8 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 8 / 8
Öğe Detection and recognition of Turkish license plate characters with image segmentation based correlation method(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Orun, ÖzgeÖğe Multi-feature extraction and multi-classification techniques with computer aided breast cancer detection(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Classification of soil surface wetness by histogram of oriented gradients and extreme learning machine models(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Parmak izi tanıma tekniklerine genel bir bakış(Batman Üniversitesi, 2018) Çalışkan, Abidin; Budak, Cafer; Acar, EmrullahÖğe 2B ve 3B medikal görüntülerde gürültü temizleme tekniklerinin karşılaştırmalı incelenmesi(Batman Üniversitesi, 2018) Çalışkan, Abidin; Çevik, Ulus; Acar, EmrullahÖğe Palmprint recognition system based on gabor wavelet transform with K-NN classifier model(INESEC, 2017) Çalışkan, Abidin; Ergen, Burhan; Acar, EmrullahPalmprint recognition system is regarded as reliable and accurate biometric identification system. The biometric approach palm recognition system has attracted the attention of researchers in recent times because of the presenting a new biometric feature compared to other models. In this work, gabor wavelet transform (GWT) based palmprint recognition system has been developed. Firstly, image coordinate system is determined in order to facilitate image alignment for feature extraction. Then, region of interest is cropped from the palmprint images. With the developed system, features are extracted from the region of interest and they are given to k-nearest neighbors (k-NN) classifier as input parameters. Finally, the highest success rate for GWT based systematic sampling was computed as 86.90% according to the non-request data selection and it was observed that the proposed recognition system provide successful results in classification of palmprint images. Moreover, a good identification of the feature vector is the main factor that affects performance. Thus, the performance can also be improved by finding more suitable feature vectors.Öğe Comparison of multiple biometric identification with a single biometric identification system(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Fingerprint recognition system based on law’s texture energy measures with extreme learning machines(INESEC, 2017) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferFingerprint recognition systems are one of the most popular biometric systems used in many areas, including prisons, border controls, educational institutions and forensic medicine. This paper presents a new approach based on the texture features for fingerprint recognition system. The dataset which employed in this study is obtained from the Hong Kong Polytechnic University High-ResolutionFingerprint database. The proposed system was implemented in two basic stages. Firstly, the texture feature vectors were extracted from the images by using Law’s Texture Energy Measures (TEM) and totally 9 parameters were extracted for each image as a feature vector. Then, the obtained feature vectors were classified by using Extreme Learning Machines (ELM) model. Finally, the average performance of the proposed system was computed according to different tuning parameters and the highest accuracy rate was observed as 83.92 % among the all system architectures.
