Abstraksistem yang dapat digunakan untuk mengenali ekspresi wajah manusia menggunakan Jaringan Syaraf Tiruan Kohonen SOM sistem tersebut menggunakan metode PCA untuk ekstraksi fitur. Hasil ekstraksi fitur dengan PCA merupakan inisialisasi untuk proses klustering pada jaringan Kohonen SOM. Jaringan Kohonen SOM digunakan untuk membagi pola masukan kedalam beberapa kelompok (cluster). Kohonen SOM dapat mengelompokkan berdasarkan vektor-vektor  dari citra ekspresi wajah, hasil keluaran jaringan Kohonen SOM adalah kelompok yang paling dekat atau mirip dengan masukan yang diberikan. pengenalan ekspresi wajah dilakukan dengan ukuran citra masukan dan  hasilnya  80.00% didapat pada ukuran citra 90x60, dengan jumlah data pengujian 30 citra ekspresi wajah. Kata kunci: Jaringan  Syaraf  Tiruan,  Kohonen  Self  Organizing  Map, Ekspresi wajah. Principal Component Analysis (PCA)

This paper proposes primary dataset with 13 images thermal capture, 8 high frequency and 4 low frequency. We utilize thermal images fluorescent lamp and using image processing with extraction feature GLCM method. Furthermore, Contrast, Correlation. Energy, Homogeinity dan sudut 0°, 45°, 90°, 135°, these feature texture using for calculated validation compare with both exsperiment qualitative results in Table1 and Table2. Therefore, exsperiment with fluorescent lamp Figure 2 quantitative results significant in Table1. Quantitative results with fluorescent lamp in Table2 extraction feature GLCM method with angle 0°, 45°, 90°, 135° and in Table1 quantitaive result with low frequency 50 Hz with T (oC) 50 is significantly robust. Comparable quantitative results in Table2 with low frequency 50 Hz from extraction feature mean value angle 0°, 45°, 90°, 135° Contrast (0.0363), Correlation (0.9959), Energy (0.1353), and Homogeneity (0.9832).

No abstract

UIN Walisongo's student identity card (KTM) does not have much function other than just for student identification. Even if the function is increased, it can be used for absenteeism at lectures, borrowing books, or double as an automated teller card (ATM). Doing absences using KTM requires a feature matching method for matching the intended KTM image with the KTM that is searched for in the student database. The feature matching process is based on feature detection in images using various methods such as ORB and Scale Invariant Feature Transform (SIFT). We can perform the feature matching method using the Brute-Force method and the Fast Library Approximated Nearest Neighbor (FLANN) on Google Colab with Python. The results of feature matching on the FLANN method are more than the Brute-Force method. The validation of the two image feature matching was carried out using the Root Mean Square Error (RMSE) method, resulting in an average value of 10.424. The purpose of this article is to detect student ID cards with matching features in the image. The FLANN and Brute-Force feature matching methods can be used to detect KTM UIN in images. Keywords: feature matching, SIFT, FLANN, Brute-Force, RMSE

We proposed an Enhanced Face Image Generative Adversarial Network (EFGAN). Single image super-resolution (SISR) using a convolutional is often a problem in enhancing more refined texture upscaling factors. Our approach focused on mean square error (MSE), validation peak-signal-to-noise ratio (PSNR), and Structural Similarity Index (SSIM). However, the peak-signal-to-noise ratio has a high value to detail. The generative Adversarial Network (GAN) loss function optimizes the super-resolution (SR) model. Thus, the generator network is developed with skip connection architecture to improve performance feature distribution.