PERANCANGAN SISTEM BIOMETRIK TELINGA BERBASIS TAPIS GABOR MENGGUNAKAN JARINGAN SYARAF TIRUAN PERAMBATAN BALIK

Innovation in developing reliable security systems is crucial for protecting personal information, privacy data, and access control. Ear biometrics, which utilizes the unique structure of the ear, offers a promising method for human identification due to its resistance to counterfeiting. This study designed and tested an ear biometric identification system using images of the right ear without accessories from five male individuals, totaling 224 images. The pre-processing involved resizing the images, converting them to grayscale, and applying a Gaussian filter. Segmentation was performed using Canny edge detection, followed by morphological operations such as dilation and hole filling. Features of the ear images were extracted using a Gabor filter, and classification was carried out with the Back Propagation Neural Network method. The system achieved an average success rate of 88.8% across five testing scenarios, with the highest accuracy of 94% in the first and fifth scenarios. Sensitivity for classes 1, 2, 3, 4, and 5 was 98%, 74%, 92%, 96%, and 82%,
respectively. Specificity reached 100% for classes 1 and 3, and 94%, 97.5%, and 94.5% for classes 2, 4, and 5. Based on the results of accuracy, sensitivity, and specificity testing, it can be concluded that the ear biometric system with Gabor filter feature extraction and Back Propagation Neural Network classification demonstrates good performance and has potential for security applications. However, there are still classification errors that could lead to misrecognition of unregistered individuals.

Keywords: Biometrics, Ear, Image Processing, Gabor Filter, Back Propagation Neural Network