• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.127-136
• /
• 2021

Real-time human recognition is a challenging task, as the images are captured in an unconstrained environment with different poses, makeups, and styles. This limitation is addressed by generating several facial images with poses, makeup, and styles with a single reference image of a person using Generative Adversarial Networks (GAN). In this paper, we propose deep learning-based human recognition using integration of GAN and Spatial Domain Techniques. A novel concept of human recognition based on face depiction approach by generating several dissimilar face images from single reference face image using Domain Transfer Generative Adversarial Networks (DT-GAN) combined with feature extraction techniques such as Local Binary Pattern (LBP) and Histogram is deliberated. The Euclidean Distance (ED) is used in the matching section for comparison of features to test the performance of the method. A database of millions of people with a single reference face image per person, instead of multiple reference face images, is created and saved on the centralized server, which helps to reduce memory load on the centralized server. It is noticed that the recognition accuracy is 100% for smaller size datasets and a little less accuracy for larger size datasets and also, results are compared with present methods to show the superiority of proposed method.

• 한국인지과학회:학술대회논문집
• /
• 한국인지과학회 2002년도 춘계학술대회
• /
• pp.111-116
• /
• 2002

The regularity effect for printed word recognition and naming depends on ambiguities between single letters (small grain-size) and their phonemic values. As a given word is repeated and becomes more familiar, letter-aggregate size (grain-size) is predicted to increase, thereby decreasing the ambiguity between spelling pattern and phonological representation and, therefore, decreasing the regularity effect. Lexical decision and naming tasks studied the effect of repetition on the regularity effect for words. The familiarity of a word from was manipulated by presenting low and high frequency words as well as by presenting half the stimuli in mixed upper- and lowercase letters (an unfamiliar form) and half in uniform case. In lexical decision, the regularity effect was initially strong for low frequency words but became null after two presentations; in naming it was also initially strong but was merely reduced (although still substantial) after three repetitions. Mixed case words were recognized and named more slowly and tended to show stronger regularity effects. The results were consistent with the primary hypothesis that familiar word forms are read faster because they are processed at a larger grain-size, which requires fewer operations to achieve lexical selection. Results are discussed in terms of a neurobiological model of word recognition based on brain imaging studies.

• 한국콘텐츠학회논문지
• /
• 제21권2호
• /
• pp.130-139
• /
• 2021

본 연구에서는 매실에 가장 큰 피해를 주는 복숭아 씨살이좀벌의 방제 적기 안내를 위해 3D 영상을 활용한 매실 인식 및 크기 추정 프로그램을 통해 매실 크기를 예측하였다. 3차원 영상 측정이 가능한 Kinect 2.0 Camera 및 RealSense Depth Camera D415를 사용하여 야간 영상 촬영을 진행하였다. 획득한 영상을 토대로 MATLAB R2018a를 이용하여 영상 전처리, 크기 추정이 가능한 매실 추출, RGB 및 Depth 영상 정합 및 매실 크기 추정의 4단계로 구성된 매실 인식 및 추정 프로그램을 구현해 매실 성장 단계를 고려하여 2018년의 5개 영상 및 2019년의 5개의 영상을 분석하였다. 10개 영상에 대해 프로그램을 구동하여 얻은 결과를 통해 매실 인식률의 평균 61.9%, 매실 인식 오류율 평균 0.5% 및 크기 측정 오차율 평균 3.6%를 도출하였다. 이러한 매실 인식 및 크기 추정 프로그램의 지속적인 개발은 향후 정확한 열매 크기 모니터링 및 복숭아 씨살이좀벌의 적기 방제 시스템 개발을 가능하게 할 것으로 예상한다.

• 한국정보통신학회논문지
• /
• 제20권6호
• /
• pp.1209-1214
• /
• 2016

자동차 번호판 인식은 대중적인 감시 기술 중의 한 종류로서, 주어진 비디오나 영상 내 광학문자 인식을 수반한다. 번호판 인식은 자동차 번호판 국부화, 번호판의 크기, 차원, 명암대비, 밝기를 조정하는 정규화, 개별문자를 얻어내는 문자 분할, 문자를 인식하는 광학 문자 인식, 번호판의 형태, 크기, 위치 들이 연도별, 지역별로 차이가 있는 번호판들의 데이터베이스를 비교하여 구문 분석을 하는 절차를 거친다. 본 논문에서는 EmguCV를 이용하여 구현한 번호판 감지를 수행하여 위치를 찾아내고, 오픈 소스 광학 문자 인식 엔진으로 잘 알려져 있는 테서렉트 OCR을 이용하여 번호판의 문자를 인식하는 자동 인식 프로그램을 구현하고 번호판의 촬영 각도, 크기, 밝기에 대한 성능평가 결과에 관해 기술하였다.

• 전자공학회논문지CI
• /
• 제47권1호
• /
• pp.152-159
• /
• 2010

본 논문에서는 기울어진 문자, 다양한 크기, 글씨체, 흐린 문자를 포함한 입력영상의 문자 복원과 인식, 효율적인 도서 검색을 위한 광학문자인식 알고리즘을 제안한다. 본 논문에서 제안한 광학문자 인식알고리즘은 검출부와 인식부로 구성되며, 검출부에서는 복잡한 배경에서 정확한 도서 영역 검출을 위하여 로버츠 에지 연산자와 허도로프 거리 알고리즘을 적용하여 필요한 영역을 검출하였다. 또한 인식부에서는 문자의 크기와 경사도, 부분 손실 등의 영상에 강인성을 갖는 바이큐빅 보간법을 적용하여 데이터 손실 복원과, 반자동 기울기를 갖는 입력 영상의 보정을 하였다. 모의실험 결과 기존 알고리즘 보다 인식률에서는 6%, 검색시간에서는 1.077초 더 우수함을 확인하였다.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.445-458
• /
• 2012

Image feature extraction is one of the basic works for biometric analysis. This paper presents the novel concept of application of ridgelets for iris recognition systems. Ridgelet transforms are the combination of Radon transforms and Wavelet transforms. They are suitable for extracting the abundantly present textural data that is in an iris. The technique proposed here uses the ridgelets to form an iris signature and to represent the iris. This paper contributes towards creating an improved iris recognition system. There is a reduction in the feature vector size, which is 1X4 in size. The False Acceptance Rate (FAR) and False Rejection Rate (FRR) were also reduced and the accuracy increased. The proposed method also avoids the iris normalization process that is traditionally used in iris recognition systems. Experimental results indicate that the proposed method achieves an accuracy of 99.82%, 0.1309% FAR, and 0.0434% FRR.

• 반도체디스플레이기술학회지
• /
• 제17권2호
• /
• pp.41-46
• /
• 2018

This paper proposes a new method for the number recognition on dot matrix LED display. The proposed method uses morphological processing that dilates dots of numbers and connects the dots into strokes. The size of numbers is normalized using horizontal projection because the gaps of dots are different according to the size of numbers. The numbers are segmented by connected component analysis and finally, template matching method recognizes the segmented numbers. The proposed method is implemented using C language in Raspberry Pi system with a camera module for a real-time image processing. Experiments were conducted by using various dot matrix LED displays. The results show that the proposed method is successful for the number recognition on dot matrix LED display.

• 한국음향학회지
• /
• 제6권4호
• /
• pp.21-30
• /
• 1987

단어음성인식에서 발성속도의 차이에 따른 단어음성 길이의 비선형적 변화는 정확한 인식을 어렵게 하는 주요한 원인이 되어 왔다. DP매칭은 시간축의 비선형 신축에 의해 시간정규화를 행함으로써 인식결과에 대한 신뢰성을 상당히 높였으나 시간정규화 파정에 요구되는 과도한 계산부담이 문제로 되어 있다. 본 논문에서는 시간정규화가 필요없는 방법으로 멀티섹션벡터양자화에 새로운 길이정규화법을 적용하는 방법을 제안한다. 이 방법은 종래의 고정프레임 길이정규화에 의해 멀티섹션코드북을 작성할 때보다. 정규화길이의 실정에 훨씬 융통성을 가질 수 있으므로 분석 및 거리계산의 양면에서 시간 단축을 가능케 하여 좀더 신속히 인식결과를 얻을 수 있는 장점이 있다

• 전자공학회논문지B
• /
• 제29B권10호
• /
• pp.69-77
• /
• 1992

Pattern Recognition is one of the fundamental areas of computer vision. The recognition of patterns with varying size and severe defects is especially important. However, it is known that the conventional algorithms such as GHT or structural approaches have limitations in speed and accuracy. In this paper, in order to avoid above-mentioned problems, we propose a new recognition algorithm which exploits the histogram of contour directions and the sampled spot matching method. While the former provides little influence against size variation, the latter has strong immunity to noise and defects. We applied those proposed algorithms for the recognition of numbers extracted from the car number plates and shapes of aircraft. Experimental result shows that it is possible to solve above-mentioned problems by complementary uses of those two suggested algorithms. The contour directional histogram method resulted in high-speed of average 0.013 sec/char and 0.1 sec/aircraft-image on IBM-386. The accuracy of recognition is as high as 99%. Sampled spot matching method has less speed than the former one, however, it showed fairly strong immunity to noise and defects.

• 전자공학회논문지B
• /
• 제30B권2호
• /
• pp.69-77
• /
• 1993

Automatic image recognition system is essential for a better man-to machine interaction. Because of the noise and deformation due to the sensor operation, it is not simple to build an image recognition system even for the fixed images. In this paper neural network which has been reported to be adequate for pattern recognition task is applied to the fixed and variational(rotation, size, position variation for the fixed image)recognition with a hope that the problems of conventional pattern recognition techniques are overcome. At fixed image recognition system. ART model is trained with face images obtained by camera. When recognizing an matching score. In the test when wigilance level 0.6 - 0.8 the system has achievel 100% correct face recognition rate. In the variational image recognition system, 65 invariant moment features sets are taken from thirteen persons. 39 data are taken to train multi-layer perceptron and other 26 data used for testing. The result shows 92.5% recognition rate.