• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.435-442
• /
• 2018

This study implemented an FPGA-based system to extract PCB defect patterns. The FPGA-based system can perform pattern matching at high speed for vision automation. An image processing library that is used to extract defect patterns was also implemented in IPs to optimize the system. The IPs implemented are Camera Link IP, Histogram IP, VGA IP, Horizontal Projection IP and Vertical Projection IP. In terms of hardware, the FPGA chip from the Vertex-5 of Xilinx was used to receive and handle images that are sent from a digital camera. This system uses MicroBlaze CPU. The image results are sent to PC and displayed on a 7inch TFT-LCD and monitor.

• The Korean Journal of Applied Statistics
• /
• v.24 no.2
• /
• pp.359-371
• /
• 2011

Edge detection in images is an important step in image segmentation and object recognition as preprocessing for image processing. This paper presents a new edge detection using local histogram analysis based on wavelet transform. In this work, the wavelet transform uses three components (horizontal, vertical and diagonal) to find the magnitude of the gradient vector, instead of the conventional approach in which tw components are used. We compare the magnitude of the gradient vector with the threshold that is obtained from a local histogram analysis to conclude that an edge is present or not. Some experimental results for our edge detector with a Sobel, Canny, Scale Multiplication, and Mallat edge detectors on sample images are given and the performances of these edge detectors are compared in terms of quantitative and qualitative measures. Our detector performs better than the other wavelet-based detectors such as Scale Multiplication and Mallat detectors. Our edge detector also preserves a good performance even if the Sobel and Canny detector are sharply low when the images are highly corrupted.

• Korean Journal of Remote Sensing
• /
• v.23 no.2
• /
• pp.113-117
• /
• 2007

In this paper, we propose a new method for determining automatically the size of the matching window using histogram of the gradient in order to improve the performance of stereo matching using one-meter resolution satellite imagery. For each pixel, we generate Flatness Index Image by calculating the mean value of the vertical or horizontal intensity gradients of the 4-neighbors of every pixel in the entire image. The edge pixel has high flatness index value, while the non-edge pixel has low flatness index value. By using the histogram of the Flatness Index Image, we find a flatness threshold value to determine whether a pixel is edge pixel or non-edge pixel. If a pixel has higher flatness index value than the flatness threshold value, we classify the pixel into edge pixel, otherwise we classify the pixel into non-edge pixel. If the ratio of the number of non-edge pixels in initial matching window is low, then we consider the pixel to be in homogeneous region and enlarge the size of the matching window We repeat this process until the size of matching window reaches to a maximum size. In the experiment, we used IKONOS satellite stereo imagery and obtained more improved matching results than the matching method using fixed matching window size.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.431-433
• /
• 2007

In This paper, we present a texture clustering method to extract Container ISO code in complex images. First, we make texture informations using top-hat morphology from realtime images, and we cluster those informations using horizontal and vertical clustering method to extract text area. After extensive experiment, our method demonstrated superior performance against well-known techniques as texture and histogram method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.855-858
• /
• 2004

본 논문에서는 원영상 영역내 포함된 우성의 에지에 대한 구체적 정보를 이용하기 위하여 Haar 웨이블릿을 이용한 에지영상 추출한다. 추출된 에지영상에 얼굴영역을 검출하기위해 이진화된 영상에 설정된 임계값을 통하여 얻은 이진영상으로부터 얼굴영역을 검출하기 위하여 얼굴의 일반적인 구조적 정보와 처리시간이 빠른 수평, 수직히스토그램 분석법을 이용하였다. 얼굴영역을 분리한 영상에 얼굴영역의 특징벡터를 구하기 위하여 26개의 특징벡터를 사용한 효율적인 고차 국소 자동 상관함수를 사용하였다. 계산된 특징벡터는 BP 신경망의 학습을 통하여 얼굴인식을 위한 데이터로 사용하여 제안된 알고리즘에 의한 인식률향상과 속도 향상을 입증한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.225-230
• /
• 2008

In this paper we embody a system that recognizes printed alphabet, numeral figures and symbols written on the keyboard for the recognition of English sentences. The image of the printed sentences is inputted and binarized, and the characters are separated by using histogram method that is the same as the existing character recognition method. During the abstraction of the individual characters, we classify one group that has not numerical information by the projection of the vertical center of the character. In case of another group that has the longer width than the height, we assort them by normalizing the width. The other group normalizes the height of the images. With the reverse application of the basic principle of the Japanese Puzzle to a normalized character image, the proposed system classifies and recognizes the printed numeral figures, symbols and characters, consequently we meet with good result.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• The Journal of the Korea Contents Association
• /
• v.2 no.2
• /
• pp.17-26
• /
• 2002

In this paper, we suggest a method to acquire the moving object centered video by panning and tilting a camera automatically according to motion vectors calculated by detecting the motion of a moving object on video steam. We create a difference image by estimating the intensity difference at the grid points of neighboring frames. And we detect the motion using both horizontal projection histogram and vertical projection histogram and decide the center of motion part. Then we calculate a new direction and degree of the motion by comparing coordinates at the center of current motion and the center of previous motion. By controling the RCM using these Motion vectors, we can get video stream positioned unwire object on the center of video frame. Through the experiments, we could get a moving object centered video stream continuously arid monitor remotely by implementing sever/client architecture based on the web.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.333-342
• /
• 2005

This paper proposes a method, which recognizes student's identification card by using image processing and recognition technology and can manage student information on the web. The presented scheme sets up an average brightness as a threshold, based on the brightest Pixel and the least bright one for the source image of the ID card. It is converting to binary image, applies a horizontal histogram, and extracts student number through its location. And, it removes the noise of the student number region by the mode smoothing with 3$\times$3 mask. After removing noise from the student number region, each number is extracted using vertical histogram and normalized. Using the enhanced ART1 algorithm recognized the extracted student number region. In this study, we propose the enhanced ART1 algorithm different from the conventional ART1 algorithm by the dynamical establishment of the vigilance parameter. which shows a tolerance limit of unbalance between voluntary and stored patterns for clustering. The Experiment results showed that the recognition rate of the proposed ART1 algorithm was improved much more than that of the conventional ART1 algorithm. So, we develop an educational matters administration system by using the proposed recognition method of the student's identification card.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.