Adaptive Restoration Before Edge Detection Using Image Condition Features

This paper described a condition-aware image restoration and edge detection system built using Flask. The image is examined before edge extraction using variance, standard deviation, impulse-noise ratio, and Laplacian variance. Based on these values, the system selects a restoration method using learned buckets, fuzzy rules, or fallback logic. Testing shows that different degradations need different preprocessing choices. Median filtering helps in impulse-noise cases, bilat-eral filtering preserves strong boundaries during smoothing, and non-local means improves random-noise cases at the cost of extra processing time. The current metric values can be improved further, but the system provides a practical starting point for restoration-assisted edge extraction in a web appli-cation.

[1]     J. Canny, “A computational approach to edge detection,” IEEE Trans-actions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679–698, 1986. [2]     J. M. S. Prewitt, “Object enhancement and extraction,” in Picture Processing and Psychopictorics. New York, NY, USA: Academic Press, 1970, pp. 75–149. [3]     C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Proc. IEEE International Conference on Computer Vision, 1998, pp. 839–846. [4]     A. Buades, B. Coll, and J. M. Morel, “A non-local algorithm for image denoising,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 60–65. [5]     Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004. [6]     L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–353, 1965. [7]     O. Kupyn, V. Budzan, M. Mykhailych, D. Mishkin, and J. Matas, “DeblurGAN: Blind motion deblurring using conditional adversarial networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8183–8192. [8]     O. Kupyn, T. Martyniuk, J. Wu, and Z. Wang, “DeblurGAN-v2: Deblur-ring orders-of-magnitude faster and better,” in Proc. IEEE International Conference on Computer Vision, 2019, pp. 8878–8887. [9]     D. Martin, C. Fowlkes, D. Tal, and J. Malik, “A database of human segmented natural images and its application to evaluating segmentation algorithms,” in Proc. IEEE International Conference on Computer Vision, 2001, pp. 416–423. [10]    R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. New York, NY, USA: Pearson, 2018.