• 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 Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.332-335
• /
• 2013

In this paper, we propose an image retrieval method using an EHD (Edge Histogram Descriptor) of MPEG-7 and the color histogram. The EHD algorithm can be used to collect the gradient of edge distribution and to find a similar image. However, if you only search the edge gradient without considering the image color, the color shows a weakness. In order to overcome this problem, we use the color histogram and extract the feature to determine whether a similar image. The proposed method shows that the weakness of existing EHD can be overcome by using the color histogram.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.355-366
• /
• 2002

The web is one of the most plentiful sources of images. The web has an immediate need for image processing technology in Java. This paper provides a practical introduction to statistical image processing using Java on the web. The paper describes how images are represented in Java and deals with four image processing operations based on basic statistical methods: point processing, spatial filtering, edge detection and image segmentation.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.195-203
• /
• 2022

Noise generated during image acquisition and transmission can negatively impact the results of image processing applications, and noise removal is typically a part of image preprocessing. Denoising techniques combined with nonlocal techniques have received significant attention in recent years, owing to the development of sophisticated hardware and image processing algorithms, much attention has been paid to; however, this approach is relatively poor for edge preservation of fine image details. To address this limitation, the current study combined a steering kernel technique with adaptive masks that can adjust the size according to the noise intensity of an image. The algorithm sets the steering weight based on a similarity comparison, allowing it to respond to edge components more effectively. The proposed algorithm was compared with existing denoising algorithms using quantitative evaluation and enlarged images. The proposed algorithm exhibited good general denoising performance and better performance in edge area processing than existing non-local techniques.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.1
• /
• pp.61-69
• /
• 2009

By the advent of the high resolution satellite imagery, a ground-coverage included by a single satellite image is decreased. By the reason, there are increasing needs in image mosaicking technology to use images to various GIS fields. This paper describes an edge-based seamline extraction algorithm using edge information such as rivers, roads, buildings for image mosaicking. For this, we developed a method to track and link discontinuous edges extracted by edge detection operator. To estimate the effectiveness of the proposed algorithm, we applied the algorithm to IKONOS, KOMPSAT-1 and SPOT-5 satellite images. The experimental results showed that the algorithm successfully dealts with discontinuities caused by geometric differences in two images.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.6
• /
• pp.1419-1427
• /
• 2007

In this paper, we propose an algorithm which implements a multi-sided side match finite-state vector quantization(MSMVQ). After extracting the edge information from an image and classifying the image into edge blocks or non-edge blocks, we construct an edge map. We subdivide edge blocks into sixteen classes using discrete cosine transform(DCT) AC coefficients. Based on edge map information, a state codebook is made from the master codebook, and side match calculation is done for two-sided or three-sided current block of image. For reducing transmitted bits, a decision is made whether or not to encode the non-edge blocks among the pre-coded blocks by using the master codebook. Also for reducing allocation bits of codeword indices to decoder, a variable length coder is used. Considering the comparison with side match finite-state vector quantization(SMVQ) and two-sided SMVQ(TSMVQ) algorithm about Zelda, Lenna, Bridge and Peppers image, the new algorithm shows better picture quality than SMVQ and TSMVQ respectively.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1129-1144
• /
• 2020

The thangka image inpainting method based on wavelet transform is not ideal for contour curves when the high frequency information is repaired. In order to solve the problem, a new image inpainting algorithm is proposed based on edge structural constraints and wavelet transform coefficients. Firstly, a damaged thangka image is decomposed into low frequency subgraphs and high frequency subgraphs with different resolutions using wavelet transform. Then, the improved fast marching method is used to repair the low frequency subgraphs which represent structural information of the image. At the same time, for the high frequency subgraphs which represent textural information of the image, the extracted and repaired edge contour information is used to constrain structure inpainting in the proposed algorithm. Finally, the texture part is repaired using texture synthesis based on the wavelet coefficient characteristic of each subgraph. In this paper, the improved method is compared with the existing three methods. It is found that the improved method is superior to them in inpainting accuracy, especially in the case of contour curve. The experimental results show that the hierarchical method combined with structural constraints has a good effect on the edge damage of thangka images.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.201-205
• /
• 2004

The digital color image can be distorted by noise for a transmission or other elements of system. It happens to vague of a boundary side in the division of a color image object, especially, boundary side of an input color image is very important because it can be determined to the division and detection element in pattern recognition. Therefore it is boundary part In this paper, it detects the optimal edge with applying this color image to WCNN algorithm, after it does level up a boundary side of a color image by using the adaptive morphology as the threshold of an input color image. Also, it is used not a conventional fixed mask edge detection method but variable mask method which is cal led a variable BBM. It is confirmed by simulation that the proposed algorithm can be got the batter result edge at the place of closing to each edges and having smoothly curved line.

• Journal of Korea Multimedia Society
• /
• v.8 no.12
• /
• pp.1565-1571
• /
• 2005

Images reconstructed with Maximum-Likelihood Expectation-Maximization (MLEM) algorithm have been observed to have checkerboard effects and have noise artifacts near edges as iterations proceed. To compensate this ill-posed nature, numerous penalized maximum-likelihood methods have been proposed. We suggest a simple algorithm of applying edge detecting process to the MLEM and Bayesian Expectation-Maximization (BEM) to reduce the noise artifacts near edges and remove checkerboard effects. We have shown by simulation that this algorithm removes checkerboard effects and improves the clarity of the reconstructed image and has good properties based on root mean square error (RMS).

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.6
• /
• pp.71-80
• /
• 1994

The purpose of this paper is to explore the use of fuzzy set theory for image processing and analysis. As an application example, the fuzzy method of edge detection is proposed to extract the edges of raised characters on tires.In general, Sobel, Prewitt, Robert and LoG filters are used to detect the edge, but it is difficult to detect the edge because of ambiguity of representations, noise and general problems in the interpretation of tire image. Therefore, in his paper, the fuzzy property plane has been extracted from the spatial domain using the ramp-mapping function. And then the ideas of fuzzy MIN and MAX are applied in removing noise and enhancement of the image simultaneously. From the result of MIN and MAX procedure a new fuzzy singleton is generated by extracting the difference between adjacent membership function values. And the edges are extracted by applying fuzzy $\alpha$-cut set to the fuzzy singletion, Finally, these ideas are applied to the tire images.