• Journal of the Korea Society of Computer and Information
• /
• v.3 no.3
• /
• pp.1-5
• /
• 1998

In this paper, it was Proposed to extract road area automatically in general road guide map. Line tracing proposed in 〔1〕 was used basic extraction method, but by choosing starting pixel automatically iterative user interaction could be removed in this paper. this was possible by classifying and analysis color of each road. The usefulness of the proposed method was proved through experiments with various color printed maps.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.525-528
• /
• 2009

Recently, image classification has been an important task in various fields. Generally, the performance of image classification is not good without the adjustment of image features. Therefore, it is desired that the way of automatic feature extraction. In this paper, we propose an image classification method which adjusts image features automatically. We assume that texture features are useful in image classification tasks because natural images are composed of several types of texture. Thus, the classification accuracy rate is improved by using distribution of texture features. We obtain texture features by calculating image features from a current considering pixel and its neighborhood pixels. And we calculate image features from distribution of textures feature. Those image features are adjusted to image classification tasks using Genetic Algorithm. We apply proposed method to classifying images into "head" or "non-head" and "male" or "female".

• Investigative Magnetic Resonance Imaging
• /
• v.3 no.2
• /
• pp.179-187
• /
• 1999

Purpose : This paper introduces a computationally inexpensive context-dependent classification of multi-echo MRI with Bayes compound decision model. In order to produce accurate region segmentation especially in homogeneous area and along boundaries of the regions, we propose a classification method that uses contextual information of local enighborhood system in the image. Material and Methods : The performance of the context free classifier over a statistically heterogeneous image can be improved if the local stationary regions in the image are disassociated from each other through the mechanism of the interaction parameters defined at he local neighborhood level. In order to improve the classification accuracy, we use the contextual information which resolves ambiguities in the class assignment of a pattern based on the labels of the neighboring patterns in classifying the image. Since the data immediately surrounding a given pixel is intimately associated with this given pixel., then if the true nature of the surrounding pixel is known this can be used to extract the true nature of the given pixel. The proposed context-dependent compound decision model uses the compound Bayes decision rule with the contextual information. As for the contextual information in the model, the directional transition probabilities estimated from the local neighborhood system are used for the interaction parameters. Results : The context-dependent classification paradigm with compound Bayesian model for multi-echo MR images is developed. Compared to context free classification which does not consider contextual information, context-dependent classifier show improved classification results especially in homogeneous and along boundaries of regions since contextual information is used during the classification. Conclusion : We introduce a new paradigm to classify multi-echo MRI using clustering analysis and Bayesian compound decision model to improve the classification results.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.3
• /
• pp.229-234
• /
• 2018

Texture is one of the most useful features in classifying and segmenting images. The LBP-based approach previously presented in the literature has been successful in many applications. However, it's theoretical foundation is based only on the difference of pixel values, and consequently it has a number of drawbacks like it performs poorly for the images corrupted with noise, and especially it cannot be used as a multiscale texture descriptor due to the exploding increase of feature vector dimension with increase of the number of neighbor pixels. In this paper, we present a method to address these drawbacks of LBP-based approach. More specifically, our approach quantizes the range of pixels values and construct a 3D histogram which captures the correlative information of pixels. This histogram is used as a texture feature. Several tests with texture images show that the proposed method outperforms the LBP-based approach in the problem of texture classification.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.9
• /
• pp.1269-1282
• /
• 1993

In this paper, we propose to method of recognizing printed chinese characters which combine the coventional deterministic methods and the neural networks. Firstly, we extract four directional vector of strokes from chinese characters. Secondly, we make the mesh of the center of gravity in the vector and then constitute the H x8 feature matrix using black pixel lenth from each meshs. This normalized feature matrix value offer as the input of neural network for classifying into the 14 character types. And this calssified character classify again into Busu group by the Busu recognizing neural network. Finally, we recognize each characters using the distance of similarity between input characters and reference characters. The usefulness of the proposed algorithm is evaluated by experimenting with recognizing the chinese characters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• Journal of Forest and Environmental Science
• /
• v.29 no.2
• /
• pp.131-137
• /
• 2013

This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carried out with CALIGEO software, which automatically corrects for both geometric and radiometric distortions of the raw image data. The radiance data set was then converted to at-sensor reflectance derived from the FODIS sensor. Spectral Angle Mapper (SAM) technique was used for image classification. The spectra libraries for tree species were established after confirming the appropriate match between field spectra and pixel spectra. Results showed that the highest spectral signature in NIR range were Kembang Semangkok (Scaphium macropodum), followed by Meranti Sarang Punai (Shorea parvifolia) and Chengal (Neobalanocarpus hemii). Meanwhile, the lowest spectral response were Kasai (Pometia pinnata), Kelat (Eugenia spp.) and Merawan (Hopea beccariana), respectively. The overall accuracy obtained was 79%. Although the accuracy of SAM techniques is below the expectation level, SAM classifier was able to classify tropical tree species. In future it is believe that the most effective way of ground data collection is to use the ground object that has the strongest response to sensor for more significant tree signatures.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.437-444
• /
• 2008

Land-use or land-cover classification of satellite images is one of the important tasks in remote sensing application and many researchers have tried to enhance classification accuracy. Previous studies have shown that the classification technique based on wavelet transform is more effective than traditional techniques based on original pixel values, especially in complicated imagery. Various basis functions such as Haar, daubechies, coiflets and symlets are mainly used in 20 image processing based on wavelet transform. Selecting adequate wavelet is very important because different results could be obtained according to the type of basis function in classification. However, it is not easy to choose the basis function which is effective to improve classification accuracy. In this study, we first computed the wavelet coefficients of satellite image using ten different basis functions, and then classified images. After evaluating classification results, we tried to ascertain which basis function is the most effective for image classification. We also tried to see if the optimum basis function is decided by energy parameter before classifying the image using all basis functions. The energy parameters of wavelet detail bands and overall accuracy are clearly correlated. The decision of optimum basis function using energy parameter in the wavelet based image classification is expected to be helpful for saving time and improving classification accuracy effectively.

• Korean Journal of Remote Sensing
• /
• v.21 no.5
• /
• pp.405-415
• /
• 2005

It is difficult to classify tidal flat surface that is composed of a mixture of mud, sand, water and microphytobenthos. We used a Linear Spectral Unmixing (LSU) method for effectively classifying the tidal flat surface characteristics within a pixel. This study aims at 1) detecting algal mat using LSU in the Saemangeum tidal flats, 2) determining a suitable end-member selection method in tidal flats, and 3) find out a habitual characteristics of algal mat. Two types of end-member were built; one is a reference end-member derived from field spectrometer measurements and the other image end-member. A field spectrometer was used to measure spectral reflectance, and a spectral library was accomplished by shape difference of spectra, r.m.s. difference of spectra, continuum removal and Mann-Whitney U-test. Reference end-members were extracted from the spectral library. Image end-members were obtained by applying Principle Component Analysis (PCA) to an image. The LSU method was effective to detect microphytobenthos, and successfully classified the intertidal zone into algal mat, sediment, and water body components. The reference end-member was slightly more effective than the image end-member for the classification. Fine grained upper tidal flat is generally considered as a rich habitat for algal mat. We also identified unusual microphytobenthos that inhabited coarse grained lower tidal flats.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.9-19
• /
• 2024

Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.