• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.329-332
• /
• 2009

Speckle noise reduction for ultrasound CT image using morphological adaptive median filtering based on edge preservation is presented in this paper. Speckle noise is multiplicative feature and causes ultrasound image to degrade widely from transducer. An input image is classified into edge region and homogeneous region in preprocessing. The speckle is reduced by morphological operation on the 2D gray scale by using convolution and correlation, and edges are preserved. The adaptive median is processed to reduce an impulse noise. As the result the proposed method enhances the image to about 20% in comparison with Winer filter by Edge Preservation Index and PSNR.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• Korean Journal of Cognitive Science
• /
• v.11 no.2
• /
• pp.53-58
• /
• 2000

This paper reconstructs local region of a facial expression image from extracted feature points of facial expression image using FCM(Fuzzy C-Meang) clustering algorithm with Gabor wavelets. The feature extraction in a face is two steps. In the first step, we accomplish the edge extraction of main components of face using average value of 2-D Gabor wavelets coefficient histogram of image and in the next step, extract final feature points from the extracted edge information using FCM clustering algorithm. This study presents that the principal components of facial expression images can be reconstructed with only a few feature points extracted from FCM clustering algorithm. It can also be applied to objects recognition as well as facial expressions recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1492-1494
• /
• 1987

This paper describes a hardware architecture called Edge Painting Machine for real time generation of scan line images for raster scan graphics display. The Edge Painting Machine consists of Scanline Processor which converts polygon data sorted in their depth priority into a set of scan line commands for each scan line, and Edge Painting Tree which converts the scanline commands set into a raster line image. Edge painting tree has been designed using combinational logic circuit. The designed circuit has been simulated to verify the proper functioning. A salient feature of the EPT is that hardware composition is simple, because each processor is constituted by only combinational logic circuit.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.8
• /
• pp.1247-1256
• /
• 1989

In this paper, we propose the dynamic scene segmentation algorithm using a cross mask and edge information. This method, a combination of the conventioanl feature-based and pixel-based approaches, uses edges as features and determines moving pixels, with a cross mask centered on each edge pixel, by computing similarity measure between two consecutive image frames. With simple calcualtion the proposed method works well for image consisting of complex background or several moving objects. Also this method works satisfactorily in case of rotaitional motion.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1214-1218
• /
• 2006

This paper presents method to speed up processing time in construction of panoramic images. The method based on invariant feature uses image down-scaling and image edge information. Reducing image size and applying feature descriptor to image portions superimposed with edge causes to reduce the number of features and to improve processing speed. In the experiments, it was shown that the proposed method was 3.26$\sim$13.87% shorter in processing time than the exiting method fer 24-bit color images of 640$\times$480 size.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2213-2216
• /
• 2003

In this paper, we propose the face identification method which is robust for lighting based on the feature points method. First of all, the proposed method extracts an edge of facial feature. Then, by the hough transform, it determines ellipse parameters of each facial feature from the extracted edge. Finally, proposed method performs the face identification by using parameters. Even if face image is taken under various lighting condition, it is easy to extract the facial feature edge. Moreover, it is possible to extract a subject even if the object has not appeared enough because this method extracts approximately the parameters by the hough transformation. Therefore, proposed method is robust for the lighting condition compared with conventional method. In order to show the effectiveness of the proposed method, computer simulations are done by using the real images.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1991.10a
• /
• pp.77-80
• /
• 1991

This paper proposes a new feature extraction method which is effectively used in character recognition, and validate the effectiveness through various computational methods for similiarity degree. To get feature vectors used in this method, Hough transform is applied to character image, which is used for edge extraction in image processing. By that transformation technique, strokes could be extracted and feature vectors constructed suitably. The characteristic of this method is solving the difficulties in stroke extraction through transform space analysis, which is induced by noise and blurring, and representing high recognition rate 99.3% within 10 candidates in relative low dimension.