Haar-like rectangular features for biometric recognition

Abstract

Developing a reliable, fast, and robust biometric recognition system is still a challenging task. This is because the inputs to these systems can be noisy, occluded, poorly illuminated, rotated, and of very low-resolutions. This paper proposes a probabilistic classifier using Haar-like features, which mostly have been used for detection, for biometric recognition. The proposed system has been tested for three different biometrics: ear, iris, and hand vein patterns and it is shown that it is robust against most of the mentioned degradations and it outperforms state-of-the-art systems. The proposed system has been tested using three public databases.

Inverter air conditioner intelligent system design

“…Bu algoritma ile yapılan gerçek zamanlı el jesti çalışmalarında çeşitli algoritmalar önerilmiştir. Bunlara örnek olarak Haar Cascade algoritması ve AdaBoost öğrenme algoritması ile gerçekleştirilen çalışmalar [9], [10], arka plan çıkarımı ve Haar dönüşümü yapılarak video takibi gerçekleştirilen çalışmalar [11], [12] verilebilmektedir. Bu çalışmanın öncü çalışması olarak el yeri jestinin tespitinde Haar Cascade algoritması kullanılarak özellik çıkarımı gerçekleştiren ve gerçek zamanlı olarak çalışan bir donanımın gerçekleştirildiği çalışma yapılmıştır [13].…”

Are Haar-Like Rectangular Features for Biometric Recognition Reducible?

“…In our very recent work [9] a feature based approach for biometric recognition has been introduced which is shown to be robust against most degradations and poor imaging conditions. The employed features in this system [9] are Haar-like rectangular features that are extracted from integral images. These features are fed to a PNN classifier in [9] for the final recognition.…”

“…The employed features in this system [9] are Haar-like rectangular features that are extracted from integral images. These features are fed to a PNN classifier in [9] for the final recognition. The Haar-like rectangular features were first introduced for rapid and robust object detection using a boosted cascade of simple weak classifiers [15] and have usually been used for the same purpose in the literature (see [9] for more information).…”

“…These features are fed to a PNN classifier in [9] for the final recognition. The Haar-like rectangular features were first introduced for rapid and robust object detection using a boosted cascade of simple weak classifiers [15] and have usually been used for the same purpose in the literature (see [9] for more information). The problem with Haar-like rectangular features is that one can define many different such features for a given image, while only few of these features are useful for the actual recognition and the rest just impose extra computations to the system.…”

“…The rest of the paper is organized as follows: biometric recognition using the Haar-like rectangular features of [9] is briefly revisited in the next section, then, TSA about the mean is explained in section 3, experimental results are discussed in section 4, and finally the paper is concluded in section 5.…”