Andere Kunden interessierten sich auch für
![A Hybrid DWT, PCA and ICA Features for Face Recognition using ANN]( "A Hybrid DWT, PCA and ICA Features for Face Recognition using ANN")
A Hybrid DWT, PCA and ICA Features for Face Recognition using ANN23,99 €![Improvement of Iris Image Authentication using Moment Based Features]( "Improvement of Iris Image Authentication using Moment Based Features")
Improvement of Iris Image Authentication using Moment Based Features42,99 €![Detection of Fast Flux Network Based Social Bot Using AB Techniques]( "Detection of Fast Flux Network Based Social Bot Using AB Techniques")
Detection of Fast Flux Network Based Social Bot Using AB Techniques23,99 €![Pose Invariant Face Recognition using PCA]( "Pose Invariant Face Recognition using PCA")
Pose Invariant Face Recognition using PCA36,99 €![Arrhythmia Detection by using Generative Adversarial Network Method]( "Arrhythmia Detection by using Generative Adversarial Network Method")
Arrhythmia Detection by using Generative Adversarial Network Method51,99 €![FAKE REPORT DETECTION USING MACHINE LEARNING]( "FAKE REPORT DETECTION USING MACHINE LEARNING")
FAKE REPORT DETECTION USING MACHINE LEARNING29,99 €![Libyan vehicle license plate detection and recognition using RBF]( "Libyan vehicle license plate detection and recognition using RBF")
Libyan vehicle license plate detection and recognition using RBF36,99 €
In this work, we propose the model for face detection. The proposed model is based on HSI (Hue, saturation and Intensity) color model. The HSI color model is used to acquire the color information of the pixel of the target image. The edge detection is used to extract the boundary and fill the image region where boundaries make a closure. Both HSI color and edge detection applied separately and simultaneously. We obtain the color segmented image by taking the union of HSI color and edge detection. The face detection is achieved using the proposed model by applying morphology operations, filled region and non-face rejection to obtain the exact number of faces present in the image. The performance of the proposed model is evaluated and compared with the existing region-growing algorithm. We consider three parameters precision (P), recall (R) and F1 value to evaluate the efficiency of proposed model. We have also measured the accuracy of the precision-recall (PR) curve against the Receiver Operator Characteristic (ROC) curves. The face detection using proposed model is tested on 290 images which are taken from UCD (University College Dublin) image dataset and other resources.