• 반도체디스플레이기술학회지
• /
• 제11권3호
• /
• pp.19-25
• /
• 2012

The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.

• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.49-56
• /
• 2011

In recent years, owing to the development of the image processing technology, the research to build control system using a vision sensor is stimulated. However, the time delay must be considered, because it works of time to get the result of an image processing in the system. It can be seen as an obstacle factor to real-time control. In this paper, using the pattern matching technique, the location of two objects is recognized from one image which was acquired by a camera. And it is implemented to a position control system as feedback data. Also, a possibility was shown to overcome a problem of time delay using PID controller. A number of experiments were done to show the validity of this study.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.60-67
• /
• 2020

Recently, artificial intelligence related technologies including machine learning are being applied to various fields, and the demand is also increasing. In particular, with the development of AR, VR, and MR technologies related to image processing, the utilization of computer vision based on deep learning has increased. The algorithms for object recognition and detection based on deep learning required for image processing are diversified and advanced. Accordingly, problems that were difficult to solve with the existing methodology were solved more simply and easily by using deep learning. This paper introduces various deep learning-based object recognition and extraction algorithms used to detect and recognize various objects in an image and analyzes the technologies that attract attention.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.108-112
• /
• 2021

Undesired reflection removal from an image captured through glass window is widely needed with the prevalence of camera. In this paper, we present and implement a reflection removal algorithm, which is specially designed for smart devices. Our implementation requires smart phone application to take two input pictures of the same target, one with flash light on and another with flash light off. Then, we find a flash spot in the picture, match the features to align the input pictures, transform the color space, and finally combine the pictures. As the result, we get a resulting image with removed reflection, achieving the visually pleasant.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.17-21
• /
• 2022

A variety of techniques have been proposed in the literature for depth improvement in depth from focus method. Unfortunately, these techniques over-smooth the depth maps over the regions of depth discontinuities. In this paper, we propose a robust technique for improving the depth map by employing a nonconvex smoothness function that preserves the depth edges. In addition, the proposed technique exploits the mutual structures between the depth map and a guidance map. This guidance map is designed by taking the mean of image intensities in the image sequence. The depth map is updated iteratively till the nonconvex objective function converges. Experiments performed on real complex image sequences revealed the effectiveness of the proposed technique.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• 반도체디스플레이기술학회지
• /
• 제23권1호
• /
• pp.56-60
• /
• 2024

In this paper, we propose a SIFT feature-based dynamic stitching algorithm for image calibration and correction of a 360-degree surround view system. The existing surround view system requires a lot of processing time and money because in the process of image calibration and correction. The traditional marker patterns are placed around the vehicle and correction is performed manually. Therefore, in this study, images captured with four fisheye cameras mounted on the surround view system were distorted and then matched with the same feature points in adjacent images through SIFT-based feature point extraction to enable image stitching without a fixed marker pattern.

• 전자공학회논문지
• /
• 제50권11호
• /
• pp.64-69
• /
• 2013

본 논문에서는 10-bit 해상도의 Two-Step Single-Slope A/D 변환기를 이용한 고속 CMOS Image Sensor(CIS)를 제안하였다. 제안하는 A/D 변환기는 5-bit coarse ADC 와 6-bit fine ADC 로 구성되어 있으며, 기존의 Single-Slope A/D 변환기보다 10배 이상의 변환속도를 나타내었다. 또한 고속 동작에서 적은 노이즈 특성을 갖기 위해 Digital Correlated Double Sampling(D-CDS) 회로를 제안하였다. 설계된 A/D 변환기는 0.13um 1-poly 4-metal CIS 공정으로 제작되었으며 QVGA($320{\times}240$)급 해상도를 갖는다. 제작된 칩의 유효면적은 $5mm{\times}3mm$ 이며 3.3V 전원전압에서 약 35mW의 전력소모를 나타내었다. 변환속도는 10us 이었으며, 프레임율은 220 frames/s으로 측정되었다.

• 방송과미디어
• /
• 제5권1호
• /
• pp.59-71
• /
• 2000

This paper presents a survey of the CMOs-based image sensor and its applications to various real field digital camera. CMOS image sensor, called active pixel sensor (APS), has many interesting properties such ash I회 sensitivity, high speed readout, random access and lower power consumption when it is compared with CCd. this paper also addresses the state-of-the-art of CMOS image sensor, and gives some examples of its application to digital camera and special-purpose cameras. with the advancement of semiconductor technology, CMOS image sensor is a future technology for imaging system, and will be widely used in the filed of image capturing for consumer electronics and scientific measurements.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.166-171
• /
• 2023

This paper presents the synaptic characteristics of IGZO memristors in neuromorphic computing, using MATLAB/Simulink and NeuroSim. In order to investigate the variations in the conductivity of IGZO memristor and the corresponding changes in the hidden layer, simulations are conducted by using the MNIST dataset. It was observed from simulation results that the recognition accuracy could be dependent on various parameters of IGZO memristor, along with the experimental exploration. Moreover, we identified optimal parameters to achieve high accuracy, showing an outstanding accuracy of 96.83% in image classification.