Comparative survey of iris recognition

Harakannanavar, Sunil S.; Puranikmath, Veena I

doi:10.1109/iceeccot.2017.8284682

Cited by 10 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The two criteria of recognition rate and equal error provide an overview of the performance of the model, which are reported in Figures (14) and (15). The results of Figure (14) show that the combined model of this paper has performed better in both levels of composition, score and specificity compared to previous methods such as Aleem et al [ 5 ] .…”

Section: Investigation Of Recognition Rate and Equal Error Ratementioning

confidence: 80%

“…To solve this problem and achieve the best answer in the shortest time, pre-trained convolution networks were introduced. These networks are available as fully trained models, each with specific targets on very large databases such as ImageNet containing 15 . In both steps of feature extraction and classification of pre-trained networks have shown very good performance and this has led to their increasing popularity in recent years [ 40 ] .…”

Section: • Fully Connected Layermentioning

confidence: 99%

See 1 more Smart Citation

A Multimodal-biometric Identification System Based on Deep Features to Identify Individuals

Akbari

darooei

2022

Preprint

View full text Add to dashboard Cite

With the growth of new technologies, biometric-based identification has been considered as an efficient method for automatic identification of individuals due to its unique nature and inability to forge it. Recently, researchers have used a combination of several different biometrics to more accurately identify people with a lower probability of error. Some of these methods use facial and fingerprint biometrics, which can become ineffective for a variety of reasons, including age and injury. As a result, choosing biometrics that are less prone to injury is an important factor. Therefore, this paper presents an identification system based on three biometrics: iris, fingerprint and face. In this method, the above biometrics are combined in two levels of feature and score, and simple and pre-trained convolutional networks are used to extract the feature from them. The results of this model on a virtual database consisting of three databases CASIA-IRIS, YaleB and FVC2000 show that the combination at the feature level gives better results due to the use of deep features. The results also indicate that the use of pre-trained network to extract features from facial biometrics, has made these biometrics more effective than the other two biometrics in accurately identifying the model.

show abstract

Section: Investigation Of Recognition Rate and Equal Error Ratementioning

confidence: 80%

Section: • Fully Connected Layermentioning

confidence: 99%

A Multimodal-biometric Identification System Based on Deep Features to Identify Individuals

Akbari

darooei

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This algorithm is an improvement on Daugman algorithm to segment images. In [16][17][18], algorithms used for the identification stages (localization, segmentation, normalisation, feature extraction and matching) of iris recognition were briefly discussed, noting their respective advantages and disadvantages.…”

Section: Matchingmentioning

confidence: 99%

Investigation of iris segmentation techniques using active contours for non-cooperative iris recognition

Akinfende

Imoize

Ajose

2020

IJEECS

View full text Add to dashboard Cite

<span>Iris image segmentation process based on graphical user interface (GUI) to accurately localize the iris structure is presented in this paper. The major challenge confronting the precision of an iris recognition model is how to determine the accuracy of the iris segmentation and localization. There are varying parameters that introduce constraints during feature extraction and these greatly affect the matching performance during iris localization. To this end, the Integro-differential operator, which involves the detection of inner and outer regions of the iris, and the circular hough transform, which is capable of detecting the circular boundary from the edge mapping were investigated, and an active contour model was evolved. In the evolved model, an emerging curve mapped with the zeros of the data set function is experimentally exploited. To demonstrate the suitability of the model for precise iris recognition, its parameters were compared against other related models. Simulation results show that the model has higher flexibility of substitution of images, and the images could be analyzed more accurately with less false rejections (FR) and false acceptance (FA) in comparison with the integro-differential operator. This implies that images could be analyzed faster using the evolved model, and easily substituted especially in situations where the need to care for numerous eye patients occur.</span>

show abstract

“…Peneliti sebelumnya melakukan comparative study terkait dengan pengenalan iris [2]. Pada penelitian ini terdapat beberapa metode yang digunakan untuk pengenalan iris baik untuk metode ekstraksi fitur dan metode pengenalan.…”

Section: Pendahuluanunclassified

Pengenalan Iris Menggunakan Fitur Local Binary Pattern Dan RBF Classifier

Rivan¹,

Devella²

2020

Simet

View full text Add to dashboard Cite

Iris merupakan bagian dari mata yang memiliki keunikan. Keunikan pada iris ini menjadi alasan iris digunakan sebagai identitas seperti sidik jari,dan suara. Dibandingkan dengan sidik jari, iris memiliki kelebihan karena letak iris yang lebih terlindungi. Setiap individu memiliki pola iris yang berbeda dan pembentukan pola iris tidak berhubungan dengan faktor genetik individu, sehingga iris merupakan biometrik yang memiliki keunikan yang tinggi dan sulitnya untuk dilakukan pemalsuan biometrik. Identifikasi atau pengenalan iris dilakukan dengan menggunakan citra iris. Pada penelitian ini citra iris akan dilakukan tahap praproses yaitu dengan menghilangkan noise seperti bulu dan kelopak mata, yang kemudian hasil praproses citra iris dilakukan ekstraksi fitur menggunakan algoritma Local Binary Pattern (LBP). Setelah proses ekstraksi fitur dilakukan, proses selanjutnya adalah melakukan pelatihan menggunakan Radial Basis Function (RBF). Setelah proses pelatihan, model RBF diuji dengan data iris yang berbeda. Akurasi tertinggi yang dicapai pada pengenalan iris menggunakan fitur LBP dan RBF yaitu 83,33%.

show abstract

Comparative survey of iris recognition

Cited by 10 publications

References 4 publications

A Multimodal-biometric Identification System Based on Deep Features to Identify Individuals

A Multimodal-biometric Identification System Based on Deep Features to Identify Individuals

Investigation of iris segmentation techniques using active contours for non-cooperative iris recognition

Pengenalan Iris Menggunakan Fitur Local Binary Pattern Dan RBF Classifier

Contact Info

Product

Resources

About