• Information and Communications Magazine
• /
• v.7 no.3
• /
• pp.27-34
• /
• 1990

The $(L,\psi)$ feature description on the binary boundary air craft image is introduced of classifying 3-D object (aircraft) identification. Three types for associative matrix memories are employed and tested for their classification performance. The fast association involved in these memories can be implemented using a parallel optical matrix-vector operation. Two associative memories are based on pseudoinverse solutions and the third one is interoduced as a paralell version of a nearest-neighbor classifier. Detailed simulation results for each associative processor are provided.

• Annual Conference of KIPS
• /
• 2003.11c
• /
• pp.1851-1854
• /
• 2003

본 논문에서는 영상의 인증과 무결성을 위한 새로운 블록 연성 워터마킹을 제안한다. 원 영상의 인증과 무결성을 확인하기 위하여 이진로고 영상을 워터마크로 사용한다. 원 영상의 각 픽셀의 정보뿐만 아니라 해당 블록의 정보로 binary look-up table을 선택하여 워터마크 비츠를 삽입한다. 기존 방식의 문제점으로 제시된 공격[6,7]을 효율적으로 막으면서도 시각적으로 변조유무 및 픽셀단위 또는 블록단위로 변조위치를 감지할 수 있음을 보인다.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.52 no.3
• /
• pp.113-120
• /
• 2003

Plasma display panels normally utilize the binary coded light emission scheme for gray scale expression. Subsequently, this expression method makes dynamic false contours. We propose the "E3DSM(enhanced 3-dimension scattering method)" that improved existing 3-d scattering method and the "HAM(histogram analysis method)" that is decided the driving schemes and subfield selections with histograms of images. Simulation results show the improving image quality.

• Journal of Korea Society of Industrial Information Systems
• /
• v.2 no.1
• /
• pp.73-87
• /
• 1997

Multilayer neural network using a modified beackpropagation learning algorithm was introduced to achieve automatic identification of different types of aircraft in a variety of 3-D orientations. A 3-D shape of an aircraft can be described by a library of 2-D images corresponding to the projected views of an aircraft. From each 2-D binary aircraft image we extracted 2-D invariant (L, Φ) feature vector to be used for training neural network aircraft classifier. Simulations concerning the neural network classification rate was compared using nearest-neighbor classfier (NNC) which has been widely served as a performance benchmark. And we also introduced reliability measure of the designed neural network classifier.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.329-332
• /
• 2000

영상 검색 기법 중 기존의 색상 정보만을 이용한 기법에는 많은 한계가 존재하기 때문에 현재의 검색 기법 혹은 상용 검색 프로그램들은 두가지 이상의 검색 기법을 동시에 이용한다. 본 논문에서는 이진 영상을 이용하여 형태 정보를 추출하고 색상 정보와의 결합을 이용한 검색 기법을 제안한다. 이진화된 영상만으로도 상당수의 형태 정보를 포함하고 있기 때문에 최소한의 계산을 이용하여 영상의 개략적인 형태를 파악할 수 있는 방법을 제안한다. 아울러, 이진화된 형태 정보로 자칫 놓칠 수 있는 형태 정보를 보완하기 위하여 영상 내의 객체의 위치 정보를 이용하기 위해 부분영상으로 영상을 분할하여 좀 더 효율적인 검색을 가능하게 하는 기법을 제안한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.474-485
• /
• 2001

This paper proposes a user-key-based fragile watermarking for detecting image modification. The embedding data in a form of binary image for authentication are inserted to the DCT coefficients of each block of the given image. To minimize possible exposure of being watermarked and the location of insertion, it is proposed to utilize a user-specific key in randomizing those information. Each DCT block hides one bit of data, all of which represent the user-specific authentication data. Experiments with 5 real images demonstrate that the proposed method not only detects whether there is modification or not, but also the actual location of modification with minimal visual deterioration. However, the proposed method has room for improvement against its loss of watermark by an attack of compression by more than 50%.

• Journal of Advanced Navigation Technology
• /
• v.11 no.1
• /
• pp.59-63
• /
• 2007

In this paper, an image segmentation algorithm is described to extract both the contour line and the inner grid patterns of body in case of ambiguous environment. The binary method using a threshold is used to extract image boundary. To reduce image noise, the $3{\times}3$ hybrid high pass filter adjusted for applying 3D information extraction of complicated shape object is proposed. This hybrid high pass filter algorithm can be applied to extract complicated shape object such as 3D body shape, CAD system, and factory automation since the processing time for image denoising is shorter than the conventional methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.255-258
• /
• 2003

Recently, Digital Watermarking is used to authenticate data and to determine whether the data are distorted or not in medical images which is digitalized. The Fourier Mellin method using the Fourier Transform and the Log-Polar coordinate transform gets an invariant feature for RST distortion in images. But there are several problems in the real materialization. Interpolation of the image value should be considered according to the pixel position and so a watermark loss, original image distortion, numerical approximation is happened. Therefore there should be solved to realization of the Fourier Mellin method. Using the Look up table, there reduce the data loss caused by the conversion between Rectangular and Polar coordinate. After diagnose, medical images are transformed the Polar coordinate and taken the Discrete Fourier transform in the center of ROI region. Maintaining the symmetry in Fourier magnitude coefficient, the gaussian distributed random vectors and binary images are embedded in medical images.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.4
• /
• pp.561-568
• /
• 2003

This paper suggests that watermarking technique make use of Threshold Values and PN code for preservation of copyright. To protect copyright, six binary images that are generated by a Dynamic Threshold Value to LSB(least significant bit) of wavelet coefficient through wavelet conversion and watermark image use PN code to each frequency sphere-HL1, LH1, HL2, LH2, HL3, LH3, decide coordinates, operate XOR, and insert watermark. They put the sphere except from low frequency which has much image deterioration and high frequency which has weak loss compression in watermark. As an experimental result, we acquired watermark inserting image that has little image deterioration and extract watermark strongly.