• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.176-181
• /
• 2023

During cancer treatment, the patient's response to drugs appears differently at the cellular level. In this paper, an image-based cell phenotypic feature quantification and key feature selection method are presented to predict the response of patient-derived cancer cells to a specific drug. In order to analyze the viability characteristics of cancer cells, high-definition microscope images in which cell nuclei are fluorescently stained are used, and individual-level cell analysis is performed. To this end, first, image stitching is performed for analysis of the same environment in units of the well plates, and uneven brightness due to the effects of illumination is adjusted based on the histogram. In order to automatically segment only the cell nucleus region, which is the region of interest, from the improved image, a superpixel-based segmentation technique is applied using the fluorescence expression level and morphological information. After extracting 242 types of features from the image through the segmented cell region information, only the features related to cell viability are selected through the ReliefF algorithm. The proposed method can be applied to cell image-based phenotypic screening to determine a patient's response to a drug.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1057-1068
• /
• 2022

본 논문은 모바일 기반의 실시간 영상 측위 기술 개발을 목표로 사용자가 촬영한 사진과 가상의 텍스쳐 영상 간의 매칭 가능성 확인 연구로 특징점 기반의 매칭 알고리즘의 조합 성능을 비교했다. 특징점 기반의 매칭 알고리즘은 특징점(feature)을 추출하는 과정과 추출된 특징점을 설명하는 서술자(descriptor)를 계산하는 과정, 최종적으로 서로 다른 영상에서 추출된 서술자를 매칭하고, 잘못 매칭된 특징점을 제거하는 과정으로 이루어진다. 이때 매칭 알고리즘 조합을 위해, 특징점을 추출하는 과정과 서술자를 계산하는 과정을 각각 같거나 다르게 조합하여 매칭 성능을 비교하였다. 가상 실내 텍스쳐 영상을 위해 V-World 3D 데스크탑을 활용하였다. 현재 V-World 3D 데스크톱에서는 수직·수평적 돌출부 및 함몰부와 같은 디테일이 보강되었다. 또한, 실제 영상 텍스쳐가 입혀진 레벨로 구축되어 있어, 이를 활용하여 가상 실내 텍스쳐 데이터를 기준영상으로 구성하고, 동일한 위치에서 직접 촬영하여 실험 데이터셋을 구성하였다. 데이터셋 구축 후, 매칭 알고리즘들로 매칭 성공률과 처리 시간을 측정하였고, 이를 바탕으로 매칭 성능 향상을 위해 매칭 알고리즘 조합을 결정하였다. 본 연구에서는 매칭 기법마다 가진 특장점을 기반으로 매칭 알고리즘을 조합하여 구축한 데이터셋에 적용해 적용 가능성을 확인하였고, 추가적으로 회전요소가 고려되었을 때의 성능 비교도 함께 수행하였다. 연구 결과, Scale Invariant Feature Transform (SIFT)의 feature와 descriptor 조합이 가장 매칭 성공률이 좋았지만 처리 소요 시간이 가장 큰 것을 확인할 수 있었고, Features from Accelerated Segment Test (FAST)의 feature와 Oriented FAST and Rotated BRIEF (ORB)의 descriptor 조합의 경우, SIFT-SIFT 조합과 유사한 매칭 성공률을 가지면서 처리 소요 시간도 우수하였다. 나아가, FAST-ORB의 경우, 10°의 회전이 데이터셋에 적용되었을 때에도 매칭 성능이 우세함을 확인하였다. 따라서 종합적으로 가상 텍스쳐 영상과 실영상간 매칭을 위해서 FAST-ORB 조합의 매칭 알고리즘이 적합한 것을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.1-10
• /
• 2020

The image analysis is an important and predominant task for classifying the different parts of the image. The analysis of complex image analysis like histopathological define a crucial factor in oncology due to its ability to help pathologists for interpretation of images and therefore various feature extraction techniques have been evolved from time to time for such analysis. Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis. The paper highlights how both techniques differ in feature extraction from complex images and discusses the potential pros and cons. The use of Convolution Neural Network (CNN) in image segmentation, detection and diagnosis of tumour, feature extraction is important but there are several challenges that need to be overcome before Deep Learning can be applied to digital pathology. The one being is the availability of sufficient training examples for medical image datasets, feature extraction from whole area of the image, ground truth localized annotations, adversarial effects of input representations and extremely large size of the digital pathological slides (in gigabytes).Even though formulating Histopathological Image Analysis (HIA) as Multi Instance Learning (MIL) problem is a remarkable step where histopathological image is divided into high resolution patches to make predictions for the patch and then combining them for overall slide predictions but it suffers from loss of contextual and spatial information. In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.

• 대한전자공학회논문지SP
• /
• 제42권4호
• /
• pp.119-126
• /
• 2005

본 논문에서는 영상의 블록 분류 특성에 적응적인 대표 컬러 히스토그램 (representative color histogram)과 방향성 패턴 히스토그램 (directional pattern histogram)을 이용한 새로운 내용 기반 영상 검색 방법 (content-based image retrieval)을 제안한다. 제안한 방법에서는 영상을 일정한 크기의 블록으로 나누고, 분할된 블록의 분류 특성에 따라 컬러와 패턴 특징 벡터를 추출한다. 먼저 분할된 블록을 채도 (saturation)에 따라 휘도 블록 또는 컬러 블록으로 분류한 후, 휘도 블록에 대해서는 블록 평균휘도 쌍의 히스토그램을 구하고, 컬러 블록에 대해서는 블록 평균 컬러 쌍 히스토그램을 구함으로써 블록 분류 특징에 따라 컬러 특징 벡터를 추출한다. 또한 블록 휘도 변화의 기울기 (gradient)를 계산하여 방향성 분류를 행한 후 히스토그램을 계산함으로써 블록 방향성 패턴 특징을 추출한다. 본 논문에서 제안한 영상 검색 방법의 성능을 평가하기 위해서 컴퓨터 모의실험을 행한 결과 제안한 방법이 기존의 방법들보다 정확도 (precision) 및 특징 벡터 차원 (feature vector dimension) 크기 등의 객관적인 측면에서 우수함을 확인하였다.

• Journal of information and communication convergence engineering
• /
• 제16권3호
• /
• pp.160-165
• /
• 2018

This paper designed and developed the image processing system of integrating feature extraction and matching by using convolutional neural network (CNN), rather than relying on the simple method of processing feature extraction and matching separately in the image processing of conventional image recognition system. To implement it, the proposed system enables CNN to operate and analyze the performance of conventional image processing system. This system extracts the features of an image using CNN and then learns them by the neural network. The proposed system showed 84% accuracy of recognition. The proposed system is a model of recognizing learned images by deep learning. Therefore, it can run in batch and work easily under any platform (including embedded platform) that can read all kinds of files anytime. Also, it does not require the implementing of feature extraction algorithm and matching algorithm therefore it can save time and it is efficient. As a result, it can be widely used as an image recognition program.

• 한국ITS학회 논문지
• /
• 제8권1호
• /
• pp.127-135
• /
• 2009

This paper presents a new technique for corner shape based object retrieval from a database. The proposed feature matrix consists of values obtained through a neighborhood operation of detected corners. This results in a significant small size feature matrix compared to the algorithms using color features and thus is computationally very efficient. The corners have been extracted by finding the intersections of the detected lines found using Hough transform. As the affine transformations preserve the co-linearity of points on a line and their intersection properties, the resulting corner features for image retrieval are robust to affine transformations. Furthermore, the corner features are invariant to noise. It is considered that the proposed algorithm will produce good results in combination with other algorithms in a way of incremental verification for similarity.

• Journal of Computing Science and Engineering
• /
• 제8권2호
• /
• pp.65-77
• /
• 2014

To address the problem of multi-target retrieval (MTR) of remote sensing images, this study proposes a new object-level feature representation model. The model provides an enhanced application image representation that improves the efficiency of MTR. Generating the model in our scheme includes processes, such as object-oriented image segmentation, feature parameter calculation, and symbolic image database construction. The proposed model uses the spatial representation method of the extended nine-direction lower-triangular (9DLT) matrix to combine spatial relationships among objects, and organizes the image features according to MPEG-7 standards. A similarity metric method is proposed that improves the precision of similarity retrieval. Our method provides a trade-off strategy that supports flexible matching on the target features, or the spatial relationship between the query target and the image database. We implement this retrieval framework on a dataset of remote sensing images. Experimental results show that the proposed model achieves competitive and high-retrieval precision.

• 정보통신설비학회논문지
• /
• 제9권2호
• /
• pp.73-79
• /
• 2010

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.

• Journal of information and communication convergence engineering
• /
• 제2권2호
• /
• pp.123-127
• /
• 2004

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.