학술논문
다양한 조명하에서 웨이블렛 변환과 히스토그램 평활화를 이용한 개선된 물체인식
Improved Object Recognition using Wavelet Transform & Histogram Equalization in the variable illumination
Improved Object Recognition using Wavelet Transform & Histogram Equalization in the variable illumination
Document Type
Article
Author
Source
정보처리학회논문지D / The KIPS Transactions : Part D. Apr 30, 2006 13(2):287
Subject
Language
Korean
ISSN
1598-2866
Abstract
주성분 분석(Principal Component Analysis : PCA)은 물체 인식 기술에서 가장 효율적인 방법으로 인정되고 있으나 영상 크기의 제곱에 비례하여 계산량이 증가하고 조명의 변화에 따라 정확성이 떨어지는 문제점이 있다. 본 논문에서는 이러한 문제점을 해결하기 위해서 웨이블렛 변환(Wavelet Transform)과 히스토그램 평활화(Histogram Equalization)를 사용하였다. 계산량이 증가하는 문제는 웨이블렛 변환으로 낮은 해상도의 영상을 사용하여 해결하였다. 조명의 변화에 따라 정확성이 떨어지는 문제는 히스토그램 평활화를 사용하여 영상의 대조를 크게 하고 휘도치의 분포를 펼침으로써 해결하였다. 제안한 기법으로 실험한 결과 조명변화에 영향을 최소화하여 인식률이 향상되고, 웨이블렛 변환으로 처리할 영역을 줄여 처리 시간이 크게 단축됨을 보여 주었다.
There are two problems associated with the existing principal component analysis, which is regarded as the most effective in object recognition technology. First, it brings about an increase in the volume of calculations in proportion to the square of image size. Second, it gives rise to a decrease in accuracy according to illumination changes. In order to solve these problems, this paper proposes wavelet transformation and histogram equalization. Wavelet transformation solves the first problem by using the images of low resolution. To solve the second problem, the histogram equalization enlarges the contrast of images and widens the distribution of brightness values. The proposed technology improves recognition rate by minimizing the effect of illumination change. It also speeds up the processing and reduces its area by wavelet transformation.
There are two problems associated with the existing principal component analysis, which is regarded as the most effective in object recognition technology. First, it brings about an increase in the volume of calculations in proportion to the square of image size. Second, it gives rise to a decrease in accuracy according to illumination changes. In order to solve these problems, this paper proposes wavelet transformation and histogram equalization. Wavelet transformation solves the first problem by using the images of low resolution. To solve the second problem, the histogram equalization enlarges the contrast of images and widens the distribution of brightness values. The proposed technology improves recognition rate by minimizing the effect of illumination change. It also speeds up the processing and reduces its area by wavelet transformation.