• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.104-112
• /
• 2019

This study proposed a robust detection algorithm. It detects face more stably with respect to changes in light and rotation forthe identification of a face shape. The proposed algorithm uses face shape asinput information in a single camera environment and divides only face area through preprocessing process. However, it is not easy to accurately recognize the face area that is sensitive to lighting changes and has a large degree of freedom, and the error range is large. In this paper, we separated the background and face area using the brightness difference of the two images to increase the recognition rate. The brightness difference between the two images means the difference between the images taken under the bright light and the images taken under the dark light. After separating only the face region, the face shape is recognized by using the self-organization feature map (SOFM) algorithm. SOFM first selects the first top neuron through the learning process. Second, the highest neuron is renewed by competing again between the highest neuron and neighboring neurons through the competition process. Third, the final top neuron is selected by repeating the learning process and the competition process. In addition, the competition will go through a three-step learning process to ensure that the top neurons are updated well among neurons. By using these SOFM neural network algorithms, we intend to implement a stable and robust real-time face shape recognition system in face shape recognition.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제13권1호
• /
• pp.34-42
• /
• 2013

Human faces have been broadly studied in digital image and video processing fields. An appearance-based method, the adaptive boosting learning algorithm using integral image representations has been successfully employed for face detection, taking advantage of the feature extraction's low computational complexity. In this paper, we propose a face-detection postprocessing method that equalizes instantaneous facial regions in an efficient hardware architecture for use in real-time multimedia applications. The proposed system requires low hardware resources and exhibits robust performance in terms of the movements, zooming, and classification of faces. A series of experimental results obtained using video sequences collected under dynamic conditions are discussed.

• 한국콘텐츠학회논문지
• /
• 제17권1호
• /
• pp.137-144
• /
• 2017

얼굴 검출은 복잡한 배경 내에서 다양한 얼굴의 자세로 인해 여전히 어려운 문제에 직면하고 있다. 본 논문은 피부색과 깊이 정보를 기반으로 한 한명 또는 여러 명의 얼굴을 검출하는 효과적인 알고리즘을 제안한다. 먼저 우리는 컬러 영상에서 가우시안 혼합 모델을 이용한 피부색 검출 방법에 대해 소개한다. 그리고 Kinect V2의 깊이 센서를 이용하여 획득한 3차원의 깊이 정보는 배경으로부터 사람의 몸을 분할할 때 유용하다. 그리고 레이블링 과정에서 여러 개의 특징을 이용하여 얼굴이 아닌 영역은 성공적으로 제거된다. 실험 결과를 통해 제안한 얼굴 검출 알고리즘은 다양한 조건과 복잡한 배경에서 얼굴이 효과적으로 검출되는 것을 확인할 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.138.3-138
• /
• 2001

Because face has non-rigid structure and is influenced by illumination, we need robust face detection algorithm with the variations of external environments (orientation of lighting and face, complex background, etc.). In this paper we develop a new face detection algorithm to achieve robustness. First we transform RGB color into other color space, in which we can reduce lighting effect much. Second, hierarchical image segmentation technique is used for dividing a image into homogeneous regions. This process uses not only color information, but also spatial information. One of them is used in segmentation by histogram analysis, the other is used in segmentation by grouping. And we can select face region among the homogeneous regions by using facial features.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.531-535
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems. In this paper, we propose an effective and robust automatic face detection approach that can locate the face region in natural scene images when the system is used as a pre-processor of a face recognition system . We use two natural and powerful visual cues, the skin color and the eyes. In the first step of the proposed system, the method based on the human skin color space by selecting flesh tone regions using normalized r-g space in color images. In the next step, we extract eye features by calculating moments and using geometrical face model. Experimental results demonstrate that the approach can efficiently detect human faces and satisfactory deal with the problems caused by bad lighting condition, skew face orientation.

• 대한전자공학회논문지SP
• /
• 제47권2호
• /
• pp.33-44
• /
• 2010

본 논문에서는 로봇 시각 처리 활용을 위한 실시간 얼굴 검출 하드웨어 구조를 제안한다. 제안한 구조는 조명 변화에 강인하고 초당 60 프레임 이상의 속도로 처리된다. 조명 변화에 강인한 얼굴 특성 추출을 위해 MCT(Modified Census Transform) 변환을 이용하였다. 그리고 AdaBoost 알고리즘은 얼굴 특징 데이터의 학습 및 생성을 하며, 이 생성된 학습 데이터를 이용해 얼굴 검출을 하게 된다. 본 논문에서는 메모리 인터페이스부, 이미지 크기 조정부, MCT 생성부, 후보 얼굴 검출부, 신뢰도 비교부, 좌표 재조정부, 데이터 그룹화부, 검출 결과 표시부로 구성된 얼굴 검출 하드웨어 구조 및 Xilinx사의 Virtex5 LX330 FPGA를 이용한 하드웨어 구현 검증 결과에 대해 설명한다. 카메라로 부터 입력받은 이미지를 이용해 검증한 결과로 초당 최대 149프레임의 속도로 한 프레엠 당 최대 32개 얼굴을 검출함을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제10권1호
• /
• pp.26-35
• /
• 2007

본 논문은 연속적으로 입력되는 비디오 영상에서 효과적인 얼굴 검출기와 칼만 필터를 이용하여 강인하게 얼굴을 추적하는 시스템을 제안한다. 효과적인 얼굴 검출기를 구성하기 위해 간단한 다섯 가지 타입의 Haar-like 특징값들을 이용하여 얼굴 특징을 추출한다. 추출된 특징값들은 PCA(Principal Component Analysis)를 이용하여 재해석되고, 해석된 주성분들을 SVM(Support Vector Machine)의 입력 값으로 사용하여 얼굴과 배경으로 분류한다. 검출된 얼굴의 정적정보와 프레임간 변화량을 이용한 동적정보를 칼만 필터(Kalman Filter)에 적용하여 얼굴을 추적한다. 실시간에 적용 가능한 시스템을 구현하기 위하여 얼굴 검출회수를 조정하여 처리속도를 향상시켰다. 실험결과, 평균 93.3%의 추적 성공률과 초당 15 프레임 처리 성능으로 강인한 실시간 얼굴 추적이 가능함을 보여주었다.

• ETRI Journal
• /
• 제33권4호
• /
• pp.600-610
• /
• 2011

This paper presents a novel approach to face detection by localizing faces as the goal-specific saliencies in a scene, using the framework of selective visual attention of a human with a particular goal in mind. The proposed approach aims at achieving human-like robustness as well as efficiency in face detection under large scene variations. The key is to establish how the specific knowledge relevant to the goal interacts with the bottom-up process of external visual stimuli for saliency detection. We propose a direct incorporation of the goal-related knowledge into the specification and/or modification of the internal process of a general bottom-up saliency detection framework. More specifically, prior knowledge of the human face, such as its size, skin color, and shape, is directly set to the window size and color signature for computing the center of difference, as well as to modify the importance weight, as a means of transforming into a goal-specific saliency detection. The experimental evaluation shows that the proposed method reaches a detection rate of 93.4% with a false positive rate of 7.1%, indicating the robustness against a wide variation of scale and rotation.

• 게임&엔터테인먼트 논문지
• /
• 제2권2호
• /
• pp.45-50
• /
• 2006

형판 정합 기반의 얼굴 검출 시스템에서 획득된 이미지에 대한 명암 정규화 및 영상 보정을 위해 히스토그램 평활화나 로그 변환 등을 사용한다. 이 방법은 조명 변화에 의해 발생한 이미지의 부분 명암 왜곡에는 효과적이지 못하다는 것이 알려져 있다. 본 논문에서는 부분적 명암 왜곡에 매우 효과적인 영상 보정을 수행하는 좌우대칭 평균화 기법을 제시한다. 실험 결과 이 기법은 기존의 방식보다 매우 효율적인 검출 성능을 보일 뿐만 아니라 얼굴 후보의 개수도 현저하게 감소하는 것으로 나타났다.