scholarly journals Performance Analysis of Otsu-Based Thresholding Algorithms: A Comparative Study

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Qinglin Cao ◽  
Letu Qingge ◽  
Pei Yang

Image thresholding is a widely used technology for a lot of computer vision applications, and among various global thresholding algorithms, Otsu-based approaches are very popular due to their simplicity and effectiveness. While the usage of Otsu-based thresholding methods is well discussed, the performance analyses of these methods are rather limited. In this paper, we first review nine Otsu-based approaches and categorize them based on their objective functions, preprocessing, and postprocessing strategies. Second, we conduct several experiments to analyze the model characteristics using different scene parameters both on synthetic images and real-world cell images. We put more attention to examine the variance of foreground object and the effect of the distance between mean values of foreground and background. Third, we explore the robustness of algorithms by introducing two typical kinds of noises under different intensities and compare the running time of each method. Experimental results show that NVE, WOV, and Xing’s methods are more robust to the distance of mean values of foreground and background. The large foreground variance will cause a larger threshold value. Experiments on cell images show that foreground miss detection becomes serious when the intensities of foreground pixels change drastically. We conclude that almost all algorithms are significantly affected by Salt&Pepper and Gaussian noises. Interestingly, we find that ME increases almost linearly with the intensity of Salt&Pepper noise. In terms of algorithms’ time cost, methods with no preprocessing and postprocessing steps have more advantages. All these findings can serve as a guideline for image thresholding when using Otsu-based thresholding approaches.

2020 ◽  
Vol 11 (4) ◽  
pp. 64-90
Author(s):  
Falguni Chakraborty ◽  
Provas Kumar Roy ◽  
Debashis Nandi

Multilevel thresholding plays a significant role in the arena of image segmentation. The main issue of multilevel image thresholding is to select the optimal combination of threshold value at different level. However, this problem has become challenging with the higher number of levels, because computational complexity is increased exponentially as the increase of number of threshold. To address this problem, this paper has proposed elephant herding optimization (EHO) based multilevel image thresholding technique for image segmentation. The EHO method has been inspired by the herding behaviour of elephant group in nature. Two well-known objective functions such as ‘Kapur's entropy' and ‘between-class variance method' have been used to determine the optimized threshold values for segmentation of different objects from an image. The performance of the proposed algorithm has been verified using a set of different test images taken from a well-known benchmark dataset named Berkeley Segmentation Dataset (BSDS). For comparative analysis, the results have been compared with three popular algorithms, e.g. cuckoo search (CS), artificial bee colony (ABC) and particle swarm optimization (PSO). It has been observed that the performance of the proposed EHO based image segmentation technique is efficient and promising with respect to the others in terms of the values of optimized thresholds, objective functions, peak signal-to-noise ratio (PSNR), structure similarity index (SSIM) and feature similarity index (FSIM). The algorithm also shows better convergence profile than the other methods discussed.


Molecules ◽  
2021 ◽  
Vol 26 (9) ◽  
pp. 2574
Author(s):  
Lahcen Hssaini ◽  
Francisca Hernandez ◽  
Manuel Viuda-Martos ◽  
Jamal Charafi ◽  
Rachid Razouk ◽  
...  

In the present study, chromatic coordinates, phenolic acids, flavonoids and antioxidant capacity assessed by 1,1-diphenyl-2-picrylhydrazyl (DPPH), 2,2′-azino-bis (3-ethylbenzothiazoline-6-sulfonate (ABTS) and lipid peroxidation inhibition capacity (LPIC) essays and their relative IC50 were investigated in 25 fig cultivars growing in Morocco. The aims of this study were to determine (i) the variation in these compounds among light and dark-colored cultivars, (ii) their partitioning between fruit peel and pulp and (iii) to display network connections among these variables. Twelve phenolic compounds (PCs) were isolated in peel extract versus eight in pulp samples. Anthocyanins, mainly cyanidin-3,5-diglucoside and cyanidin-3-O-rutinoside, were the predominant compounds in peels, where the mean concentrations were 75.90 ± 18.76 and 77.97 ± 18.95 µg/g dw, respectively. On the other hand, (−)-epicatechin and cyanidin-3-O-rutinoside were the major compounds in the pulp extracts, where the mean values were 5.23 ± 4.03 and 9.01 ± 5.67 µg/g dw, respectively. A two-dimensional hierarchically clustered heatmap was applied to the dataset to explore correlations in the dataset and similarities between cultivars, without dimensionality reduction. Results showed that anthocyanins, particularly pelargonidin-3-O-rutinoside, cyanidin-3,5-diglucoside and cyanidin-3-O-rutinoside, were the main contributors to the peels’ free radical scavenging capacity. This capacity was particularly higher in the peel of dark-colored figs compared to the fruit pulp. The local cultivar “INRA 1301” showed the most promising phenolic profile due to its very high levels of almost all detected PCs, especially (−)-epicatechin, quercetin-3-O-rutinoside, quercetin-3-O-glucoside, cyanidine-3,5-diglucoside, cyanidine-3-O-rutinoside and pelargonidin-3-O-rutinoside (54.66, 141.08, 35.48, 494.08, 478.66, 12.56 µg/g dw, respectively). Having the darkest figs in the collection (L* = 25.72, c* = 22.09 and h° = 20.99), this cultivar has also combined promising IC50 values, which were of 19.85, 40.58 and 124.78 µg/mL for DPPH, ABTS and LPIC essays, respectively.


2021 ◽  
Vol 2021 ◽  
pp. 1-22
Author(s):  
Senhong Wang ◽  
Jiangzhong Cao ◽  
Fangyuan Lei ◽  
Qingyun Dai ◽  
Shangsong Liang ◽  
...  

A number of literature reports have shown that multi-view clustering can acquire a better performance on complete multi-view data. However, real-world data usually suffers from missing some samples in each view and has a small number of labeled samples. Additionally, almost all existing multi-view clustering models do not execute incomplete multi-view data well and fail to fully utilize the labeled samples to reduce computational complexity, which precludes them from practical application. In view of these problems, this paper proposes a novel framework called Semi-supervised Multi-View Clustering with Weighted Anchor Graph Embedding (SMVC_WAGE), which is conceptually simple and efficiently generates high-quality clustering results in practice. Specifically, we introduce a simple and effective anchor strategy. Based on selected anchor points, we can exploit the intrinsic and extrinsic view information to bridge all samples and capture more reliable nonlinear relations, which greatly enhances efficiency and improves stableness. Meanwhile, we construct the global fused graph compatibly across multiple views via a parameter-free graph fusion mechanism which directly coalesces the view-wise graphs. To this end, the proposed method can not only deal with complete multi-view clustering well but also be easily extended to incomplete multi-view cases. Experimental results clearly show that our algorithm surpasses some state-of-the-art competitors in clustering ability and time cost.


2021 ◽  
Vol 9 ◽  
Author(s):  
Martha Habibi ◽  
Panagiotis K. Karyofyllis ◽  
Aggeliki Nikolakopoulou ◽  
Panagiotis Papagiannis ◽  
Pantelis Karaiskos ◽  
...  

The effect of the reportedly low ionizing radiation doses, such as those very often delivered to patients in interventional cardiology, remains ambiguous. As interventional cardiac procedures may have a significant impact on total collective effective dose, there are radiation protection concerns for patients and physicians regarding potential late health effects. Given that very low doses (<100 mSv) are expected to be delivered during these procedures, the purpose of this study was to assess the potency and suitability of current genotoxicity biomarkers to detect and quantitate biological effects essential for risk estimation in interventional cardiology. Specifically, the biomarkers γ-H2AX foci, dicentric chromosomes, and micronuclei, which underpin radiation-induced DNA damage, were studied in blood lymphocytes of 25 adult patients before and after interventional cardiac procedures. Even though the mean values of all patients as a group for all three endpoints tested show increased yields relative to baseline following medical exposure, our results demonstrate that only the γ-H2AX biomarker enables detection of statistically significant differences at the individual level (p < 0.001) for almost all patients (91%). Furthermore, 24 h after exposure, residual γ-H2AX foci were still detectable in irradiated lymphocytes. Their decline was found to vary significantly among the individuals and the repair kinetics of γ-H2AX foci was found to range from 25 to 95.6% of their maximum values obtained.


2018 ◽  
pp. 41-57 ◽  
Author(s):  
M. V. Konyushkova ◽  
S. Alavipanah ◽  
A. Abdollahi ◽  
S. Hamzeh ◽  
A. Heidari ◽  
...  

The study is focused on the pattern of soil salinity at the young loamy coastal plains of the Caspian Sea in Russia and Iran which were released from water less than 300 years ago. At two key sites of 45×30 m (Russia) and 25×20 m (Iran), the soil sampling with 1 to 5 m grid was performed to the depth of 1 m. The electrical conductivity (1 : 2.5) was measured in soil samples and soil sa-linity maps were compiled. Soils are represented by solonchaks with 2–3% of salts in the top layer or highly saline soils partly leached in the upper 5–10 cm. The ground water table is shallow (2–2.5 m). The studied sites are different in terms of climate, microtopography, and vegetation cover but spatial differentiation of soil salinity is quite similar what is evidenced from the similar distributions (mean values and variance) of electrical conductivity in almost all studied depths. The redistribution of salts is mainly observed in the upper 50 cm with the maximal manifestation in the upper 5 cm.


2018 ◽  
Vol 13 (3) ◽  
pp. 323-336 ◽  
Author(s):  
Naeimeh Elkhani ◽  
Ravie Chandren Muniyandi ◽  
Gexiang Zhang

Computational cost is a big challenge for almost all intelligent algorithms which are run on CPU. In this regard, our proposed kernel P system multi-objective binary particle swarm optimization feature selection and classification method should perform with an efficient time that we aimed to settle via using potentials of membrane computing in parallel processing and nondeterminism. Moreover, GPUs perform better with latency-tolerant, highly parallel and independent tasks. In this study, to meet all the potentials of a membrane-inspired model particularly parallelism and to improve the time cost, feature selection method implemented on GPU. The time cost of the proposed method on CPU, GPU and Multicore indicates a significant improvement via implementing method on GPU.


2020 ◽  
Vol 70 (3) ◽  
pp. 191-199
Author(s):  
A Senthilselvan ◽  
W V L Coonghe ◽  
J Beach

Abstract Background Workers are exposed to physical, chemical and other hazards in the workplace, which may impact their respiratory health. Aims To examine the healthy worker effect in the Canadian working population and to identify the association between occupation and respiratory health. Methods Data from four cycles of the Canadian Health Measures Survey were utilized. The current occupation of employed participants was classified into 10 broad categories based on National Occupation Category 2011 codes. Data relating to 15 400 subjects were analysed. Results A significantly lower proportion of those in current employment than those not in current employment reported respiratory symptoms or diseases or had airway obstruction. Similarly, those currently employed reported better general health and had greater mean values for percent-predicted forced vital capacity (FVC), forced expiratory volume in one second (FEV1), forced expiratory flow between 25% and 75% of FVC (FEF25–75%) and FEV1/FVC ratio. Among males, females and older age groups, significant differences were observed for almost all the respiratory outcomes for those in current employment. Those in ‘Occupations unique to primary industry’ had a significantly greater likelihood of regular cough with sputum and ever asthma and had lower mean values of percent-predicted FEV1/FVC and FEF25–75% than those in ‘Management occupations’. Those in ‘Health occupations’ had the highest proportion of current asthma. Conclusions Participants in current employment were healthier than those not in current employment providing further support for the healthy worker effect. Those in ‘Occupations unique to primary industry’ had an increased risk of adverse respiratory outcomes and reducing workplace exposures in these occupations has the potential to improve their respiratory health.


2005 ◽  
Vol 143 (2-3) ◽  
pp. 199-207 ◽  
Author(s):  
C. FAVERIN ◽  
C. A. MEZZADRA ◽  
H. M. FERNÁNDEZ ◽  
L. M. MELUCCI

Brody, Gompertz, Logistic, Richards and von Bertalanffy functions were compared as descriptors of growth in 319 coypus (Myocastor coypus) of Greenland and Silver varieties, from birth to 10–19 months of age. Several criteria were considered for the selection of the model: (a) bias in the asymptotic weight; (b) bias in birth weight; (c) error sum of squares; (d) error mean squares weighted by the number of animals converging in all functions; (e) determination coefficient. To adjust the curves NLIN procedure from SAS and iterative method of Marquardt were applied. A mixed model was used to analyse the parameters of the selected growth curve (asymptotic weight, A; constant of integration, B; and maturation rate, k) which included effects of farm, variety, sex, sire within farm and variety, reproductive status within sex, birth season and first order interactions. The effect of sire was considered as random. The von Bertalanffy function was selected and mean values for the parameters of this function were 8016 g and 0·008 g/g per day, for A and k respectively. There were differences in the estimated parameters between sexes; males had larger values of A and k than females.Weights at fixed ages (birth, weaning, 6–7 months) were analysed, as well as the final recorded weight and average postweaning gain. The model of analysis was similar to the previous one. There were no differences between varieties. Significant differences between sexes for almost all studied traits were detected. With age, weight difference between males and females increased. At 6 months of age, males were 37% heavier than females. Male average daily gain was higher than that of females, sexual dimorphism being evident in all analysed traits.


2008 ◽  
Vol 18 (05) ◽  
pp. 405-418 ◽  
Author(s):  
ADNAN KHASHMAN ◽  
BORAN SEKEROGLU

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.


2010 ◽  
Vol 3 (6) ◽  
pp. 1629-1646 ◽  
Author(s):  
H. K. Roscoe ◽  
M. Van Roozendael ◽  
C. Fayt ◽  
A. du Piesanie ◽  
N. Abuhassan ◽  
...  

Abstract. In June 2009, 22 spectrometers from 14 institutes measured tropospheric and stratospheric NO2 from the ground for more than 11 days during the Cabauw Intercomparison Campaign of Nitrogen Dioxide measuring Instruments (CINDI), at Cabauw, NL (51.97° N, 4.93° E). All visible instruments used a common wavelength range and set of cross sections for the spectral analysis. Most of the instruments were of the multi-axis design with analysis by differential spectroscopy software (MAX-DOAS), whose non-zenith slant columns were compared by examining slopes of their least-squares straight line fits to mean values of a selection of instruments, after taking 30-min averages. Zenith slant columns near twilight were compared by fits to interpolated values of a reference instrument, then normalised by the mean of the slopes of the best instruments. For visible MAX-DOAS instruments, the means of the fitted slopes for NO2 and O4 of all except one instrument were within 10% of unity at almost all non-zenith elevations, and most were within 5%. Values for UV MAX-DOAS instruments were almost as good, being 12% and 7%, respectively. For visible instruments at zenith near twilight, the means of the fitted slopes of all instruments were within 5% of unity. This level of agreement is as good as that of previous intercomparisons, despite the site not being ideal for zenith twilight measurements. It bodes well for the future of measurements of tropospheric NO2, as previous intercomparisons were only for zenith instruments focussing on stratospheric NO2, with their longer heritage.


Sign in / Sign up

Export Citation Format

Share Document