Performance Evaluation of DBLA Technique Based on Image Enhancement by using Fuzzy Logic

Performance Evaluation of DBLA Technique Based on Image Enhancement by using Fuzzy Logic

Sandeep Kaur

B.C.E.T College, Gurdaspur, Punjab 143521

Abstract- Image enhancement is the utmost standard process for visualization uses. In recent times ample effort is done to enhance the brightness for improving the accuracy of remote sensing images. This research work proposed the DWT, Guided filter as well as Fuzzy logic technique as the post processing function to enhance the accuracy of image by reducing the problem of noise which has been present in the images.

Keywords: Adaptive histogram transfer function, DWT, dominant brightness level analysis, fuzzy based enhancement.

I INTRODUCTION

Remote sensing images have an essential function in several areas for example for instance metrology, agriculture geology etc[1]. Dominant brightness level analysis(DBLA)[1] indicates that it is an efficient method for the image enhancement. Contrast improvement images could have power distortion and eliminate image data in number of sections. To irresistible the glitches of images ,decompose the original image into numerous levels. The projected algorithm conduct discrete wavelet transform (DWT)[2] on the original images that decompose the original image into different sub- bands LL, HL, HH and HL[2]. From then decompose the LL sub-band into low, middle, and high intensity layers. Intensity transfer functions are adaptively estimated by applying the knee transfer function and the gamma adjustment function. The resultant improved image is obtained by applying the inverse DWT(IDWT).

Proposed image

Dominent brightness levels

fig(a)dominant result fig(b)Proposed dominant result

1. DWT

   HH

   HH

   H

   H

   H(x,y)

   H(x,y)

   HL

   HL

   Image enhancement is the process of enhancing the feature of the digital images. The cause may be a low resolution camera or poor brightness. [3]They usage wavelet transforms due to their integral property. These transforms decomposed the input image into different frequency components. DWT has various uses in image processing, like feature extraction ,de- noising face recognition ,satellite image super resolution etc. I practice 2-D DWT to decompose the image into four sub- band HH, HL,LL,LH[1]. The LL sub-band contains illumination information while the other sub-bands set up the information of edges.

   LL

   LL

   L

   L

   LH

   LH

   Block diagram of DWT

2. DBLA

   This algorithm computes brightness by using the Low intensity factor in the wavelet domain and transfer intensity values[12]. First of all DWT is attained on the new images and formerly utilise the log-average luminance. The LL sub group split in to three different forms. Power transfer functions are adaptively predicted utilise the log transfer function and the gamma adapt function. Since at that point, the subsequent improved image is attained usage the inverse DWT[10]. The algorithm promotes the complete contrast and recognition facts better than present techniques.

3. ADAPTIVE INTENSITY TRANSFER FUNCTION:

   This function figured in three disintegrated by using the knee transfer function and the gamma transfer function[12]. Formerly, this function is applied for colour-preservation. The ensuing enhanced image is acquired via the IDWT.

4. ADAPTIVE HISTOGRAM EQUALIZATION

   Adaptive histogram equalization [AHE] is an excellent contrast improvement method for both natural images and medical images. It is dissimilar from standard HE in the respect that the adaptive process figures numerous histograms, each equivalent to a dissimilar part of the image[8]. AHE is the process by which at lower scales contrast is improved, though at larger scales contrast of a image is reduced. The benefit of AHE is that it is , reducible and frequently creates superior images.

5. FUZZY BASED IMAGE DEVELOPMENT

This technique is among the vital methods of image processing. It has two essential parameters M and k. M is the average intensity value and K is the contrast intensity parameter. Only the V component spread with contrast enhancement techniques as well as compared with advanced algorithms

II RELEATED WORK

Jafar et al. (2007) [1] has proposed that contrast enhancement is a vital stage in virtually apiece image processing. This method is simple and effective. Li et al.(2008)[2] has suggested a novel color image enhancement process which is based on (Multi Scale Retinex)MSR. Apposite wavelets bases input image fragmented in three levels. Then decompose the process input image into different enhancements algorithms. Then coefficients were employed to scale. Chen et al.(2008)[3] has planned a new contrast enhancement technique for remote sensing images which is based on fuzzy. Fuzzy set theory proposed use grey due to the traditional division by values to evade claps. The foremost conception of the principle is that the elements of an interval [0, 1] instead of binary value membership degree. Sheets et al. (2010) [4] has proposed a new method to increase its brightness and contrast enhancement capabilities.Performance time- dependent on subdivision size and histogram. Yang et al. (2010) [5] has defined some nonlinear transform image contrast enhancement method. It is the most used functions to represent a regularized incomplete beta function estimates. But how to define beta function coefficients for Marg is a problematic. To avoid tricking in local optimum, a chaotic differential evolution algorithm is suggested. Men et al (2010) [6] has described a fuzzy contrast enhancement procedure using fuzzy principle in non-subsampled contour- let transform (NSCT) domain. In this technique the input image high pass sub-band and decomposed in sub-band low pass by NSCT. Then, map each high pass membership function in Fuzzy domain for applying to image contrast. Finally, modify the NSCT fuzzy domain and modified from image NSCT coefficients to regroup. Demirel et al.(2010)[7] has presented a new satellite image contrast enhancement process. It is based on the DWT and SVD. In these techniques divide the input image using dwt-up and low-sub- band image. Then singular value matrix estimates and again it is the inverse DWT. Experimental results shows that the planned process has the superiority over previous and State- of-artprocesses. Akho et al. (2012) [8] has suggested a novel fuzzy logic and histogram based algorithm for image enhancement. It has two essential parameters M and k. M is the average intensity value and K is the contrast intensity

parameter. Only the V component spread with traditional contrast enhancement techniques as well as compared with advanced algorithms. Ramadan et al (2014)[9]] has presented a novel technique for an images impulsive noise decrease and edge protection. There are two conditions to determine whether an image pixel is noisy or not in the detection stage. To distinguish between corrupted and uncorrupted pixels two predetermined threshold values are elaborate in the computation of the second condition.Only pixels detection stage to be set for the noise in the next filtering stage. Yu et al.(2014)[10] has provided that Edge preservation ratio (EPR) is a full-reference metric for objective image quality assessment(IQA).The probability and supremacy of EPR have now been validated via image amplification and noise decrease. Tentative effects propose it is tough to totally recover missing communications by image zoom and high image distinction may be produced from brief and distinctive image assemblies. Dshmukh et al.(2015)[11] has presented novel contrast enhancement method which is based on fuzzy. The image fuzzify, function and defuzzify is proposed.To capture the medical image contrast this method is applied. Arora et al.(2015)[12]has defined that a vastly overexposed color image is considered by high brightness, low chromaticity and loss of feature.Based on the intensity of exposure, split two areas, dark and bright image. Contrast improvement and bright areas darker than V components are fuzzified and choosing modify membership functions. For being illuminated , s component is modified and fuzzified. Sarangi, p. P. Et al (2014) [13] has presented an examination procedure for engineering and machine knowledge optimization problems. Enhance its adaptability and effectiveness in a gray scale image detail. Jin et al.(2015)[14] has offered a new method for both noise suppression and edge protection. To perceive the edge info the building tensor is proposed. In this technique reduction, detection and quantified process are integrated as a matrix mask.

III GAPS IN LITERATURE

Following are the various gaps in earlier work on image enhancement techniques.

1. The DBLA has neglected the use of guided image filter to decrease the problem of noise which will bes in the image.

2. It is also found the color artifacts which are existing in the image because of the transform domain methods are also ignored in DBLA.

IV PROPOSED METHODOLOGY

Input Image

DWT

LL subband

HH,LH and LH subband

Image decomposition based on dominant brightness level

Low intensity layer

Analysis of dominant Of brightness level

Analysis of dominant Of brightness level

Middle intens- ty layer

High-intensity layer

Adaptive intensity transfer function Estimation

Adaptive intensity transfer function Estimation

Adaptive intensity transfer function Estimation

Adaptive intensity transfer function Estimation

Boundary Smoothing

Contrast enhancement

Contrast enhancement

Contrast enhancement

IDWT

IDWT

Image Fusion

Guided filer

Guided filer

Adaptive histogram equilization

Adaptive histogram equilization

Contrast enhancement

Weighted Map Estimation

Fuzzy based enhancement

Fuzzy based enhancement

V RESULTS AND DISCUSSIONS

Towards appliance the planned algorithm, plan and implementation has been prepared in MATLAB applying image control toolbox. Outcome appearances that this method provides superior effects than surviving procedures.Table 1 is show the numerous images that are found in that research work. As revealed in provided numbers, we're comparing the outcomes of many images. Results shows assessed method results which are a lot better than existing methodologies. The outcomes shows the performance analysis between existing and in the projected methods. There are various parameters are used to show the performance of projected technique

It necessities to be abridged so the projected algorithm is show the enhanced results than the accessible method such as MSE is less in entirely case

Table1. Images used in research work

Mean Square Value(Mse)

MSE is the best process to show dimension of the persisting technique and proposed technique. This is process is forthright to project algorithm that fall the mean square error.

Table2. Mean square error value

Fig1.Analysis of MSE

Peak Signal To Noise Ratio(Psnr)

This process is the relation between the determined probable unit of signal and debasing noise that affect the value of image. PSNR signify the peak error. To calculate the PSNR firstly find out the value of the MSE.

It is defined as:

MSE

=20 MSE

=20 )

Table3. peak signal to noise ratio

Fig2.Analysis of peak signal to noise ratio

ROOT MEAN SQUARE ERROR(RMSE)

The RMSE is used to figure the change amid the expected values and values detected from the surrounds that is being demonstrated. RMSE need to be minimized.

Table 4.Root mean square error

Fig4.Analysis of rot mean square error

BIT ERROR RATE(BIR)

This is simply the Bit Error Ratio among the input image and final image. It need to be minimized.

Table 5.Bit error rate

Fig3.Analysis of bit error rate

Normalize Cross Co-Relation(Ncc)

NCC necessities to be close to 1, so planned algorithm show improved outcomes than the existing procedures as NCC is close to 1 in each instance .The main objective is to preserve NCC as much as possible to close to one.

NCC =

Table6. Normalized cross co-relation

Fig5Analysis of normalization cross co-relation

NORMALIZED ABSOLUTE ERROR(NAE)

NAE is a degree of exactly how distant is the fused image from the novel image. Large value of Normalized absolute error shows poor quality of the image.

NAE

Table7.Normalized absolute error

Fig6.Analysis of normalized absolute error

1. CONCLUSION

   This paper represents enhancement approach based on dominant brightness level analysis Fuzzy logic for remote sensing images. The existing technique has been done work on the low-contrast images acquired by a satellite camera . As such no work has done for the images having the color artifacts.In this work proposed the DWT as well as adaptive histogram equalization as the post processing function and also uses the illuminate normalization to enhance the accuracy of image by reducing the problem of noise.The evaluation of technique is done on the basis of the parameters Mean square error, Peak signal to noise ratio, Root mean square value, Bit error rate, Normalize cross co-relation, Normalize absolute error has performed well as compared to existing technique.

2. REFERENCES

1. Lee E, Kim S, Kang W, Seo D, Paik J. Contrast enhancement using dominant brightness level analysis and adaptive intensity transformation for remote sensing images. Geoscience and Remote Sensing Letters, IEEE. 2013 Jan;10(1):62-6.

2. Varma N, Gupta AP, Sharma A. IMAGE ENHANCEMENT USING DWT.

3. Rajput S, Suralkar SR. Comparative study of image enhancement techniques. International Journal of Computer Science and Mobile Computing (IJCSMC). 2013 Jan;2(1):11- 21.

4. Jafar, Iyad, and Hao Ying. "Multilevel component-based histogram equalization for enhancing the quality of grayscale images." In Electro/Information Technology, 2007 IEEE International Conference on, pp. 563-568. IEEE, 2007.

5. He, Li, and You Yang. "An Improved Color Image Enhancement Algorithm Based on MSR." In Computer Science and Computational Technology, 2008. ISCSCT'08. International Symposium on, vol. 1, pp. 13-16. IEEE, 2008.

6. Chen, Chi-Farn, Hung-Yu Chang, and Li-Yu Chang. "A Fuzzy- based method for remote sensing image contrast enhancement." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 37 (2008): 995-998.

7. Sheet, Debdoot, Hrushikesh Garud, Amit Suveer, Manjunatha Mahadevappa, and Jyotirmoy Chatterjee. "Brightness preserving dynamic fuzzy histogram equalization." Consumer Electronics, IEEE Transactions on 56, no. 4 (2010): 2475- 2480.

8. Yang, Qingyun. "An adaptive image contrast enhancement based on differential evolution." In Image and Signal Processing (CISP), 2010 3rd International Congress on, vol. 2, pp. 631-634. IEEE, 2010.

9. Men, Guo-Zun, Jian-Lei Yang, and Jie Zhao. "Fuzzy contrast enhancement for remote sensing image based on fuzzy set in nonsubsampled contourlet domain." In Machine Learning and Cybernetics (ICMLC), 2010 International Conference on, vol. 2, pp. 735-740. IEEE, 2010.

10. Demirel, Hasan, Cagri Ozcinar, and Gholamreza Anbarjafari. "Satellite image contrast enhancement using discrete wavelet transform and singular value decomposition." Geoscience and Remote Sensing Letters, IEEE 7, no. 2 (2010): 333-337.

11. AkhoZahieh, Maryam M., and Nasser Abdellatif. "Iternational Journal of Electronics and Communications (AEU)." (2012).

12. Lee, Edward, Sungho Kim, Wei Kang, Daeban Seo, and Jamie Paik. "Contrast enhancement using dominant brightness level analysis and adaptive intensity transformation for remote sensing images." Geoscience and Remote Sensing Letters, IEEE 10, no. 1 (2013): 62-66.

13. Ramadan, Zayed M. "A New Method for Impulse Noise Elimination and Edge Preservation." Electrical and Computer Engineering, Canadian Journal of 37, no. 1 (2014): 2-10

14. Yu, Shaode, Wentao Zhang, Shibin Wu, Xiaolong Li, and Yaoqin Xie. "Applications of edge preservation ratio in image processing." In Signal Processing (ICSP), 2014 12th International Conference on, pp. 698-702. IEEE, 2014.

15. Deshmukh, Pranali. "Fuzzy based contrast enhancement." In Electrical, Electronics, Signals, Communication and Optimization (EESCO), 2015 International Conference on, pp. 1-4. IEEE, 2015

16. Arora, Shaveta, M. Hanmandlu, Gaurav Gupta, and Latika Singh. "Enhancement of overexposed color images." In Information and Communication Technology (ICoICT), 2015 3rd International Conference on, pp. 207-211. IEEE, 2015.

17. Sarangi, P. P., B. S. P. Mishra, Banshidhar Majhi, and S. Dehuri. "Gray-level image enhancement using differential evolution optimization algorithm." In Signal Processing and Integrated Networks (SPIN), 2014 International Conference on, pp. 95-100. IEEE, 2014.

18. Jin, Jing, Songyuan Tang, and Yi Shen. "An innovative image enhancement method for edge preservation in wavelet domain." In Instrumentation and Measurement Technology Conference (I2MTC), 2015 IEEE International, pp. 52-56. IEEE, 2015.

will compare the Gray Stretch Based algorithm for image