Peningkatan Kualitas Citra Hasil Enhancement Dengan Metode Peningkatan Rata - Rata Dan Simpangan Baku Berbasis Statistik Representasi Visual

Faruk alfiyan

Abstract


Penurunan kualitas sebuah citra seringkali terjadi akibat adanya proses perbaikan yang dilakukan pada citra tersebut. Penurunan kualitas citra umumnya ditandai dengan hilangnya kontras pada beberapa lokal citra dan juga hilangnya detail dalam bagian tertentu citra. Dampak dari hal ini tentu akan sangat besar pada citra, karena informasi atau data yang terkandung dalam citra akan bias dan jauh dari relevansinya. Untuk meminimalisir penurunan kualitas citra yang disebabkan karena proses enhancement citra, maka harus dilakukan langkah-langkah yang dapat mengembalikan informasi yang ada dalam citra asal ke dalam citra hasil enhancement tersebut. Dengan menggabungkan kembali citra asal dan citra hasil enhancement, informasi yang hilang pada citra akan dapat dikembalikan sebagaimana mestinya. Namun proses penggabungan citra tersebut harus didahului dengan sebuah proses yang dapat meningkatkan rata-rata nilai dan rata-rata dari simpangan baku citra hasil enhancement. Jika kedua proses tersebut dilakukan dengan benar, maka informasi yang didapat dari penggabungan kedua citra akan memberikan hasil yang maksimal. Dari uji coba terhadap lima ratus sample citra yang dikelompokkan dalam tiga kategori, yaitu citra dengan tingkat brightness kurang, citra dengan tingkat kontras kurang, dan citra dengan tingkat brightness dan kontras kurang, terdapat tujuh puluh empat sample citra yang belum dapat diperbaiki. Sedangkan pada sample citra uji coba yang lain, dapat diperbaiki kekurangannya. Artinya keberhasilan yang telah dicapai sebesar delapan puluh lima persen.

 

Decreasing the quality of an image often occurs due to the process of improvement made on the image. The decrease in image quality is generally characterized by loss of contrast in some local images and also loss of detail in certain parts of the image. The impact of this will certainly be very large in the image because the information or data contained in the image will be biased and far from its relevance.To minimize the decline in image quality caused by the image enhancement process, steps must be taken to restore the information contained in the original image into the enhancement image. By re-combining the original image and the enhancement image, the information lost in the image will be restored accordingly. But the process of combining these images must be preceded by a process that can increase the average value and average of the standard deviation of the image results of enhancement. If the two processes are carried out correctly, the information obtained from the merging of the two images will give maximum results.From the trial of five hundred image samples grouped in three categories, namely images with less brightness, images with less contrast levels, and images with less brightness and contrast, there are seventy-four image samples that cannot be repaired. Whereas in other trial sample images, the deficiencies can be corrected. This means that the success achieved is eighty-five percent.


Keywords


Citra; Rata-rata; Simpangan Baku; Statistik

Full Text:

pdf (Indonesian)

References


Arifin, A. Z., & Arieshanti, I. (2017). Perbaikan Kualitas Citra Dengan Metode Fusi Berbasis Pada Statistik Representasi Visual. 1–7. Surabaya.

Chen, Q., Xu, X., Sun, Q., & Xia, D. (2017). A solution to the deficiencies of image enhancement. Signal Processing, 90(1), 44–56. https://doi.org/10.1016/j.sigpro.2009.05.015

Ghrare, S. E. (2018). The Effect of Image Data Compression on the Clinical Information Quality of Compressed Computed Tomography Images for Teleradiology Applications. European Journal of Scientific Research, 23(1), 6–12.

Gonzalez, R. C. ., & Woods, R. E. (2016). Digital image processing. Nueva Jersey, p. 976. New Jersey: Prentice Hall.

Han, Z., Tang, X., Gao, X., & Hu, F. (2018). Image Fusion and Image Quality Assessment of Fused Images. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-7/W1(4), 33–36. https://doi.org/10.5194/isprsarchives-xl-7-w1-33-2013

Jobson, D. J., Rahman, Z. U., & Woodell, G. A. (2017). A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image Processing, 6(7), 965–976. https://doi.org/10.1109/83.597272

Jobson, D. J., Rahman, Z., & Woodell, G. A. (2018). The Statistics of Visual Representation. Visual Information Processing XI, 4736. Orlando, FL, United States.

Kaiqi, H., Zhenyang, W., Qiao, W. (2017). Image enhancement based on the statistics of visual representation. Image and Vision Computing, 23(1), 51–57. https://doi.org/10.1016/j.imavis.2004.07.005

Mevik, B. (2017). Mean squared error of prediction ( MSEP ) estimates for principal component regression ( PCR ) and partial least squares regression ( PLSR ) ∗. Journal of Chemometrics, 18(9), 422–429.

Raskar, R., Ilie, A., & Yu, J. (2017). Image Fusion for Context Enhancement. NPAR ’04 Proceedings of the 3rd International Symposium on Non-Photorealistic Animation and Rendering, 85–152. Annecy, France: ACM New York, NY, USA.




DOI: http://dx.doi.org/10.35671/telematika.v12i2.853

Refbacks





Indexed by:


Telematika
ISSN: 2442-4528 (online) | ISSN: 1979-925X (print)
Published by : Universitas Amikom Purwokerto
Jl. Let. Jend. POL SUMARTO Watumas, Purwonegoro - Purwokerto, Indonesia


Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License .