Face Detection Algorithm based on Skin Detection, Watershed Method and Gabor Filters

Abstract

Automatic face detection has been intensively studied for human-related recognition systems. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. In this paper, a new face detection algorithm is proposed. This speedy and robust solution developed, on the one hand is based on the segmentation of the color image to skin regions using a new approach to detect the pixels of the skin and the water shed segmentation method. On the other hand, using Gabor filters, combined with a proposed model of face, skin regions are classified into two classes: face and non-face. The integration of these tools in our algorithm permits to develop a face detector with very reasonable and efficient performances. Experimental results show that the method mentioned in this paper can achieve high detection rates and low false positives. To evaluate the detection speed of proposed algorithm, a comparison with a recent known algorithm is made too.

ORB feature based web pornographic image recognition

“…In this paper we use the skin-color model from the reference [21] to detect the skin-color regions of images. The model is described as: (Cb ≥ 97.…”

Analisis Identifikasi Wajah Menggunakan Gabor Filter Dan Skin Model

“…Beberapa penelitian menggunakan fitur warna dalam kegiatan pengenalan objek dikarenakan proses yang cepat dan sederhana [1]. Skin Model merupakan kondisi atau kriteria yang digunakan untuk membantu menentukan apakah suatu piksel memiliki nilai warna yang memenuhi syarat sebagai warna kulit atau bukan [2]. Hasil ekstraksi fitur kulit sangat membantu dalam memisahkan anggota tubuh manusia dari objek lain yang terdapat pada citra salah satunya adalah wajah.…”

Complete Architecture of a Robust System of Face Recognition

“…In order to accomplish the detection procedure in the developed system, we adopted the approach of detecting and locating faces in 2D images to multiple faces published in [11]. In this approach, from the captured color image, a binary image is constructed composed of two classes of pixels (skin and not-skin) by means of a skin pixel detection algorithm.…”