• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.464-475
• /
• 2017

In this paper, we present a new texture image retrieval method which combines color and texture features extracted from images by a set of multi-resolution multi-direction (MRMD) filters. The MRMD filter set chosen is simple and can be separable to low and high frequency information, and provides efficient multi-resolution and multi-direction analysis. The color space used is HSV color space separable to hue, saturation, and value components, which are easily analyzed as showing characteristics similar to the human visual system. This experiment is conducted by comparing precision vs. recall of retrieval and feature vector dimensions. Images for experiments include Corel DB and VisTex DB; Corel_MR DB and VisTex_MR DB, which are transformed from the aforementioned two DBs to have multi-resolution images; and Corel_MD DB and VisTex_MD DB, transformed from the two DBs to have multi-direction images. According to the experimental results, the proposed method improves upon the existing methods in aspects of precision and recall of retrieval, and also reduces feature vector dimensions.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.

• Journal of Sensor Science and Technology
• /
• v.25 no.4
• /
• pp.285-290
• /
• 2016

Human sensing is an important but challenging technology. Unlike other methods for sensing humans, a vision sensor has many advantages, and there has been active research in automatic human detection in camera images. The combination of Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is currently one of the most successful methods in vision-based human detection. However, extracting HOG features from an image is computer intensive, and it is thus hard to employ the HOG method in real-time processing applications. This paper describes an efficient solution to this speed problem of the HOG method. Our method obtains edge information of an image and finds candidate regions where humans very likely exist based on the distribution pattern of the detected edge points. The HOG features are then extracted only from the candidate image regions. Since complex HOG processing is adaptively done by the guidance of the simpler edge detection step, human detection can be performed quickly. Experimental results show that the proposed method is effective in various images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.37-44
• /
• 2013

In this paper, we propose the pulmonary nodule detection system based on voxel classification. The proposed system consists of three main steps. In the first step, we segment lung volume. In the second step, the lung structures are initially segmented. In the last step, we classify the nodules using voxel classification. To describe characteristics of each voxel, we extract the log-polar sampling based features. Support Vector Machine is applied to the extracted features to classify into nodules and non-nodules.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1531-1536
• /
• 2011

We propose an automatic swearword filter system for online game chatting by using Support Vector Machines(SVM). We collected chatting sentences from online games and tagged them as normal sentences or swearword included sentences. We use n-gram syllables and lexical-part of speech (POS) tags of a word as features and select useful features by chi square statistics. Each selected feature is represented as binary weight and used in training SVM. SVM classifies each chatting sentence as swearword included one or not. In experiment, we acquired overall 90.4% of F1 accuracy.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.103-116
• /
• 2013

Prostate cancer is one of the most frequent cancers in men and is a major cause of mortality in the most of countries. In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation in TRUS images using Gabor feature extraction and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. The speckle reduction for preprocessing step has been achieved by using stick filter and top-hat transform has been implemented for smoothing the contour. A Gabor filter bank for extraction of rotation-invariant texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. Finally, the boundary of prostate is extracted by the snake-like contour algorithm. A number of experiments are conducted to validate this method and results showed that this new algorithm extracted the prostate boundary with less than 10.2% of the accuracy which is relative to boundary provided manually by experts.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.251-256
• /
• 2004

This paper will show examples and methods of spatial relationship operations that extract spatial information from satellite images. Geographical information system phenomena of complex and variant real world can abstract and implement simple features. The abstract features classify geo_objects and geo_field. The geo_object and the geo_field can represent vector and raster respectively. The raster based satellite image can use remote sensing applications. This paper needs topology operations and geometric operations for extracting the remote sensing. The spatial information transforms the raster based image to the vector based object, and extract from the spatial information. The extracted information will contribute on the application of the remote sensing satellite images.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.255-258
• /
• 2011

An application of Gammatone auditory filterbank for emotion recognition from speech is described in this paper. Gammatone filterbank is a bank of Gammatone filters which are used as a preprocessing stage before applying feature extraction methods to get the most relevant features for emotion recognition from speech. In the feature extraction step, the energy value of output signal of each filter is computed and combined with other of all filters to produce a feature vector for the learning step. A feature vector is estimated in a short time period of input speech signal to take the advantage of dependence on time domain. Finally, in the learning step, Hidden Markov Model (HMM) is used to create a model for each emotion class and recognize a particular input emotional speech. In the experiment, feature extraction based on Gammatone filterbank (GTF) shows the better outcomes in comparison with features based on Mel-Frequency Cepstral Coefficient (MFCC) which is a well-known feature extraction for speech recognition as well as emotion recognition from speech.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.158-166
• /
• 2004

Predicting the destination of a protein in a cell gives valuable information for annotating the function of the protein. Recent technological breakthroughs have led us to develop more accurate methods for predicting the subcellular localization of proteins. The most important factor in determining the accuracy of these methods, is a way of extracting useful features from protein sequences. We propose a new method for extracting appropriate features only from the sequence data by computing pairwise sequence alignment scores. As a classifier, support vector machine (SVM) is used. The overall prediction accuracy evaluated by the jackknife validation technique reach 94.70% for the eukaryotic non-plant data set and 92.10% for the eukaryotic plant data set, which show the highest prediction accuracy among methods reported so far with such data sets. Our numerical experimental results confirm that our feature extraction method based on pairwise sequence alignment, is useful for this classification problem.