• Journal of Biosystems Engineering
• /
• v.21 no.3
• /
• pp.315-324
• /
• 1996

This study was one of a series of studies on application of machine vision and image processing to extract the geometrical features of plants and to analyze plant growth. Several algorithms were developed to measure morphological properties of plants and describing the growth development of in-situ lettuce(Lactuca sativa L.). Canopy, centroid, leaf density and fractal dimension of plant were measured from a top viewed binary image. It was capable of identifying plants by a thinning top viewed image. Overlapping the thinning side viewed image with a side viewed binary image of plant was very effective to auto-detect meaningful nodes associated with canopy components such as stem, branch, petiole and leaf. And, plant height, stem diameter, number and angle of branches, and internode length and so on were analyzed by using meaningful nodes extracted from overlapped side viewed images. Canopy, leaf density and fractal dimension showed high relation with fresh weight or growth pattern of in-situ lettuces. It was concluded that machine vision system and image processing techniques are very useful in extracting geometrical features and monitoring plant growth, although interactive methods, for some applications, were required.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.329-335
• /
• 2010

Digital imaging detectors can use a variety of detection materials to convert X-ray radiation either to light or directly to electron charge. Many detectors such as amorphous silicon flat panels, CCDs, and CMOS photodiode arrays incorporate a scintillator screen to convert x-ray to light. The digital radiography systems based on semiconductor detectors, commonly referred to as flat panel detectors, are gaining popularity in the clinical & hospital. The X-ray detectors are described between a-Silicon based indirect type and a-Selenium based direct type. The DRS of detectors is used to convert the x-ray to electron hole pairs. Image processing is described by specific image features: Latitude compression, Contrast enhancement, Edge enhancement, Look up table, Noise suppression. The image features are tuned independently. The final enhancement result is a combination of all image features. The parameters are altered by using specific image features in the different several hospitals. The image in a radiological report consists of two image evaluation processes: Clinical image parameters and MTF is a descriptor of the spatial resolution of a digital imaging system. We used the edge test phantom and exposure procedure described in the IEC 61267 to obtain an edge spread function from which the MTF is calculated. We can compare image in the processing parameters to change between original and processed image data. The angle of the edge with respect to the axes of detector was varied in order to determine the MTF as a function of direction. Each MTF is integrated within the spatial resolution interval of 1.35-11.70 cycles/mm at the 50% MTF point. Each image enhancement parameters consists of edge, frequency, contrast, LUT, noise, sensitometry curve, threshold level, windows. The digital device is also shown to have good uniformity of MTF and image parameters across its modality. The measurements reported here represent a comprehensive evaluation of digital radiography system designed for use in the DRS. The results indicate that the parameter enables very good image quality in the digital radiography. Of course, the quality of image from a parameter is determined by other digital devices in addition to the proper clinical image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.134-138
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.4
• /
• pp.23-40
• /
• 1993

In this paper, we developed a prototype part recognition system for FMS (Flexible Manufacturing System) by comparing the features extracted from CAD data and the features obtained from the image through a single camera, Good or distinct features with high recognition efficiency for a specific part are obtained automatically and intelligently according to the rules from CAD data. Since the selection of distinct features are done automatically without any human interference, the developed system seems to be quite robust. Fourther, since it uses only a few distinct features on-line among many features and all the time-consuming calculations are done off-line, it is possible to recognize each part quickly and accurately. In order to evaluate the performance and the effectiveness of the developed system, two example(L and T shaped parts) are tested and the results are reported.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.553-556
• /
• 2003

In the field of content-based image retrieval, various mathematical low-level features have been proposed to describe the perceptual content of images. Since most of the features are assumed to be independent of each other, one feature is extracted from images without any consideration of the other features. Recently proposed CCE and SCFT taking advantage of the correlation between color and texture have shown relatively good performance. In this paper, the performance of CCE, SCFT, and the traditional regular weighted comparison method are evaluated. Simulation results with natural images have shown that CCE outperforms the other methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1902-1911
• /
• 1999

In this paper we present a content-based image retrieval algorithm using the visual feature vectors which describe the spatial characteristics of objects. The proposed technique uses the Gaussian mixture model(GMM) to represent multi-colored objects and the expectation maximization(EM) algorithm is employed to estimate the maximum likelihood(ML) parameters of the model. After image segmentation is performed based on GMM, the shape and color features are extracted from each object using Fourier descriptors and color histograms, respectively. Image retrieval consists of two steps: first, the shape-based query is carried out to find the candidate images whose objects have the similar shapes with the query image and second, the color-based query is followed. The experimental results show that the proposed algorithm is effective in image retrieving by using the spatial and visual features of segmented objects.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1204-1218
• /
• 1999

문서영상 검색을 위한 디지털도서관의 대부분은 논문제목과/또는 논문요약으로부터 만들어진 색인에 근거한 제한적인 검색기능을 제공하고 있다. 본 논문에서는 영문 문서영상전체에 대한 검색을 위한 단어 영상 형태 특징기반의 단어검색시스템을 제안한다. 본 논문에서는 검색의 효율성과 정확도를 높이기 위해 1) 기존의 단어검색시스템에서 사용된 특징들을 조합하여 사용하며, 2) 특징의 개수 및 위치뿐만 아니라 특징들의 순서를 포함하여 매칭하는 방법을 사용하며, 3) 특징비교에 의해 검색결과를 얻은 후에 여과목적으로 문자인식을 부분적으로 적용하는 2단계의 검색방법을 사용한다. 제안된 시스템의 동작은 다음과 같다. 문서 영상이 주어지면, 문서 영상 구조가 분석되고 단어 영역들의 조합으로 분할된다. 단어 영상의 특징들이 추출되어 저장된다. 사용자의 텍스트 질의가 주어지면 이에 대응되는 단어 영상이 만들어지며 이로부터 영상특징이 추출된다. 이 참조 특징과 저장된 특징들과 비교하여 유사한 단어를 검색하게 된다. 제안된 시스템은 IBM-PC를 이용한 웹 환경에서 구축되었으며, 영문 문서영상을 이용하여 실험이 수행되었다. 실험결과는 본 논문에서 제안하는 방법들의 유효성을 보여주고 있다. Abstract Most existing digital libraries for document image retrieval provide a limited retrieval service due to their indexing from document titles and/or the content of document abstracts. This paper proposes a word spotting system for full English document image retrieval based on word image shape features. In order to improve not only the efficiency but also the precision of a retrieval system, we develop the system by 1) using a combination of the holistic features which have been used in the existing word spotting systems, 2) performing image matching by comparing the order of features in a word in addition to the number of features and their positions, and 3) adopting 2 stage retrieval strategies by obtaining retrieval results by image feature matching and applying OCR(Optical Charater Recognition) partly to the results for filtering purpose. The proposed system operates as follows: given a document image, its structure is analyzed and is segmented into a set of word regions. Then, word shape features are extracted and stored. Given a user's query with text, features are extracted after its corresponding word image is generated. This reference model is compared with the stored features to find out similar words. The proposed system is implemented with IBM-PC in a web environment and its experiments are performed with English document images. Experimental results show the effectiveness of the proposed methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.