Enhancement Research Articles

Research on the Contrast Enhancement Algorithm for X-ray Images of BiFeO3 Material Experiment

High-Temperature Materials Science Experiment Cabinet on the Chinese Space Station is mainly used to carry out experimental research related to high-temperature materials science in microgravity. It is equipped with an X-ray transmission imaging module, which is applied to realize transmission imaging of material samples under microgravity. However, the X-ray light source is far away from the experimental samples, and the images obtained by the module are blurred, so it is impossible to accurately observe the morphological changes during the melting and solidification processes of high-temperature materials. To address this issue, this paper proposed a contrast enhancement algorithm specifically designed for X-ray images obtained during the experiments of high-temperature materials. The algorithm is based on gradient three-interval equalization, and it is combined with a Gaussian function to expand the gradient histogram. Meanwhile, the local gray level information within each gradient interval is corrected by designing an improved adaptive contrast enhancement algorithm. By comparing with Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithms, EnlightenGAN, and Wavelet algorithms, the Contrast Enhancement based contrast-changed Image Quality measure (CEIQ) and Measure of Enhancement (EME) are improved by an average of 56.97%, 10.58%, and Measure of Entropy (MOE) are improved by an average of 7.74 times. The experimental results show that the algorithm makes the image details clearer on the basis of image contrast enhancement. The solid-liquid interface in the image can be clearly observed after contrast enhancement. The algorithm provides strong support for the study of interface dynamics during the experiment process of high-temperature materials.

Fusion of multiscale gradient domain enhancement and gamma correction for underwater image/video enhancement and restoration

Underwater images and video often suffer from poor visibility and color cast because light gets scattered and absorbed in water. To solve this problem, a novel method based on the fusion of multiscale gradient-domain enhancement and gamma correction is proposed for underwater images and video enhancement. Firstly, a white balance is used for color correction to the input underwater image and video. secondly, the color corrected underwater RGB images are converted to YCbCr color space. The Y-component of the image is decomposed into the base layer and detail layers using a Weighted Least Squares (WLS) filter. The base layer is enhanced by using gamma correction and detail layers are enhanced using the S-shape function in the gradient domain. The enhanced base layer and detail layers are fused. Finally, the fused image combined with Cb and Cr-component of YCbCr color space to obtained enhanced image. The proposed method has been implemented on the Underwater Image Enhancement Benchmark (UIEB) dataset, Underwater-45 (U45) dataset, and Dataset Real-world Underwater Video of Artifacts (DRUVA) based on the Peak Signal-to-Noise Ratio (PSNR), Structure Similarity Index Measure (SSIM), Measure of Enhancement (EME), Discrete Entropy (DE), Underwater Image Quality Measure (UIQM), and Underwater Color Image Quality Evaluation (UCIQE). To verify the efficacy of the proposed method, a qualitative and quantitative comparison has been conducted on the UIEB, U45, and DRUVA datasets. The result demonstrates that the proposed method outperforms the state-of-the-art method, in terms of PSNR, SSIM, EME, UIQM, and UCIQE parameters. Furthermore, the efficiency of proposed method tested on fog image and low illumination images.

EACE: A document-level event argument extraction model with argument constraint enhancement

There are two key challenges remaining for the document-level event argument extraction tasks: long-range dependency and same-role argument assignment. The existing methods could not effectively handle the above two challenges at the same time, resulting in argument misidentification and over- or under-extraction, reducing the precision and recall of event argument extraction. In this paper, we propose a document-level event argument extraction model with argument constraint enhancement (EACE), which constructs the argument constraint tree using the hierarchical constraints between arguments to address the above two challenges simultaneously. Specifically, EACE first constructs an argument constraint decoder and uses abstractive summarization to establish the long-range hierarchical constraint relationships between arguments and to obtain the trunk structure of the argument constraint tree, which improves argument identification precision. Secondly, EACE calculates dynamic branch thresholds to expand the branch structure of the argument constraint tree and improve the recall of argument extraction. Extensive experiments on WIKIEVENTS and RAMS have shown that EACE outperforms the baseline models by 2.2% F1 and 0.2% F1, respectively. Moreover, it exceeds the baseline model (PAIE) by up to 17.1% F1 in the same-role argument assignment setting in WIKIEVENTS.

Single Point Integration a Monolithic Application for Versatile Multifunctionality

In today's digitally interconnected world, the management of multiple social media accounts has become increasingly complex. The need for a unified solution that simplifies access to diverse platforms and centralizes notifications has led to the development of a groundbreaking application. This application offers a seamless and user-friendly experience, enabling individuals and businesses to effortlessly consolidate their social media presence in one place. With the capability to access and switch between various social media accounts at the click of a button, users can streamline their online interactions, saving time and improving overall efficiency. This paper introduces the concept and features of this innovative application, highlighting its potential to revolutionize the way we engage with our digital networks while enhancing convenience and productivity. Keywords: Social Media Management, Unified Solution, Centralized Notifications, User-Friendly Interface, Consolidation of Accounts, Diverse Platforms, Efficiency Optimization, Digital Networks, Time-Saving, Online Interactions, Digital Presence, Seamless Access, Switching Between Accounts, Streamlining, Multifunctional Application, Interconnected World, Convenience Enhancem ent, Productivity Improvement, Ground breaking Technology, Social Media Engagement.

P‐17.4: Research On High‐performance Of Automotive BDCELL Module

The BOE BDCELL technology has been suc cessfully applied to automotive display. It is essentially a dual‐cell display technology: The color cell is for d isplay, the mono cell is for backlight, and the back lig ht is still common edge type. In this paper, the perfor mance of BDCELL products is further optimized based on the actual application scenarios of the vehicle: incl uding the pixel design of dual‐cell, contrast ratio enhan cement, halo optimization, ghost optimization, large vie w image quality optimization, and EMC performance o ptimization. It can be applied directly to vehicle displa y to provide users safer and better driving experiences.

OGIF: A novel Optimized Guided Image Filter for image enhancement

AbstractImage processing techniques are applied on various kinds of images such as medical images, microscopy images and remote sensing images for improving the visual qualities of these images as their credibility is questioned because of poor visibility, contrast, acquired noise etc. Image enhancement is necessary for removing the visual ailment of these images. Guided image filter (GIF) has been a suitable filter for image contrast enhancement, but the controlling parameters are taken as constant values in the conventional GIF. These control parameters vary for different kind of images; therefore, require manual tuning and adjustment which is often cumbersome, time‐consuming. The proposed work modifies the existing GIF by incorporating performance improvement in terms of optimal selection of control parameters. Thus, a novel optimized guided image filter (OGIF) is developed with the help of particle Swarm optimization (PSO) algorithm. The design methodology involves contrast and edge enhancement of the images which helps in accurate detection of region of interest (ROI) as well as noise removal. OGIF automatically adjusts the value of the controlling parameters in an optimal manner on which the detection of ROI is the most dependants. Image quality assessment (IQA) of enhanced images has been carried out using measurement of enhancement (EME), peak signal‐to‐noise ratio (PSNR in dB), measure of enhancement error using entropy (EMEE), standard deviation (SD) and entropy. The incremental change in the values of EME and EMEE advocates the suitability of OGIF for contrast enhancement.

Underwater Image Enhancement Using Customized CLAHE and Adaptive Color Correction

Underwater images degraded due to low contrast and visibility issues. Therefore, it is important to enhance the images and videos taken in the underwater environment before processing. Enhancement is a way to improve or increase image quality and to improve the contrast of degraded images. The original image or video which is captured through image processing devices needs to improve as there are various issues such as less light available, low resolution, and blurriness in underwater images caused by the normal camera. Various researchers have proposed different solutions to overcome these problems. Dark channel prior (DCP) is one of the most used techniques which produced a better Peak Signal to Noise Ratio (PSNR) value. However, DCP has some issues such as it tends to darken images, reduce contrast, and produce halo effects. The proposed method solves these issues with the help of contrast-limited adaptive histogram equalization (CLAHE) and the Adaptive Color Correction Method. The proposed method was assessed using Japan Agency for Marine-Earth Science and Technology (JAMSTEC), and some images were collected from the internet. The measure of entropy (MOE), Measure of Enhancement (EME), Mean Square Error (MSE), and PSNR opted as performance measures during experiments. The values of MSE and PSNR achieved by the proposed framework are 0.26 and 32 respectively which shows better results.

Spin-Coated Ag NPs SERS Substrate: Role of Electromagnetic and Chemical Enhancement in Trace Detection of Methylene Blue and Congo Red

This work demonstrates a simple low-cost and reproducible spin-coating method followed by thermal reduction for the uniform growth of silver nanoparticles (Ag NPs) as surface-enhanced Raman scattering (SERS) substrate. In this work, cationic dye MB and anionic dye CR are selected as two different kinds of SERS probe molecules to investigate the differences between electromagnetic field enhancement (EME) and chemical enhancement (CE) mechanisms. The results indicate that SERS spectra of MB molecule on Ag NPs SERS substrate exhibit the shift in the Raman peak positions and high sensitivity (limit of detection, LOD ~ 10−10 M) with large GSERS (~ 109) value, which can be attributed to the contribution from both EME and CE mechanisms. It is found that Cl− halide ions present in the MB molecule are forming surface complex (Ag NPs@Cl−) on the surface of Ag NPs SERS substrate which is confirmed by the XPS investigation, which might be responsible for the CE enhancement in MB molecule. Whereas Congo red being anionic dye showed no shift in Raman peak positions and less sensitivity (LOD ~ 10−8) with GSERS (~ 107) value on Ag NPs SERS substrate, which can be attributed to EME mechanism only. The obtained results suggest that Cl− halide ions present in the MB molecule play an important role by giving large SERS enhancement for MB molecule on Ag NPs SERS substrate. It is expected that this work will provide insight into role of EME and CE mechanisms for cationic dye MB and anionic dye CR.

Intelligent Image Enhancement System based on Similarity Pixels

The main goal of image enhancement is to enhance the fine details present in the images having low luminance for better image quality. In the digital image processing field, the enhancement and removing the noise from the image is a critical issue; image noise removal is the manipulation of the image data to produce a visually high-quality image. The important details and useful information on image decreasing by the noise where the noise treated as information. The filters are used to remove unwanted information. The filters’ objectives are to improve the image quality. This paper proposes an enhancement image system, which chooses the appropriate filter and value of center pixel depends on the number of similarities adjusted neighbors pixels to the center pixel. The performance of this system is evaluated by using different quality metrics, such as Mean square error (MSE), Peak Signal Noise to Ratio (PSNR), Absolute Mean Brightness Error (AMBE), Measure of Enhancement (EME), and Measure of Enhancement by Entropy (EMEE), Entropy, Second-Order Entropy (SOE), and Image Enhancement Metric (IEM). The proposed enhancement system is efficient in removing noises and enhancing the image quality. Experiments are applied to a set of images, such as Lena, butterfly, etc. with different image sizes. The results show that the enhancement quality was performed well in the proposed system with minimal unexpected artifacts as compared to the other techniques, where the results of the proposed system for MSE, PSNR, AMBE, Entropy, SOE, EME, EMEE, and IEM for baboon image with the size 255x 255 are 2.906, 8.875, 3.92, 5.154, 2.692, 3.915, 0.442 and 3.674 in sequence.

Nonlinear Exposure Intensity Based Modification Histogram Equalization for Non-Uniform Illumination Image Enhancement

Non-uniform illumination image is often generated owing to various factors, such as an improper setting in the image acquisition device and absorption or reflectance of the objects that results in the existence of different exposure regions in the image. Although Histogram Equalization (HE) is well known and widely used in image enhancement, existing HE-based methods often generate washed-out effects and show unnatural appearance due to the over-enhancement phenomenon, which limits the capabilities of achieving illumination uniformity of an image. Therefore, this study proposes a modified HE method for non-uniform illumination image, namely Nonlinear Exposure Intensity-Based Modification Histogram Equalization (NEIMHE). The proposed NEIMHE method divides the non-uniform illumination image into five sub-regions and modifies the histogram of each sub-region by setting a nonlinear weight into their cumulative density function (CDF) of histogram in each sub-region. Each modified histogram is then equalized using modified HE equations that provide the intensity expansion and different intensity mapping directions for under-exposed and over-exposed sub-regions. A total of 354 non-uniform illuminated sample images were used to evaluate the performance of the proposed NEIMHE method, qualitatively and quantitatively. The proposed NEIMHE method was compared qualitatively with five state-of-the-art methods: Backlit, Adaptive Fuzzy Exposure Local Contrast Enhancement (AFELCE), Visual Contrast Enhancement Algorithm Based on Histogram Equalization (VCEA), Exposure Region-based Multi Histogram Equalization (ERMHE); and Exposure based Sub-Image Histogram Equalization (ESIHE). The proposed NEIMHE method produced an enhanced image with more uniform illumination, better preservation of image details, and high capability of maintaining image naturalness. Quantitatively, the proposed NEIMHE method achieved the highest scores in Discrete Entropy (DE), Measure of Enhancement (EME), Measure of Enhancement by Entropy (EMEE), and Peak Signal to Noise Ratio (PSNR); it attained second-best in Absolute Mean Brightness Error (AMBE) and Lightness Order Error (LOE). From both analyses, the proposed NEIMHE method has shown its capability of enhancing different exposure regions that exist in non-uniform illumination images.

Fractional derivative based Unsharp masking approach for enhancement of digital images

Image visual quality is severely degraded due to various environmental conditions, thus, leading to the loss in image details. Therefore, an image enhancement approach is required to improve the visual quality of images. In this paper, Unsharp Masking (UM) approach based on Riemann-Liouville (RL), Grunwald-Letnikov (GL), and Riesz fractional derivatives is proposed for the image enhancement. The fractional derivatives based UM approach sharpened the edges of an image while preserving its low and medium frequency details. Furthermore, the extra parameter of fractional derivative provides an additional degree of freedom, thus, increasing the effectiveness of the proposed approach. Extensive simulations carried out on several standard images of different sizes validated the performance of proposed approach in comparison to the existing techniques. The capability of the proposed approach is further confirmed by considering the test images with varying illumination conditions. Moreover, the comparative analysis performed in terms of quantitative measures such as Information Entropy (IE), Average Gradient (AG), Measure of Enhancement (EME), etc. confirmed that the proposed UM approach based on Riesz fractional derivative outperforms the existing state-of-the-art image enhancement techniques. Furthermore, the potential of the proposed approach is validated by considering its application in the medical images.

The dynamic enhanced characterization with low mechanical index gray-scale harmonic imaging inflammatory pseudotumor of liver compared with hepatic VX2 tumor and normal liver.

Inflammatory pseudotumor of the liver (IPTL) is misdiagnosed usually as a malignant tumor based on the imaging findings. Differential diagnosis should be established to avoid hepatic resection. At imaging, IPTL has been misdiagnosed usually as hepatocellular carcinoma (HCC). It is usually found firstly using conventional ultrasonic examination, which cannot give a definitive diagnosis. Because of its atypical clinical presentation and radiological appearance, a presumptive diagnosis of malignancy is frequently made. With the development of ultrasound systems and ultrasound contrast agents (UCA), contrast-enhanced ultrasound is widely used in diagnosing focal lesions of the liver. To delineate the hemodynamic features of IPTL compared with hepatic VX2 tumor and normal liver using contrast-enhanced ultrasound. Freund's complete adjuvant (FCA) was injected using a modified method into the desirable portion of the liver in rabbits. Two weeks after the injection, solitary IPTLs were formed (which was proved with pathological examination). Ten rabbits with IPTL, 10 rabbits with VX2 carcinoma and 10 healthy rabbits were studied using contrast-enhanced ultrasound with bolus injection of SonoVueTM through the peripheral vein. Corresponding parameters such as time to enhancement (ET), time to peak intensity (PIT), time to ascent (AT), and time to lighten (LT) were measured with wash-in/wash-out curve. Contrast-enhanced imaging clearly delineated the dynamic enhancement of the lesions and liver parenchyma during the whole phase. Inflammatory pseudotumor of the liver showed the same enhanced features as the liver parenchyma. In VX2 tumors, hyperechoic enhancement in arterial phase and hypoechoic enhancement was observed in the portal and delayed phase compared with the surrounding hepatic parenchyma. The normal liver showed whole of liver parenchyma enhanced in portal phase. The study showed that contrast-enhanced ultrasound provided useful information about perfusion in IPTL and VX2 carcinoma. Contrast-enhanced ultrasound is a useful technique in the differential diagnosis of focal liver lesions if combined with time-intensity curve.

Statistical study of geomagnetic storm effects on the occurrence of ionospheric irregularities over equatorial/low-latitude region of Africa from 2001 to 2017

The effect of Coronal Mass Ejection (CME) and Corotating Interaction Region (CIR)-driven storms on the occurrence of ionospheric irregularities (OIIs) over the African equatorial and low-latitude region are studied statistically for the first time. In addition to the CME and CIRs’ catalogs, we have used the disturbance storm time (Dst) ≤ -30 nT and Kp ≥ 3 to identify the storm periods. The study was based on Global Navigation Satellite System (GNSS) total electron content (TEC) observation from three stations (nklg: 8.05°S, 81.05°E; mbar: 10.22°S, 102.36°E; and nazr: 0.25°S, 111.01°E, Geomagnetic) during 2001–2017. Based on the GNSS observations, the rate of change of total electron indices (ROTIROTI and ROTIave) have been used to observe the presence/absence of ionospheric irregularities. To examine the effect of the storms on the OIIs, ratio of ROTIave of the selected storm period to the quiet monthly mean of ROTIave, ROTIratio=ROTIobs/ROTI‾quiet, was applied. Based on our analysis, ROTIratio≥3.2, ROTIratio≤0.16 and 0.16<ROTIratio<3.2 were identified as threshold values indicating the enhancement (EN), suppression (SP), and no significant (NE) effect of the storms on the OIIs, respectively. Our results revealed that the SP in the OII during CME-and CIR-driven storms are more prevalent than the EN. During both CIR-and CME-driven storms, the percentage occurrence rate in EN observed over nklg was greater than mbar and nazr. Most of the SP effect of the storms, on the other hand, was predominantly observed over nazr and mbar stations. The occurrence rate of EN, SP and NE effect of both CME-and CIR-driven storms show dependence on the local time at which large decrease in Dst occurs. We also found that SP effect of both CIR-and CME-driven storm show a positive and linear correlation with sunspot number (SSN). While the EN effect of CIR-driven storm show a negative and linear relation with SSN, CME-driven storm effects show weak relation. The polarity and amplitude of different sources of disturbance electric field observed in the evening hours could play a dominant role in affecting the OIIs. The difference in the seasonal variation in the occurrence rate of EN, SP and NE effect of the storms observed over different stations were also discussed.

Unsupervised Deep Contrast Enhancement with Power Constraint for OLED Displays.

Various power-constrained contrast enhance-ment (PCCE) techniques have been applied to an organic light emitting diode (OLED) display for reducing the pow-er demands of the display while preserving the image qual-ity. In this paper, we propose a new deep learning-based PCCE scheme that constrains the power consumption of the OLED displays while enhancing the contrast of the displayed image. In the proposed method, the power con-sumption is constrained by simply reducing the brightness a certain ratio, whereas the perceived visual quality is pre-served as much as possible by enhancing the contrast of the image using a convolutional neural network (CNN). Furthermore, our CNN can learn the PCCE technique without a reference image by unsupervised learning. Ex-perimental results show that the proposed method is supe-rior to conventional ones in terms of image quality assess-ment metrics such as a visual saliency-induced index (VSI) and a measure of enhancement (EME).1.

Segmentation of Low Contrast Satellite and Medical Image s Based on Level Set Function with Harmony Search Optimization Algorithm

The main aim of digital image segmentation for portioned the image in to its constituents parts for getting information regarding features of image also used to get pathological details from medical images. The literature available from last two decades the important scheme for image segmentation is with Level Set technique, multilevel thresholding of gray scale on histogram of image is also a traditional method of image segmentation. In this paper low contrast images from medical and satellite images considered for image segmentation to extract features. This paper puts forward a novel image segmentation method via Level Set Function along with Bi-Histogram Equalization based on Harmony Search Algorithm(LSFBHEHS). The Selective Binary and Gaussian Filtering Regularised Level Set (SBGFRLS) is efficient novel region based Active Contour Model, it uses a novel region-based signed pressure force (SPF) function, it can adeptly halt the contours at blurred edges and weak edges. Other important advantage is internal and external boundaries can be distinguished by fixing the initial contour may be anyplace in the considered image. This method is resourceful but requires more time and inefficient for segmentation of low contrast images. This problem is rectified by applying bi-histogram equalization(BHE) image enhancement method prior to Level Set, it can be treated as pre-processing. In BHE technique of image enhancement, the image histogram is partitioned into two divisions based optimized gray level threshold , and equalize each part of histogram separately and combined later. To find the optimized threshold level to slice the histogram into two parts, Otsu’s multilevel thresholding method used to find threshold level, to find optimized thresholding level Harmony Search Algorithm(HSA) is implemented to maximize inert class variance as objective function. For evaluating the proposed method and SBGFRLS, the qualitative measured used like Dice similarity index, Measure of Enhancement(EME) and time required, for experimentation numerous low contrast satellite and medical images are considered, results clarified that the proposed method is more efficient for low contrast and inhomogeneous images.

Adaptive Geometric Filtering Based on Average Brightness of the Image and Discrete Cosine Transform Coefficient Adjustment for Gray and Color Image Enhancement

An adaptive geometric filter approach based on average brightness of the image and discrete cosine transform (DCT) coefficient adjustment is proposed in this paper for gray and color image enhancement. Adaptive geometric filter is employed for smoothing the histogram peaks before histogram equalization and DCT coefficient adjustment is applied for enhancing the fine details of the image. The proposed method is compared with the state-of-the-art other contrast enhancement techniques. Experimental results show that proposed technique exceeds the other compared methods both visually and quantitatively. Three metrics are evaluated for numerical assessment that are entropy, quality index and measure of enhancement (EME). Also color quality enhancement metric is tested for color images. After thorough study, it is concluded that our method intensifies the image contrast very well and also preserves the original characteristics of the input images.

Rotational stability of a new multicomponent intraocular lens.

PurposeTo evaluate the rotational stability of the Precisight multicomponent intraocular lens (MCIOL) following primary implantation and after enhancement procedures.Patients and methodsProspective, single-center study of eyes that underwent routine cataract surgery with implantation of a non-toric MCIOL, (Precisight, InfiniteVision, Optics, Strasbourg, France). The axis of the MCIOL was measured with a line bisecting the two dialing holes in the front lens. Intraoperative orientation was determined using a digital surgical guidance system while the postoperative orientation was determined using slit-lamp imaging. Two populations were analyzed: eyes that only underwent cataract surgery (PRIM) and eyes that also underwent enhancement (ENH), consisting of surgical front optic exchange. Both populations had 3 observation visits: first implantation (P-Op); 3 months (3mo) and 6 months (6mo) after primary surgery. The ENH group had an additional fourth visit that corresponded to the enhancement surgery (E-Op). The main outcome measure was mean absolute change in MCIOL orientation (degrees). The effects of axial length (AL) and anterior chamber depth (ACD) on IOL rotational stability were examined.ResultsThirty-three eyes received MCIOL of which 29 had usable orientation images. Of these, 12 were in the PRIM group and 17 underwent ENH. Regarding the mean absolute rotation, among PRIM eyes, P-Op to 3mo was 3.03±2.45 degrees; P-Op to 6mo, 2.28±1.54 degrees; and 3–6mo, 2.37±1.56 degrees. Among the ENH eyes, P-Op to 3mo was 3.09±1.68; E-Op to 6mo, 2.71±3.30 and P-Op to 6mo, 3.62±3.42. There were no significant differences in the IOL rotation. There were no statistical differences in rotational stability between the ENH and PRIM groups. There was no correlation between IOL rotation and AL or ACD.ConclusionPrecisight appears to be rotationally stable. The enhancement procedure does not affect rotational stability.

Contrast enhancement of medical images using a new version of the World Cup Optimization algorithm.

In this paper, a new method for optimal enhancement of the contrast of a medical image is proposed. The main idea is to improve the Gamma correction method to enhance and highlight the image information and the details based on a new design of the World Cup Optimization (WCO) algorithm. Gamma correction is a suitable method for contrast enhancement with an efficiency that directly depends on the correct selection of the Gamma coefficient. In this study, a newly presented algorithm was employed for optimal selection of the Gamma value by considering the entropy, edge content, and multi-objective optimization. The simulation results were compared with 5 state of the art methods for presenting method efficiency. To do this, contrast, homogeneity, weighted average peak signal-to-noise ratio (WPSNR), measure of enhancement (EME), and contrast-to-noise ratio (CNR) were employed. Final results denote that the presented multi-objective optimization algorithm improves the quality of the image contrast and can provide more details and information than the other comparable methods.

English

English

An objective function based technique for devignetting fundus imagery using MST

Abstract Fundus photography is a powerful imaging modality that is utilized for detecting macular degeneration, retinal neoplasms, choroid disturbances, glaucoma and diabetic retinopathy. As the illumination source in fundus imaging is situated at the center of the fundus camera, the illumination at the peripheral regions of the images would be relatively less than the center, which is termed vignetting. Vignetting adversely affects the performance of computerized methods for analyzing fundus imagery. A devignetting method for fundus imagery based on the Modified Sigmoid Transform (MST) is proposed in this paper. Gain (A) and centering parameter (α) of MST have a crucial influence on its performance. For low values of the gain, local contrast is penalized, and the overall dynamic range is compressed. When the value of gain is very high, the images after the illumination correction will have a washed out appearance. The optimum value of gain is determined in this paper from an objective method based on two statistical indices, Average Gradient of Illumination Component (AGIC) and Error of Enhancement (EME). MST with gain value defined via objective methods is able to correct the uneven illumination in fundus images without penalizing the local contrast. The proposed method is compared with illumination equalization model, homomorphic filtering and Adaptive Gamma Correction (AGC) and was found to be superior in terms of ‘naturality’, uniformity of background illumination, and computational speed.