• Journal of radiological science and technology
• /
• v.30 no.4
• /
• pp.419-426
• /
• 2007

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize taste(bitter, sweet, sour and salty) pattern vectors. The signal intensity of taste are used to compose the input pattern vectors. The SOM(Self Organizing Maps) algorithm for taste pattern recognition is used to learn initial reference vectors and the ot-star learning algorithm is used to determine the class of the output neurons of the sunclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ(Learning Vector Quantization) algorithm. The pattern vectors are classified into subclasses by neurons in the subclass layer, and the weights between subclass layer and output layer are learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors, the proposed algorithm is simulated with ones of the conventional LVQ, and it is confirmed that the proposed learning method is more successful classification than the conventional LVQ.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.226-230
• /
• 2001

오류 역전파 알고리즘을 영상 인식에 적용한 경우 은닉층의 노드 수를 경험적으로 설정하여야 하는 문제점이 있다. 따라서 본 논문에서는 오류 역전파 알고리즘의 은닉층 노드 수를 동적으로 설정하는 문제를 해결하기 위해 ART1을 수정하여 지도 학습 방법과 결합한 자가 생성 지도 학습 알고리즘을 제안하였다. 제안된 학습 알고리즘의 성능을 평가하기 위해 콘테이너 영상의 문자 및 숫자 인식 문제에 적용하여 기존의 오류 역전파 알고리즘과 성능을 비교, 분석하였다. 실험 결과에서는 제안된 자가 생성 지도 학습알고리즘이 기존의 오류 역전과 알고리즘보다 지역 최소화에 빠질 가능성이 감소하였으며 학습 시간과 수렴성이 개선되었을 뿐만 아니라, 영상 인식에 적용할 수 있는 가능성도 제시하였다.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.327-336
• /
• 2002

Texture analysis is an important technique in many image understanding areas, such as perception of surface, object, shape and depth. But the previous works are intend to the issue of only texture segment, that is not capable of acquiring recognition information. No unsupervised method is basased on the recognition of texture in image. we propose a novel approach for efficient texture image analysis that uses unsupervised learning schemes for the texture recognition. The self-organization neural network for multiple texture image identification is based on block-based clustering and merging. The texture features used are the angle and magnitude in orientation-field that might be different from the sample textures. In order to show the performance of the proposed system, After we have attempted to build a various texture images. The final segmentation is achieved by using efficient edge detection algorithm applying to block-based dilation. The experimental results show that the performance of the system Is very successful.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.61-69
• /
• 2007

This paper proposes new preprocessing algorithm to extract minutiae in the process of fingerprint recognition. Fingerprint images quality enhancement is a topic phase to ensure good performance in a topic phase to ensure good performance in a Automatic Fingerprint Identification System(AFIS) based on minutiae matching. This paper proposes an algorithm to improve fingerprint image preprocessing to extract minutiae accurately based on directional filter. We improved the suitability of low quality fingerprint images to better suit fingerprint recognition by using valid ridge vector and ridge probability of fingerprint images. With the proposed fingerprint improvement algorithm, noise is removed and presumed ridges are more clearly ascertained. The algorithm is based on five step: computation of effective ridge vector, computation of ridge probability, noise reduction, ridge emphasis, and orientation compensation and frequency estimation. The performance of the proposed approach has been evaluated on two set of images: the first one is self collected using a capacitive semiconductor sensor and second one is DB3 database from Fingerprint Verification Competition (FVC).

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1133-1138
• /
• 2000

This paper describes a signal recognition method for diagnosing the rotating machinery using wavelet-aided Self-Organizing Feature Map(SOFM). The SOFM specialized from neural network is a new and effective algorithm for interpreting large and complex data sets. It converts high-dimensional data items into simple order relationships with low dimension. Additionally the Learning Vector Quantization(LVQ) is used for reducing the error from SOFM. Multi-resolution and wavelet transform are used to extract salient features from the primary vibration signals. Since it decomposes the raw timebase signal into two respective parts in the time space and frequency domain, it does not lose either information unlike Fourier transform. This paper is focused on the development of advanced signal classifier in order to automatize vibration signal pattern recognition. This method is verified by the experiment and several abnormal vibrations such as unbalance and rubbing are classified with high flexibility and reliability by the proposed methods.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.431-434
• /
• 2001

Knowledge discovery in databases(KDD) is the process for extracting valid, novel, potentially useful and understandable knowledge form real data. There are many academic and industrial activities with new technologies and application areas. Particularly, data mining is the core step in the KDD process, consisting of many algorithms to perform clustering, pattern recognition and rule induction functions. The main goal of these algorithms is prediction and description. Prediction means the assessment of unknown variables. Description is concerned with providing understandable results in a compatible format to human users. We introduce an efficient data mining algorithm considering predictive and descriptive capability. Reasonable pattern is derived from real world data by a revised neural network model and a proposed fuzzy rule extraction technique is applied to obtain understandable knowledge. The proposed neural network model is a hierarchical self-organizing system. The rule base is compatible to decision makers perception because the generated fuzzy rule set reflects the human information process. Results from real world application are analyzed to evaluate the system\`s performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1291-1300
• /
• 2008

In this paper, we propose a intelligent system to improve the accuracy of pattern recognition. The proposed intelligent system consist in SOFM, LVQ and FCM algorithm. We are confirmed the effectiveness of the proposed intelligent system through the several experiments that classify Fisher's Iris data and face image data that offered by ORL of Cambridge Univ. and EMG data. As the results of experiments, the proposed intelligent system has better accuracy of pattern recognition than general LVQ.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.134-138
• /
• 1998

Unification of Kohone SOM(Self-Organizing Maps) neural network with the branch-and-bound algorithm is presented for clustering large set of patterns. The branch-and-bound search technique is employed for designing coarse neural network learning paradaim. Those unification can be use for clustering or calssfication of large patterns. For classfication purposes further usefulness is possible, since only two clusters exists in the SOM neural network of each nodes. The result of experiments show the fast learning time, the fast recognition time and the compactness of clustering.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.