Effect Percentage of Seam Carving Implementation on Image Based on Texture Characteristics Using GLCM
Abstract
flexibility of the appearance of electronic devices currently causes new demands on digital media, especially for the provision of content. Until now, images, although an important element in digital media, usually remain rigid in terms of size and cannot change size so that they cannot adjust to different layouts automatically. The solution to overcome this problem is by resizing the image. One method that works well for resizing images is seam carving. Seam carving aims to resize the image by not eliminating important content in the image. This study aims to see the effect of changing the texture of seam carving images to images that have different levels of complexity. The trial was conducted by comparing the original image and seam carving image. Seam carving image used is differentiated based on the ratio scale, which is 10%, 20%, 30%, 40%, 50%. Testing is done by processing 4 image samples using the Gray Level Co-Occurence Matrix (GLCM) method including Contrast, Correlation, Energy and Homogeneity. Then testing is done by comparing the original image with seam carving image using the features of GLCM. From the test results it can be concluded that seam carving as a method of resizing images can work well, with the comparison of textures using GLCM the highest level of similarity reaches 98% and the lowest is 86%.
References
Amal, I. (2014). Replika Content-Aware Scaling Photoshop® Menggunakan Dynamic Programming. Makalah IF2211, 7.
Ayu Kardina Sukmawati, N. S., Dini Adni Navastara. (2017). Implementasi Deteksi Seam Carving Berdasarkan Perubahan Ukuran Citra Menggunakan Local Binary Patterns dan Support Vector Machine. JURNAL TEKNIK ITS, 6(2), A346.
Er. Kanchan Sharma, E. P., Er. Aditi Kalsh, Er.Kulbeer Saini. (2015). GLCM and its Features IJARECE, 4(8), 2182.
Feri Wibowo, A. H. (2017). Klasifikasi Mutu Pepaya Berdasarkan Ciri Tekstur GLCM Menggunakan Jaringan Saraf Tiruan KHAZANAH INFORMATIKA, 3(2), 104.
Lita Nur Fitriani, F. U., Wijaya Kurniawan. (2019). Klasifikasi Jenis Buah Apel Lokal Berdasarkan Penciri Warna, Aspecratio dan GLCM Menggunakan Belt Konveyor Berbasis Raspberry Pi. Jurnal Pengembangan Teknologi dan Ilmu Komputer, 3(2), 1173.
Pathak, S. (2017). Implementationand Analysis of Seam Carving with Multiple Energy Functions for Content-Aware Image Resizing. Rochestar Institute Of Technology, 59.
Rahmat Hidayat, T. A. B. W. (2015). Implementasi Seam Carving Pada Pembentukan Gambar Panorama. E-procedding of Enginering Tel-U, 8.
Rizky Andhika Surya, A. F., Anton Yudhana (2016). Ekstraksi Ciri Citra Batik Berdasarkan Tekstur Menggunakan Metode Gray Level Co Occurrence Matrix UNSRI, 2(1), 150.
Shai Avidan, A. S. (2007). Seam Carving For Content-Aware Image Resizing. ACM Transactions on Graphics, 26(3), 10-19.
Siti Fatimah, G. M., Suryasatriya Trihandaru. (2018). Analisis Homogenitas Citra Ultrasonografi Berbasis Silicone Rubber Phantom dengan GLCM Jurnal Fisika UNNES, 1(22), 27.
Zehra KARAPINAR SENTURK, D. A., Arafat SENTURK (2014). A Performance Analysis for Seam Carving Algorithm IJASCSE, 3(12), 11.
