real-life applications. To alleviate the burden of intensive data annotation, one way is to resort to unsupervised methods. This has motivated us to propose a novel algorithm for unsupervised video-based person re-id applications. To achieve this, the frames of a person video tracklet are divided into a set of clusters that are subsequently matched using a distance measure based on the Naive Bayes nearest neighbor algorithm and Spearman distance. Knowing that person's sequences may suffer from substantial changes in viewpoint, pose, and illumination distortions, our technique allows the rejection of poor and noisy clusters while retaining the most discriminative ones for matching. Experiments on three widely used datasets for video person re-id PRID2011, iLIDS-VID and MARS have been carried out, and the results demonstrate the superiority of the proposed approach.

Modifying Texture of a Photograph Object, with the Use of Neural Networks Ensemble

In this paper, we consider a problem-solving technique of the texture changing of an object in a photograph. The task in hand is relevant in the field of intelligent image processing and has a number of practical applications. The solutions to this problem have been proposed in a number of works devoted to the neural network style transfer approach, but they have a number of limitations. Examples of the limitations are as follows: the texture transfer selectivity absence (the image is changed entirely), the target texture distortion with the heterogeneity of the original one, the initial illumination distortion of the object, and the absence of the photographic realism of the resulting image. To solve the problems mentioned above, in this paper we propose a sequential image processing with the use of several neural networks types: segmental, stylizing and generative-adversarial (GAN) ones. The reliable transfer problem of an object illumination is proposed to be solved by the joint work of GAN and methods that do not use the neural network approach. In the context of this paper we developed an algorithm that allows solving the texture transferring task with completely or partially elimination of the listed problems of classical methods. Its high quality of work is shown with the maintaining productivity acceptable for common use. Demonstration of the algorithm is performed on the task of a virtual furniture dust covers fitting (sofas, armchairs). In addition to the algorithm itself, this work includes an enumeration of some heuristics and limitations stated during its implementation and application.

PLT‐based spectral features for texture image retrieval

Effective texture feature is an essential component in any content-based image retrieval system. In this study, new texture features based on image enhancement technique are presented. The authors have effectively exploited power-law transform (PLT) to extract new spectral texture features called PLT-based spectral features. Extensive experiments on the Brodatz texture database and Salzburg Textures image database prove the effectiveness of the proposed techniques and show that the proposed features significantly outperform the widely used Gabor and curvelet features. The proposed features are also compared with recently published Gaussian copula models of Gabor feature and local tetra patterns (LTrP). The experimental results confirm that the proposed features have more tolerance to scale, orientation and illumination distortion than the state-of-the-art Gabor, curvelet, Gaussian copula models of Gabor and LTrPs.

Step beyond Kohler illumination analysis for far-field quantitative imaging: angular illumination asymmetry (ANILAS) maps.

For far-field optical imaging of three-dimensional objects and such critical applications as quantitative optical imaging, optical metrology, and optical lithography, it is necessary not only to meet the Kohler illumination condition (i.e. uniform spatial intensity) but also to minimize angular illumination asymmetry (ANILAS) at the sample plane. The presence of ANILAS results in distorted optical images, and most likely in erroneous quantitative measurements. ANILAS results from optical and illumination aberrations, optical misalignment and other problems. We present a detailed procedure to measure and create maps of ANILAS across the field-of-view (FOV). ANILAS maps enable visualization of the state of illumination at the sample plane. Since the presence of ANILAS is detrimental to quantitative measurements, it is important to know the magnitude and type of ANILAS across the FOV before making any attempt to correct it. Here we intentionally create different types of illumination distortions and generate corresponding ANILAS maps, which help us evaluate the state of illumination beyond the Kohler illumination criterion. We expect that the ANILAS maps will be helpful for a wide range of far-field imaging applications.

Application-Driven No-Reference Quality Assessment for Dermoscopy Images With Multiple Distortions.

Dermoscopy images often suffer from blur and uneven illumination distortions that occur during acquisition, which can adversely influence consequent automatic image analysis results on potential lesion objects. The purpose of this paper is to deploy an algorithm that can automatically assess the quality of dermoscopy images. Such an algorithm could be used to direct image recapture or correction. We describe an application-driven no-reference image quality assessment (IQA) model for dermoscopy images affected by possibly multiple distortions. For this purpose, we created a multiple distortion dataset of dermoscopy images impaired by varying degrees of blur and uneven illumination. The basis of this model is two single distortion IQA metrics that are sensitive to blur and uneven illumination, respectively. The outputs of these two metrics are combined to predict the quality of multiply distorted dermoscopy images using a fuzzy neural network. Unlike traditional IQA algorithms, which use human subjective score as ground truth, here ground truth is driven by the application, and generated according to the degree of influence of the distortions on lesion analysis. The experimental results reveal that the proposed model delivers accurate and stable quality prediction results for dermoscopy images impaired by multiple distortions. The proposed model is effective for quality assessment of multiple distorted dermoscopy images. An application-driven concept for IQA is introduced, and at the same time, a solution framework for the IQA of multiple distortions is proposed.

Optical Sectioning and High Resolution in Single-Slice Structured Illumination Microscopy by Thick Slice Blind-SIM Reconstruction.

The microscope image of a thick fluorescent sample taken at a given focal plane is plagued by out-of-focus fluorescence and diffraction limited resolution. In this work, we show that a single slice of Structured Illumination Microscopy (two or three beam SIM) data can be processed to provide an image exhibiting tight sectioning and high transverse resolution. Our reconstruction algorithm is adapted from the blind-SIM technique which requires very little knowledge of the illumination patterns. It is thus able to deal with illumination distortions induced by the sample or illumination optics. We named this new algorithm thick slice blind-SIM because it models a three-dimensional sample even though only a single two-dimensional plane of focus was measured.

Automatic GCP Extraction in Mountainous Areas Using DEM and PolSAR Data

Mountainous areas in synthetic aperture radar (SAR) images suffer severe geometric distortions caused by different look directions. Consequently, ground control point (GCP) extraction hardly obtains accurate results for aircraft positioning. Based on the digital elevation model (DEM) and polarimetric SAR (PolSAR) data, we propose a method for extracting GCPs in mountainous areas by introducing the polarization orientation angle shift (POAS) to minimize geometric distortions. In this method, DEM data are used as the reference map by providing POASs at arbitrary look directions to make up for the look-direction sensitivity of POASs transformed from PolSAR data. The geometric distortions between POASs transformed from DEM and PolSAR data are effectively reduced by calculating the POASs from DEM data at the same look direction and look angles of the PolSAR data. In contrast to the SAR data, which have a large dynamic range, the values of POAS are limited to a small interval. Therefore, the illumination distortions induced by visualization can be reduced. Finally, the GCP extraction between the POAS images is conducted by bilateral filter scale-invariant feature transform. Experiments using various data at different look directions demonstrate that the proposed method obtains better-quality GCPs but less invalid keypoints than the method using only intensity images for mountainous areas.

A pipeline for digital restoration of deteriorating photographic negatives

Extending work presented at the second International Workshop on Historical Document Imaging and Processing, we demonstrate a digitization pipeline to capture and restore negatives in low-dynamic range file formats. The majority of early photographs were captured on acetate-based film. However, it has been determined that these negatives will deteriorate beyond repair even with proper conservation and no suitable restoration method is available without physically altering each negative. In this paper, we present an automatic method to remove various non-linear illumination distortions caused by deteriorating photographic support material. First, using a high-dynamic range structured-light scanning method, a 2D Gaussian model for light transmission is estimated for each pixel of the negative image. Estimated amplitude at each pixel provides an accurate model of light transmission, but also includes regions of lower transmission caused by damaged areas. Principal component analysis is then used to estimate the photometric error and effectively restore the original illumination information of the negative. A novel tone mapping approach is then used to produce the final restored image. Using both the shift in the Gaussian light stripes between pixels and their variations in standard deviation, a 3D surface estimate is calculated. Experiments of real historical negatives show promising results for widespread implementation in memory institutions.

Designed and Development of Embedded QR Code Bar Code Recognition System

Based on J2ME technology,develop a Embedded QR Code bar code recognition system.This system integrated image graying,image binarization, image rotation and other processing methods to realize bar code pre-process, anti-perspective transformation algorithm is adapted to correct distortion pictures,solved mobile taking picture on problems of image lean, distortion illumination on QR code effectively, have higher identification of image under different lighting conditions.

Region Duplication Detection Using Image Feature Matching

Region duplication is a simple and effective operation to create digital image forgeries, where a continuous portion of pixels in an image, after possible geometrical and illumination adjustments, are copied and pasted to a different location in the same image. Most existing region duplication detection methods are based on directly matching blocks of image pixels or transform coefficients, and are not effective when the duplicated regions have geometrical or illumination distortions. In this work, we describe a new region duplication detection method that is robust to distortions of the duplicated regions. Our method starts by estimating the transform between matched scale invariant feature transform (SIFT) keypoints, which are insensitive to geometrical and illumination distortions, and then finds all pixels within the duplicated regions after discounting the estimated transforms. The proposed method shows effective detection on an automatically synthesized forgery image database with duplicated and distorted regions. We further demonstrate its practical performance with several challenging forgery images created with state-of-the-art tools.

Progressive Coding and Illumination and View Dependent Transmission of 3-D Meshes Using R-D Optimization

For transmitting complex 3-D models over bandwidth-limited networks, efficient mesh coding and transmission are indispensable. The state-of-the-art 3-D mesh transmission system employs a wavelet-based progressive mesh coder, which converts an irregular mesh into a semi-regular mesh and directly applies the zerotree-like image coders to compress the wavelet vectors, and view-dependent transmission, which saves the transmission bandwidth through only delivering the visible portions of a mesh model. We propose methods to improve both progressive mesh coding and transmission based on thorough rate-distortion analysis. In particular, by noticing that the dependency among the wavelet coefficients generated in remeshing is not being considered in the existing approaches, we propose to introduce a preprocessing step to scale up the wavelets so that the inherent dependency of wavelets can be truly understood by the zerotree-like image compression algorithms. The weights used in the scaling process are carefully designed through thoroughly analyzing the distortions of wavelets at different refinement levels. For the transmission part, we propose to incorporate the illumination effects into the existing view-depend progressive mesh transmission system to further improve the performance. We develop a novel distortion model that considers both illumination distortion and geometry distortion. Based on our proposed distortion model, given the viewing and lighting parameters, we are able to optimally allocate bits among different segments in real time. Simulation results show significant improvements in both progressive compression and transmission.

Nonlinear composite filter performance

We use nonlinear composite filters in object recognition, even when they have rotation, scale, noise, and illumination distortions. We generated 936 images of the letters E, F, H, P, and B. The images consisted of these letters scaled from 70% to 130% and rotated 360 deg. The maximum number of images supported by these filters was determined by a numerical experiment. Considering a system confidence level of at least 80%, the maximum number of images is around 216. We found a "rotation problem" when the filter contained the letter rotated 360 deg, since circles were artificially introduced, and this creates complications when working with images that also have circles in their spectrum. Due to this, we propose a segmented filter that breaks the circular symmetry. Experiments where carried out in order to find the noise tolerance of each filter, and the use of Spearman's rank correlation (in conjunction with the nonlinear method, SNM) is proposed in order to increase that tolerance. We also made an assessment of the impact that illumination changes had in the correlation output, in the problem image, and we propose the use of SNM to obtain illumination invariance. We tested these filters with two real-life problems; nonlinear composite filters can recognize the target in the presence of distortions.

Robust Texture Feature Extraction Method for Geometrical and Illumination Distortions

In this paper, we propose a robust feature extraction method for texture image retrieval, and verify the effectiveness. In this method, the original image is transformed to log-polar autocorrelation image. The log-polar image is decomposed by discreet wavelet transform to obtain the approximation images. We extract the edge component from the approximation image by sobel filter processing, and we use higher order local autocorrelation as feature vector. Using this method to texture image, we obtain the robust feature for geometrical (shift, rotation, scale) and illumination distortions.In order to show the effectiveness of this method, we estimated the similarity between images by using the feature vector. According to the result of computer simulation, we verified the higher retrieval rate to geometrical and illumination distorted images than the conventional approaches.

Engineering design of an image acquisition and analysis system for dendrochronology

The design and implementation of a computer-vision-based analysis system for dendrochronology are described. The primary issues covered are automatic focus detection, illumination distortion, spatial and radiometric registration of a sequence of images into a single mosaic, and edge detection and linking. These issues are not unique to the ap- plication, but are likely of interest to anyone developing automated image analysis systems. A modification of the Canny edge detection algorithm that adapts to the variable characteristics of tree-ring images is also described. © 2000 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(00)01502-6)

Visualization and image processing of an acoustically excited jet flow

Recent work investigating excitation effects on an acoustically excited jet flow is reported. Emphasis is placed on integrated visualization and high-resolution and digital image processing, sequential planar gas concentrations and some characteristics of the large-scale vortical structures of acoustically excited jet flow, such as multiple-eddy merging, vortex-braids formation, eddy evolution and entrainment processes, jet-boundary expansion, etc. The digital image processing technique employed here extends our previous work (Chao et al. 1990) to optimal threshold filtering of the background noise and in situ calibration of camera and illumination distortions. A compact, low-cost, automatic frame acquisition and analysis system is developed for mean and r.m.s. planar gas concentrations and automatic jet-boundary identification. Also, stroboscopic images are created for detailed sequential study of a quick-changing process using a low framing-rate camera by suitably controlling the acoustic excitation frequency and the jet flow.