• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.87-94
• /
• 2008

In this paper, an extraction method of objects of interest in the color images is proposed. It is possible to extract objects of interest from a complex background without any prior-knowledge based on the proposed method. For object extraction, Gator images that contain information of object location, are created by using Gator filter. Based on the images the initial location of attention windows is determined, from which image features are selected to extract objects. To extract object, I modify the previous method partially and apply the modified method. To evaluate the performance of propsed method, precision, recall and F-measure are calculated between the extraction results from propsed method and manually extracted results. I verify the performance of the proposed methods based on these accuracies. Also through comparison of the results with the existing method, I verily the superiority of the proposed method over the existing method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2006

In this paper, adaptive Facial Emotional Recognition system based on Gabor Wavelet Neural Network, considering six feature Points in face image to extract specific features of facial expression, is proposed. Levenberg-Marquardt-based training methodology is used to formulate initial network, including feature extraction stage. Therefore, heuristics in determining feature extraction process can be excluded. Moreover, to make an adaptive network for new user, Q-learning which has enhanced reward function and unsupervised fuzzy neural network model are used. Q-learning enables the system to ge optimal Gabor filters' sets which are capable of obtaining separable features, and Fuzzy Neural Network enables it to adapt to the user's change. Therefore, proposed system has a good on-line adaptation capability, meaning that it can trace the change of user's face continuously.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.371-384
• /
• 2019

Motion perception has been tremendously improved in neuroscience and computer vision. The baseline motion perception model is mediated by the dorsal visual pathway involving the cortex areas the primary visual cortex (V1) and the middle temporal (V5 or MT) visual area. However, few works have been done on the extension of neural models to improve the efficacy and robustness of motion perception of real sequences. To overcome shortcomings in situations, such as varying illumination and large displacement, an adaptive V1-MT motion perception (Ad-V1MTMP) algorithm enriched to deal with real sequences is proposed and analyzed. First, the total variation semi-norm model based on Gabor functions (TV-Gabor) for structure-texture decomposition is performed to manage the illumination and color changes. And then, we study the impact of image local context, which is processed in extra-striate visual areas II (V2), on spatial motion integration by MT neurons, and propose a V1-V2 method to extract the image contrast information at a given location. Furthermore, we take feedback inputs from V2 into account during the polling stage. To use the algorithm on natural scenes, finally, multi-scale approach has been used to handle the frequency range, and adaptive pyramidal decomposition and decomposed spatio-temporal filters have been used to diminish computational cost. Theoretical analysis and experimental results suggest the new Ad-V1MTMP algorithm which mimics human primary motion pathway has universal, effective and robust performance.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.617-629
• /
• 2001

The mathematical models for the receptive field of simple cells in the human visual system have been developed in the areas of psychophysics, physiology and neuroscience. The various models used in the fields of digital image processing and computer vision include Gator complex, Gaussian derivatives and Hermite functions. In this paper, the effective widths for the models are derived based on the space-frequency uncertainty principle. The center frequency and parameters related to the models are determined in accordance with the human visual filters, and resultant bandwidths are analyzed. Furthermore, the characteristics of space and frequency for the models is analyzed and compared to the experimental data obtained from psychophysics.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.77-89
• /
• 2001

Applying perceptual hierarchy of facial feature points, a neural network model for recognizing facial expressions was designed. Input data were convolution values of 150 facial expression pictures by Gabor-filters of 5 different sizes and 8 different orientations for each of 39 mesh points defined by MPEG-4 SNHC (Synthetic/Natural Hybrid Coding). A set of multiple regression analyses was performed with the rating value of the affective states for each facial expression and the Gabor-filtered values of 39 feature points. The results show that the pleasure-displeasure dimension of affective states is mainly related to the feature points around the mouth and the eyebrows, while a arousal-sleep dimension is closely related to the feature points around eyes. For the filter sizes. the affective states were found to be mostly related to the low spatial frequency. and for the filter orientations. the oblique orientations. An optimized neural network model was designed on the basis of these results by reducing original 1560(39x5x8) input elements to 400(25x2x8) The optimized model could predict human affective rating values. up to the correlation value of 0.886 for the pleasure-displeasure, and 0.631 for the arousal-sleep. Mapping the results of the optimized model to the six basic emotional categories (happy, sad, fear, angry, surprised, disgusted) fit 74% of human responses. Results of this study imply that, using human principles of recognizing facial expressions, a system for recognizing facial expressions can be optimized even with a a relatively little amount of information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.451-454
• /
• 2005

본 논문에서는 수정된 CNN(Convolutional Neural Network) 모델과 다중 필터가 상호 결합된 형태의 얼굴 패턴 검출 기법을 소개 한다. 이는 로봇 시각의 응용문제에서 실내영상의 실시간 인식문제를 대상으로 한다. 검출 과정의 효율성 향상을 위하여 도입된 다중 필터는 후보 영역의 개수와 범위를 줄일 수 있게 한다. 제안된 모델에서 CNN 신경망은 가보변환(Gabor Transform)계층을 두어 검출 과정의 첫 단계에서 영상 내의 기본 특징 지도를 생성 하도록 하였다. 보다 강인한 검출기능을 위하여 조명보정 기법이 시스템의 전처리 단계로 구현 된다. 실제 영상을 통한 실험 결과로부터 제안된 이론의 타당성을 고찰 한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.215-220
• /
• 2010

In this paper, we propose a new texture-based page segmentation and classification method in which table region, background region, image region and text region in a given document image are automatically identified. The proposed method for document images consists of two stages, document segmentation and contents classification. In the first stage, we segment the document image, and then, we classify contents of document in the second stage. The proposed classification method is based on a texture analysis. Each contents in the document are considered as regions with different textures. Thus the problem of classification contents of document can be posed as a texture segmentation and analysis problem. Two-dimensional Gabor filters are used to extract texture features for each of these regions. Our method does not assume any a priori knowledge about content or language of the document. As we can see experiment results, our method gives good performance in document segmentation and contents classification. The proposed system is expected to apply such as multimedia data searching, real-time image processing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.7
• /
• pp.956-962
• /
• 2018

As the study of the object feature detection from image, we explain methods to identify the species of the tree in forest using the picture taken from dron. Generally there are three kinds of methods, which are GLCM (Gray Level Co-occurrence Matrix) and Gabor filters, in order to extract the object features. We proposed the object extraction method using the statistical properties of trees in this research because of the similarity of the leaves. After we extract the sample images from the original images, we detect the objects using cross correlation techniques between the original image and sample images. Through this experiment, we realized the mean value and standard deviation of the sample images is very important factor to identify the object. The analysis of the color component of the RGB model and HSV model is also used to identify the object.

• The Journal of the Korea Contents Association
• /
• v.9 no.6
• /
• pp.1-8
• /
• 2009

There are a lot of influences, such as location of camera, luminosity, brightness, and direction of light, which affect the performance of 2-dimensional image recognition. This paper suggests an adaptive method for face-image recognition in noisy environments using evolvable filtering and feature extraction which uses one sample image from camera. This suggested method consists of two main parts. One is the environmental-adjustment module which determines optimum sets of filters, filter parameters, and dimensions of features by using "steady state genetic algorithm". The other another part is for face recognition module which performs recognition of face-image using the previous results. In the processing, we used Gabor wavelet for extracting features in the images and k-Nearest Neighbor method for the classification. For testing of the adaptive face recognition method, we tested the adaptive method in the brightness noise, in the impulse noise and in the composite noise and verified that the adaptive method protects face recognition-rate's rapidly decrease which can be occurred generally in the noisy environments.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.