• Journal of the Optical Society of Korea
• /
• v.15 no.1
• /
• pp.15-21
• /
• 2011

This paper proposes a new approach to palmprint verification based on the gradient, in which a palm image is considered to be a three-dimensional terrain. Principal lines and wrinkles make deep and shallow valleys on a palm landscape. Then the steepest slope direction in each local area is first computed using the Kirsch operator, after which an orientation map is created that represents the dominant slope direction of each pixel. In this study, three orientation maps were made with different scales to represent local and global gradient information. Next, feature matching based on pixel-unit comparison was performed. The experimental results showed that the proposed method is superior to several state-of-the-art methods. In addition, the verification could be greatly improved by fusing orientation maps with different scales.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• Journal of the Optical Society of Korea
• /
• v.16 no.4
• /
• pp.372-380
• /
• 2012

The optical method Digital Speckle Correlation Measurement (DSCM) has been extensively applied due its capability to measure the entire displacement field over a body surface. A formula of displacement measurement errors by the gradient-based DSCM method was derived. The errors were found to explicitly relate to the image grayscale errors consisting of sub-pixel interpolation algorithm errors, image noise, and subset deformation mismatch at each point of the subset. A power-law dependence of the standard deviation of displacement measurement errors on the subset size was established when the subset deformation was rigid body translation and random image noise was dominant and it was confirmed by both the numerical and experimental results. In a gradient-based algorithm the basic assumption is rigid body translation of the interrogated subsets, however, this is in contradiction to the real circumstances where strains exist. Numerical and experimental results also indicated that, subset shape function mismatch was dominant when the order of the assumed subset shape function was lower than that of the actual subset deformation field and the power-law dependence clearly broke down. The power-law relationship further leads to a simple criterion for choosing a suitable subset size, image quality, sub-pixel algorithm, and subset shape function for DSCM.

• Journal of Digital Contents Society
• /
• v.4 no.2
• /
• pp.211-221
• /
• 2003

The objective of this paper is performance analysis of the digital document image decimation algorithm which generates a value of decimated element by an average of a target pixel value and a value of neighbor intelligible element to adaptively reflect the merits of ZOD method and FOD method on the decimated image. First, a target pixel located at the center of sliding window is selected, then the gradient amplitudes of its right neighbor pixel and its lower neighbor pixel are calculated using first order derivative operator respectively. Secondly, each gradient amplitude is divided by the summation result of two gradient amplitudes to generate each local intelligible weight. Next, a value of neighbor intelligible element is obtained by adding a value of the right neighbor pixel times its local intelligible weight to a value of the lower neighbor pixel times its intelligible weight. The decimated image can be acquired by applying the process repetitively to all pixels in input image which generates the value of decimated element by calculating the average of the target pixel value and the value of neighbor intelligible element. In this paper, the performance comparison of proposed method and conventional methods in terms of subjective performance and hardware complexity is analyzed and the preferable approach for developing the decimation algorithm of the digital document image on the basis of this analysis result has been reviewed.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.108-113
• /
• 2018

In this study, we introduce a new image gradient computation based on understanding of image generation. Most images consist of groups of pixels with similar color information because the images are generally obtained by taking a picture of the real world. The general gradient operator for an image compares only the neighboring pixels and cannot obtain information about a wide area, and there is a risk of falling into a local minimum problem. Therefore, it is necessary to attempt to introduce the gradient operator of the interval concept. We present a bow-tie gradient by color values of pixels on bow-tie region of a given pixel. To confirm the superiority of our study, we applied our bow-tie gradient to image segmentation algorithms for various images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.66-72
• /
• 2014

Histogram of oriented gradient (HOG) feature is widely used in vision-based pedestrian detection. The interpolation is the most important technique in HOG feature calculation to provide high detection rate. In interpolation technique of HOG feature calculation, two nearest orientation bins to gradient orientation for each pixel and the corresponding weights are required. In this paper, therefore, an efficient gradient orientation bin and weight calculation circuit for HOG feature is proposed. In the proposed circuit, pre-calculated values are defined in tables to avoid the operations of tangent function and division, and the size of tables is minimized by utilizing the characteristics of tangent function and weights for each gradient orientation. Pipeline architecture is adopted to the proposed circuit to accelerate the processing speed, and orientation bins and the corresponding weights for each pixel are calculated in two clock cycles by applying efficient coarse and fine search schemes. Since the proposed circuit calculates gradient orientation for each pixel with the interval of $1^{\circ}$ and determines both orientation bins and weights required in interpolation technique, it can be utilized in HOG feature calculation to support interpolation technique to provide high detection rate.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.575-591
• /
• 2013

Most of the edge detection methods available in literature are gradient based, which further apply thresholding, to find the final edge map in an image. In this paper, we propose a novel method that is based on fuzzy logic for edge detection in gray images without using the gradient and thresholding. Fuzzy logic is a mathematical logic that attempts to solve problems by assigning values to an imprecise spectrum of data in order to arrive at the most accurate conclusion possible. Here, the fuzzy logic is used to conclude whether a pixel is an edge pixel or not. The proposed technique begins by fuzzifying the gray values of a pixel into two fuzzy variables, namely the black and the white. Fuzzy rules are defined to find the edge pixels in the fuzzified image. The resultant edge map may contain some extraneous edges, which are further removed from the edge map by separately examining the intermediate intensity range pixels. Finally, the edge map is improved by finding some left out edge pixels by defining a new membership function for the pixels that have their entire 8-neighbourhood pixels classified as white. We have compared our proposed method with some of the existing standard edge detector operators that are available in the literature on image processing. The quantitative analysis of the proposed method is given in terms of entropy value.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.59-67
• /
• 2012

In this paper, an efficient interpolation scheme using gradient information between adjacent pixel values was proposed to estimate the value of interpolated pixel to have the locality which exists in real image and the characteristic of simple convex surface and simple concave surface which exist partially in the real image. PSNR(Peak Signal to Noise Ratio) was used to evaluate the performance of the proposed scheme. The PSNR values of the magnified images using the proposed scheme are greater than those of the magnified images using the previous interpolation schemes.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.155-160
• /
• 2004

In this paper, we describe the results of a study on the edge enhancement of X-ray images by using their fuzzy system representation. A set of gray scale X-ray images was generated using the EGS4 computer code. An aluminum plate or a lead plate with three parallel strips taken out has been used as the object with the thickness and the width of the plate, and the gap between the two strips varied. We started with a comparative study on a set of the fuzzy sets for their applicability as the input fuzzy sets for the fuzzy system representation of the gray scale images. Then we describe how the fuzzy system is used to sharpen the edges. Our algorithm is based on adding the magnitude of the gradient not to the pixel value of concern but rather to the nearest neighboring pixel in the direction of the gradient. We show that this algorithm is better in maintaining the spatial resolution of the original image after the edge enhancement.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.772-775
• /
• 2006

Muilti-dimensional feature vector matching algorithm uses multiple features such as intensity, gradient, variance, first or second derivative of a pixel to find correspondence pixels in stereo images. In this paper, we proposed a new method for adjusting automatically the weight of feature in multi-dimensional feature vector matching considering sharpeness of a pixel in feature vector distance curve. The sharpeness consists of minimum and maximum vector distances of a small window mask. In the experiment we used IKONOS satellite stereo imagery and obtained accurate matching results comparable to the manual weight-adjusting method.