• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.131-138
• /
• 2018

This work describes a binary image based fast Difference of Gaussian (DoG) filter using zero-dimensional (0-d) convolution and state machine look up tables (LUTs) for image and video stitching hardware platforms. The proposed approach for using binary images to obtain DoG filtering can significantly reduce the data size compared to conventional gray scale based DoG filters, yet binary images still preserve the key features of the image such as contours, edges, and corners. Furthermore, the binary image based DoG filtering can be realized with zero-dimensional convolution and state machine LUTs which eliminates the major portion of the adder and multiplier blocks that are generally used in conventional DoG filter hardware engines. This enables fast computation time along with the data size reduction which can lead to compact and low power image and video stitching hardware blocks. The proposed DoG filter using binary images has been implemented with a FPGA (Altera DE2-115), and the results have been verified.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.1
• /
• pp.81-91
• /
• 1994

A DCT map and new cldebook design algorithm based on a two-dimension discrete cosine transform (2D-DCT) is presented for coder of image vector quantizer. We divide the image into smaller subblocks, then, using 2D DCT, separate it into blocks which are hard to code but it bears most of the visual information and easy to code but little visual information, and DCT map is made. According to this map, the significant features of training image are extracted by using the 2D DCT. A codebook is generated by partitioning the training set into a binary tree based on tree-structure. Each training vector at a nonterminal node of the binary tree is directed to one of the two descendants by comparing a single feature associated with that node to a threshold. Compared with the pairwise neighbor (PPN) and classified VQ(CVQ) algorithm, about 'Lenna' and 'Boat' image, the new algorithm results in a reduction in computation time and shows better picture quality with 0.45 dB and 0.33dB differences as to PNN, 0.05dB and 0.1dB differences as to CVQ respectively.

• Journal of the Semiconductor & Display Technology
• /
• v.8 no.2
• /
• pp.23-29
• /
• 2009

To increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, a new 2D barcode detection algorithm based on Local Binary Pattern is presented. To locate 2D barcode symbols, a texture analysis scheme based on the Local Binary Pattern is adopted, and a gray-scale projection with sub-pixel operation is utilized to separate the symbol precisely from the input image. Finally, the segmented symbol is normalized using the inverse perspective transformation for the decoding process. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments show that our method is very robust and efficient in detecting the symbol area for the various types of 2D barcodes.

• Journal of Biomedical Engineering Research
• /
• v.19 no.2
• /
• pp.199-210
• /
• 1998

In this paper, we present a 3D reconstruction method of color volume data for a computerized human atlas. Binary volume rendering which takes the advantages of object-order ray traversal and run-length encoding visualizes 3D organs at an interactive speed in a general PC without the help of specific hardwares. This rendering method improves the rendering speed by simplifying the determination of the pixel value of an intermediate depth image and applying newly developed normal vector calculation method. Moreover, we describe the 3D boundary encoding that reduces the involved data considerably without the penalty of image quality. The interactive speed of the binary rendering and the storage efficiency of 3D boundary encoding will accelerate the development of the PC-based human atlas.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.205-208
• /
• 2013

Generally, binary pattern transforms have been used in the field of the face recognition and facial expression, since they are robust to illumination. Thus, this paper proposes an illumination-robust face recognition system combining an MLDP, which improves the texture component of the LDP, and a 2D-PCA algorithm. Unlike that binary pattern transforms such as LBP and LDP were used to extract histogram features, the proposed method directly uses the MLDP image for feature extraction by 2D-PCA. The performance evaluation of proposed method was carried out using various algorithms such as PCA, 2D-PCA and Gabor wavelets-based LBP on Yale B and CMU-PIE databases which were constructed under varying lighting condition. From the experimental results, we confirmed that the proposed method showed the best recognition accuracy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.61-74
• /
• 2012

In this paper, we propose a illumination-robust face recognition system using MCS-LBP and 2D-PCA algorithm. A binary pattern transform which has been used in the field of the face recognition and facial expression, has a characteristic of robust to illumination. Thus, this paper propose MCS-LBP which is more robust to illumination than previous LBP, and face recognition system fusing 2D-PCA algorithm. The performance evaluation of proposed system was performed by using various binary pattern images and well-known face recognition features such as PCA, LDA, 2D-PCA and ULBP histogram of gabor images. In the process of performance evaluation, we used a YaleB face database, an extended YaleB face database, and a CMU-PIE face database that are constructed under varying lighting condition, and the proposed system which consists of MCS-LBP image and 2D-PCA feature show the best recognition accuracy.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.322-323
• /
• 2002

Partial volume averaging effect of PET data influences on the accuracy of quantitative measurements of regional brain metabolism because spatial resolution of PET is limited. The purpose of this study was to evaluate the accuracy of partial volume correction carried out on $^{18}$ F-PET images using Hoffman brain phantom. $^{18}$ F-PET Hoffman phantom images were co-registered to MR slices of the same phantom. All the MR slices of the phantom were then segmented to be binary images. Each of these binary images was convolved in 2 dimensions with the spatial resolution of the PET. The original PET images were then divided by the smoothed binary images in slice-by-slice, voxel-by-voxel basis resulting in larger PET image volume in size. This enlarged partial volume corrected PET image volume was multiplied by original binary image volume to exclude extracortical region. The evaluation of partial volume corrected PET image volume was performed by region of interests (ROI) analysis applying ROIs, which were drawn on cortical regions of the original MR image slices, to corrected and original PET image volume. From the ROI analysis, range of regional mean values increases of partial volume corrected PET images was 4 to 14%, and average increase for all the ROIs was about 10% in this phantom study. Hoffman brain phantom study was useful for the objective evaluation of the partial volume correction method. This MR-based correction method would be applicable to patients in the. quantitative analysis of FDG-PET studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.532-543
• /
• 2003

In this paper, we proposed structure of a reversible discrete-time cellular neural network (DTCNN) for labeling digital images to protect copylight. First, we present the concept and the structure of reversible DTCNN, which can be used to generate 2D binary pseudo-random images sequences. We presented some, output examples of different kinds of reversible DTCNNs to show their complex behaviors. Then both the original image and the copyright label, which is often another binary image, are used to generate a binary random key image. The key image is then used to scramble the original image. Since the reversibility of a reversible DTCNN, the same reversible DTCNN can recover the copyright label from a labeled image. Due to the high speed of a DTCNN chip, our method can be used to label image sequences, e.g., video sequences, in real time. Computer simulation results are presented.

• 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.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.