잡음이 있고 흐릿한 영상의 블라인드 디컨벌루션을 위한 유전 프로그래밍 기법

( Muhammad Tariq Mahmood†? ),추연호 ( Yeon Ho Chu ),최영규 ( Young Kyu Choi ) 한국정보처리학회 2014 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.3 No.1

영상의 디컨벌루션은 보통 감시 시스템에서 모션 블러 (motion blur)나 초점이 맞지 않아 발생하는 블러 (out-of-focus blur) 문제를 줄이기 위해 전처리 과정에서 사용된다. 본 논문에서는 유전 프로그래밍 (Genetic Programming, GP)에 기반한 새로운 블라인드 영상 디컨벌루션 필터 링 방법을 제안한다. GP 진화 과정을 통해 영상 복원을 위한 수학적 표현이 만들어지는데, 이것은 블러 영상의 특징들 사이의 관계를 최적으로 조합하여 원래 화소 값을 복원할 수 있는 추정자 함수가 된다. 이를 위해, 먼저 각 화소의 작은 이웃으로부터 특징 벡터를 만들고 추정자 함수를 학습시키는데, 이러한 GP 진화 과정을 통해 지정한 적합성 기준에 따라 유용한 정보들이 자동으로 조합된다. 개발된 함수는 훼손된 영상의 각 화소에 적용하여 원래의 화소 값을 복원하게 된다. 개발된 함수는 다양한 방법으로 훼손된 영상에 적용하여 실험하였는데, 실험 결과 제안 된 방법이 기존 알고리즘에 비해 좋은 결과를 나타내는 것을 알 수 있었다. Usually, image deconvolution is applied as a preprocessing step in surveillance systems to reduce the effect of motion or out-of-focus blur problem. In this paper, we propose a blind-image deconvolution filtering approach based on genetic programming (GP). A numerical expression is developed using GP process for image restoration which optimally combines and exploits dependencies among features of the blurred image. In order to develop such function, first, a set of feature vectors is formed by considering a small neighborhood around each pixel. At second stage, the estimator is trained and developed through GP process that automatically selects and combines the useful feature information under a fitness criterion. The developed function is then applied to estimate the image pixel intensity of the degraded image. The performance of developed function is estimated using various degraded image sequences. Our comparative analysis highlights the effectiveness of the proposed filter.

3차원 형상 복원을 위한 수학적 모폴로지 기반의 초점 측도 기법

( Muhammad Tariq Mahmood ),최영규 ( Young Kyu Choi ) 한국정보처리학회 2017 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.6 No.1

Shape from focus (SFF) 기법은 카메라 렌즈를 다양한 초점 거리로 놓고 촬영한 영상을 이용해 물체의 3차원 정보를 추출하는 방법이다. 이 논문에서는 미소 객체(microscopic object)의 3차원 깊이 정보를 추출하기 위해 수학적 모폴로지의 기울기 연산자를 이용하는 새로운 SFF 방법을 제안한다. 전통적으로 SFF 기법에서는 초점의 품질을 측정하기 위해 하나의 초점 측도(focus measure)를 사용한다. 그러나 미소 객체의 복잡한 형태와 텍스쳐 특성에 따라 하나의 초점 측도만을 사용하는 것은 충분하지가 않은데, 본 논문에서는 향상된 초점 측도를 위해 다수의 형태소(multi-structuring elements)를 사용하는 모폴로지 연산자를 사용하는 방법을 제안한다. 최종적으로 모든 초점 측도 결과를 통합하여 최적의 깊이 맵을 계산하게 된다. 실험을 통해 제안된 알고리즘이 기존의 방법들에 비해 3차원 형상 복원 측면에서 더 정밀한 깊이 맵을 제공하는 것을 알 수 있었다. Shape from focus (SFF) is a technique used to reconstruct 3D shape of objects from a sequence of images obtained at different focus settings of the lens. In this paper, a new shape from focus method for 3D reconstruction of microscopic objects is described, which is based on gradient operator in Mathematical Morphology. Conventionally, in SFF methods, a single focus measure is used for measuring the focus quality. Due to the complex shape and texture of microscopic objects, single measure based operators are not sufficient, so we propose morphological operators with multi-structuring elements for computing the focus values. Finally, an optimal focus measure is obtained by combining the response of all focus measures. The experimental results showed that the proposed algorithm has provided more accurate depth maps than the existing methods in terms of three-dimensional shape recovery.

Focus measure based on the energy of high-frequency components in the S transform.

Mahmood, Muhammad Tariq,Choi, Tae-Sun Optical Society of America 2010 Optics letters Vol.35 No.8

<P>Focus measure plays a fundamental role in the shape from focus technique. In this Letter, we suggest a focus measure in the S-transform domain that is based on the energy of high-frequency components. A localized spectrum by using variable window size provides a more accurate method of measuring image sharpness as compared to other focus measures proposed in spectral domains. An optimal focus measure is obtained by selecting an appropriate frequency-dependent window width. The performance of the proposed focus measure is compared with those of existing focus measures in terms of three-dimensional shape recovery. Experimental results demonstrate the effectiveness of the proposed focus measure.</P>

Cloud Computing and its Environmental Effects

Muhammad Arif,Tariq Mahmood 보안공학연구지원센터 2015 International Journal of Grid and Distributed Comp Vol.8 No.1

Cloud computing is providing basic level of computing facility to meet the daily needs of general or public community.in this paper we have selected the topic cloud computing and its environmental effects. Global warming, greenhouse effect, increasing temperature of the whole environment are major concerns regarding to rise in temperature and pollution of the environment of the whole world. No doubt cloud computing is providing basic facility of computing to general community but at the same time it is playing major role in increasing temperature of the whole world and becoming the source of pollution for the environment. In this paper different strategies have been adopted to control this problem. Virtualization technique is being utilized to control the problem of energy consumption and emission of carbon dioxide gas. So many techniques regarding to virtualization like live migration of VM, Dynamic Resource Allocation of different resources, virtualization of network resources like routers, routing protocols, virtualization of hardware resources like server, storage, memory and other devices. An effort is being exercised to reduce the problem of carbon emission and energy consumption of cloud computing to large extent.

Hybrid histogram matching for image registration

Muhammad Tariq Mahmood(무하마드 타릭 마무드),Ik Hyun Lee(이익현) 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.1

Blur Detection through Multinomial Logistic Regression based Adaptive Threshold

Mahmood, Muhammad Tariq,Siddiqui, Shahbaz Ahmed,Choi, Young Kyu The Korean Society Of SemiconductorDisplay Technol 2019 반도체디스플레이기술학회지 Vol.18 No.4

Blur detection and segmentation play vital role in many computer vision applications. Among various methods, local binary pattern based methods provide reasonable blur detection results. However, in conventional local binary pattern based methods, the blur map is computed by using a fixed threshold irrespective of the type and level of blur. It may not be suitable for images with variations in imaging conditions and blur. In this paper we propose an effective method based on local binary pattern with adaptive threshold for blur detection. The adaptive threshold is computed based on the model learned through the multinomial logistic regression. The performance of the proposed method is evaluated using different datasets. The comparative analysis not only demonstrates the effectiveness of the proposed method but also exhibits it superiority over the existing methods.

Rician noise reduction by combining mathematical morphological operators through genetic programming

Sharif, Muhammad,Jaffar, Muhammad Arfan,Mahmood, Muhammad Tariq Springer-Verlag 2013 Optical review Vol.20 No.4

수학적 모폴로지 연산자와 유전자 프로그래밍을 이용한 자기 공명 영상의 잡음 제거

무하마드 타릭 마흐무드(Muhammad Tariq Mahmood),최영규(Young Kyu Choi) 한국정보과학회 2013 정보과학회 컴퓨팅의 실제 논문지 Vol.19 No.9

수학적 모폴로지 연산자를 기반으로 하는 대부분의 복합 필터들은 미리 정해진 연산자의 조합을 사용하거나 연산자의 선형 조합을 이용하는데, 이에 따라 다양한 범위의 잡음 레벨에 대한 처리 성능이 제한을 받는다. 본 논문에서는 자기 공명 (Magnetic Resonance) 영상에 나타나는 잡음을 제거하기 위한 유전자 프로그래밍 기반의 새로운 방법을 제안한다. 제안된 방법은 적합도 조건을 바탕으로 그레이스케일 모폴로지 연산자를 수 세대 동안 조합하는 방법으로 최적의 복합 모폴로지 필터 FOCMSF를 만들게 되는데, 특히 잡음의 분산에 대한 어떤 사전 지식도 필요 없다는 장점이 있다. 실험을 위하여 시뮬레이션 된 데이터와 환자로부터 실제로 촬영한 MRI 데이터가 사용되었다. 실험을 통해 제안된 GP 기반 잡음 제거기법이 기존의 방법들에 비해 우수한 결과를 보이는 것을 알 수 있었다. Most of the composite filters based on mathematical morphological (MM) operators depend on a certain prefixed or a linear combination of MM operators that limits their performance in the diverse range of noise levels. We propose a Genetic Programming (GP) based approach for noise reduction from Magnetic Resonance Images (MRI). An Optimal Composite Morphological Supervised Filter FOCMSF is evolved through a certain number of generations by combining the gray-scale MM operators under a fitness criterion. The proposed method does not need any prior information about the noise variance. The improved performance of the developed filter is investigated using simulated and real MRI datasets. Comparative analysis demonstrates the superiority of the proposed GP based scheme over the existing approaches.

비 지역적 평균과 유도 영상 필터링에 기반한 자기 공명 영상의 잡음 제거

무하마드 타릭 마흐무드(Muhammad Tariq Mahmood),최영규(Young Kyu Choi) 한국정보과학회 2014 정보과학회 컴퓨팅의 실제 논문지 Vol.20 No.11

자기 공명 영상에서 흔히 발생하는 잡음을 없애기 위해 비 지역적 평균과 유도 영상 필터링을 이용하는 새로운 방법을 제안한다. 제안된 방법은 두 가지 단계로 구성되어 있다. 첫 단계에서는 비 지역적 평균 필터를 이용하여 잡음 영상으로부터 유도 영상 구하는데, 필터의 커널을 적응적으로 제어하기 위해 경계도(edgeness) 개념을 사용하였다. 두 번째 단계에서는 유도 영상 필터링으로 잡음을 제거하는 과정으로 원래의 잡음 영상과 앞 단계에서 구한 유도 영상을 이용하여 잡음이 제거된 영상을 복원한다. 제안된 방법의 우수성을 확인하기 위해 다양한 표준 자기 공명 영상 데이터를 이용하여 실험을 하였는데, 실험 결과 제안된 방법이 기존의 방법들에 비해 우수한 성능을 나타내는 것을 확인할 수 있었다. In this letter, we propose a noise reduction method for use in magnetic resonance images that is based on non-local mean and guided image filters. Our method consists of two phases. In the first phase, the guidance image is obtained from a noisy image by using an adaptive non-local mean filter. The spread of the kernel is adaptively by controlled by implementing the concept of edgeness. In the second phase, the noisy images and the guidance images are provided to the guided image filter as input in order to produce a noise-free image. The improved performance of the proposed method is investigated by conducting experiments on standard datasets that contain magnetic resonance images. The results show that the proposed scheme is superior over the existing approaches.

In vitro Callogenesis and Detection of Somaclonal Variations in Plantago ovata L.

Tariq Mahmood,Aysha Jameel,Bilal Haider Abbasi,Faiza Munir,Syed Muhammad Saqlan Naqvi 한국작물학회 2012 Journal of crop science and biotechnology Vol.15 No.4

Planago ovata L. is an economically important species in the monotypic genus Plantago. It is a short-stemmed annual herb. The seed husk of this plant is commonly called psyllium or isabgol which is important in pharmaceutical formulation and food industry. In this study, callus induction was optimized using different explants of Plantago ovata. Callus DNA was utilized to access the somaclonal variations using the Random Amplification of Polymorphic DNA (RAPD) markers. The maximum callus growth was observed in Murashige and Skoog (MS) medium containing 4 mg L-1 2,4-D concentration for shoots, 0.5 mg L-1 for seeds and 2 mg L-1for roots. Moreover, the effect of culture age was considered in assessing genetic variability. Maximum genetic variability was observed in the DNA samples of callus at the concentration of 2 mg L-1 2,4-D for all explants (roots, shoots, and seeds). Cluster analysis was performed based on 1) similarity coefficient between samples and 2) molecular data using the Numerical Taxonomy and Multivariate Analysis System (NTSYS) PC version 2.01; similarity index was generated by similarity for Quantitative Data (SIMQUAL). Our study indicated that Random Amplified Polymorphic DNAs can successfully be used to explore polymorphism among callus samples at different hormonal concentrations. This study can be useful for the production of callus from Plantago ovata and estimation of genetic variations due to tissue culture conditions. Evaluation of genetic variations can display novel features and manipulate genetic bottlenecks in Plantago ovata. New genetic variations in somaclones can bring vital insight for plant improvement.