• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.321-326
• /
• 2004

Many researchers have been studied texturing the 3D face model with front and side pictures of ordinary person. It is very important to exactly detect the psition of eyes, nose, mouth of a human from the side pictures. Previous results first found the position of eye, nose, or mouth and then extract the other face components using their positional correlation. The detection results greatly depend on the correct extraction of the neck from the images. Therefore, we present a new algorithm that remove the neck completely and thus improve the detection rates of face components. To do this, we will use the RGB values and its differences.

• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1141-1149
• /
• 2014

Recently, various methods to effectively eliminate the noise are researched in image processing techniques. However, the conventional noise filtering techniques, which remove most of the noise, are less efficient for remained noise detection after filtering due to exploiting no face feature information. In this paper, we proposed a feature vector generation technique in the mouth region by distinguishing and revising the remained noise through gradient correction, when the outline is extracted after performing noise filtering.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.61-71
• /
• 2004

Recently, various techniques for face detection are studied, but most of them still have problems on processing in real-time. Therefore, in this paper, we propose novel techniques for real-time detection of human faces in sequential images using motion and chroma information. First, background model is used to find a moving area. In this procmoving area. edure, intensity values for reference images are averaged, then skin-color are detected in We use HCr color-space model and adaptive threshold method for detection. Second, binary image labeling is applied to acquire candidate regions for faces. Candidates for mouth and eyes on a face are obtained using differences between green(G) and blue(B), intensity(I) and chroma-red(Cr) value. We also considered distances between eye points and mouth on a face. Experimental results show effectiveness of real-time detection for human faces in sequential images.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.311-318
• /
• 2013

For face detection techniques, the correctness of detection decreases with different lightings and backgrounds so such requires new methods and techniques. This study has aimed to obtain data for reasoning human emotional information by analyzing the components of the eyes and mouth that are critical in expressing emotions. To do this, existing problems in detecting face are addressed and a detection method that has a high detection rate and fast processing speed good at detecting environmental elements is proposed. This method must detect a specific part (eyes and a mouth) by using Haar-like Feature technique with the application of an integral image. After which, binaries detect elements based on color information, dividing the face zone and skin zone. To generate correct shape, the shape of detected elements is generated by using a bezier curve-a curve generation algorithm. To evaluate the performance of the proposed method, an experiment was conducted by using data in the Face Recognition Homepage. The result showed that Haar-like technique and bezier curve method were able to detect face elements more elaborately.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.519-528
• /
• 2012

Voice activity detection (VAD) is generally conducted by extracting features from the acoustic signal and a decision rule. The performance of such VAD algorithms driven by the input acoustic signal highly depends on the acoustic noise. When video signals are available as well, the performance of VAD can be enhanced by using the visual information which is not affected by the acoustic noise. Previous visual VAD algorithms usually use single visual feature to detect the lip activity, such as active appearance models, optical flow or intensity variation. Based on the analysis of the weakness of each feature, we propose to combine intensity change measure and the optical flow in the mouth region, which can compensate for each other's weakness. In order to minimize the computational complexity, we develop simple measures that avoid statistical estimation or modeling. Specifically, the optical flow is the averaged motion vector of some grid regions and the intensity variation is detected by simple thresholding. To extract the mouth region, we propose a simple algorithm which first detects two eyes and uses the profile of intensity to detect the center of mouth. Experiments show that the proposed combination of two simple measures show higher detection rates for the given false positive rate than the methods that use a single feature.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.57-60
• /
• 2002

Facial features are often used for human computer interface(HCI). This paper proposes a method to detect facial features using color and facial geometry information. Face region is first extracted by using color information, and then the pupils are detected by applying a separability filter and facial geometry constraints. Mouth is also extracted from Cr(coded red) component. Experimental results shows that the proposed detection method is robust to a wide range of facial variation in position, scale, color and gaze.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.29 no.5
• /
• pp.315-322
• /
• 2003

Background : Important factors to determine treatment method and prognosis of oral cancer are anatomical site, tumor size, metastatic lesion, histologic cell differenciation and microvascular invasion. Anatomical site has great effect to oral cancer patient's survival rate because each site's accessibility and lymph node metastasis is different but this factor was't studied much than other factors. Patients and Methods : 228 patients with squamous cell carcinoma of common primary sites(Mandible, Maxilla, Floor of Mouth and Tongue) in oral cavity who were diagnosed in the Korea Cancer Center Hospital from January 1989 to December 1999, were clinically studied and analyzed on survival rate. Results : 1. Survival rates of each anatomical sites were Tongue(36.8%), Mandible(33.3%), Maxilla(28.7%) and Floor of Mouth(24.5%). Survival rates difference between Tongue and Floor of Mouth has significance(p<0.05). 2. Survival rates for early cancer of each site were Maxilla(100%), Mandible(57.1%), Tongue(54.2%) and Floor of Mouth(46.7%). Survival rates difference between Maxilla and Floor of Mouth has significance(p<0.05). 3. Survival rates by surgery method of each site were Maxilla(60.6%), Tongue(56.9%), Mandible(44.8%) and Floor of Mouth(26.3%). Survival rates difference between Maxilla and Floor of Mouth has significance(p<0.05). 4. Survival rates by radiation or chemo method of each site were Floor of Mouth(23.5%), Mandible(20.0%), Maxilla(9.5%), and Tongue(9.1%). Survival rates difference between each site doesn't have significance(p>0.05). 5. In advance stage, Survival rates by single therapy of each site were Tongue(33.6%), Mandible(23.5%), Floor of Mouth(16.7%), Maxilla(0%), and Survival rates difference between Maxilla and Tongue has significance (p<0.05). Survival rates by combination therapy of each site were Mandible(38.1%), Maxilla(30.0%), Floor of mouth(18.2%), Tongue(12.5%), and Survival rates difference between Mandible and Tongue has significance(p<0.05). Conclusion : Survival rate of tongue is higher than the other sites, early detection of oral cancer can increase survival rate at any site and combination therapy is the most effetive method, especially at maxilla.

• IE interfaces
• /
• v.19 no.3
• /
• pp.174-180
• /
• 2006

This paper deals with the robot system of recognizing human's expression from a detected human's face and then showing human's emotion. A face detection method is as follows. First, change RGB color space to CIElab color space. Second, extract skin candidate territory. Third, detect a face through facial geometrical interrelation by face filter. Then, the position of eyes, a nose and a mouth which are used as the preliminary data of expression, he uses eyebrows, eyes and a mouth. In this paper, the change of eyebrows and are sent to a robot through serial communication. Then the robot operates a motor that is installed and shows human's expression. Experimental results on 10 Persons show 78.15% accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.110-115
• /
• 2005

This paper proposes the method to detect contours of a face, eyes and a mouth in a color image for making an avatar automatically. First, we use the HSI color model to exclude the effect of various light condition, and we find skin regions in an input image by using the skin color is defined on HS-plane. And then, we use deformable templates and Genetic Algorithm(GA) to detect contours of a face, eyes and a mouth. Deformable templates consist of B-spline curves and control point vectors. Those can represent various shape of a face, eyes and a mouth. And GA is very useful search procedure based on the mechanics of natural selection and natural genetics. Second, an avatar is created automatically by using contours and Fuzzy C-means clustering(FCM). FCM is used to reduce the number of face color As a result, we could create avatars like handmade caricatures which can represent the user's identity, differing from ones generated by the existing methods.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.575-578
• /
• 1999

The principal features of a face are as follows : skin-tone, symmetry, and requisites such as shape of ellipse, eyes, nose, mouth. Also, faces have different size, various shape and position. In case of application of face recognition and detection without preprocessing, efficiency of the performance is decreased. In addition, face itself, complex background, image quality, etc. are included. Therefore, previous face recognition methods are implemented on the base of specific constraints of the face image. In this paper, we propose the efficient and automatic face detection algorithm for minimizing influence such as complex background, image quality, etc. This face detection technique consists of skin-tone, candidate face region and face region extractions.