• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.41-47
• /
• 2022

In this paper, we propose a new and simple self-supervised learning method that predicts the middle image of a face image sequence for automatic expression recognition. Automatic facial expression recognition can achieve high performance through deep learning methods, however, generally requires a expensive large data set. The size of the data set and the performance of the algorithm are tend to be proportional. The proposed method learns latent deep representation of a face through self-supervised learning using an existing dataset without constructing an additional dataset. Then it transfers the learned parameter to new facial expression reorganization model for improving the performance of automatic expression recognition. The proposed method showed high performance improvement for two datasets, CK+ and AFEW 8.0, and showed that the proposed method can achieve a great effect.

• Journal of Biosystems Engineering
• /
• v.19 no.2
• /
• pp.124-137
• /
• 1994

Visual features of a mushroom(Lentinus Edodes, L.) are critical in grading and sorting as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. To realize the automatic handling and grading of mushrooms in real time, the computer vision system should be utilized and the efficient and robust processing of the camera captured visual information be provided. Since visual features of a mushroom are distributed over the front and back sides, recognizing sides and states of the stalk including the stalk orientation from the captured image is a prime process in the automatic task processing. In this paper, the efficient and robust recognition process identifying the front and back side and the state of the stalk was developed and its performance was compared with other recognition trials. First, recognition was tried based on the rule set up with some experimental heuristics using the quantitative features such as geometry and texture extracted from the segmented mushroom image. And the neural net based learning recognition was done without extracting quantitative features. For network inputs the segmented binary image obtained from the combined type automatic thresholding was tested first. And then the gray valued raw camera image was directly utilized. The state of the stalk seriously affects the measured size of the mushroom cap. When its effect is serious, the stalk should be excluded in mushroom cap sizing. In this paper, the stalk removal process followed by the boundary regeneration of the cap image was also presented. The neural net based gray valued raw image processing showed the successful results for our recognition task. The developed technology through this research may open the new way of the quality inspection and sorting especially for the agricultural products whose visual features are fuzzy and not uniquely defined.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.167-177
• /
• 2003

This paper presents a method of building an exceptional pronunciation dictionary for Korean automatic pronunciation generator. An automatic pronunciation generator is an essential element of speech recognition system and a TTS (Text-To-Speech) system. It is composed of a part of regular rules and an exceptional pronunciation dictionary. The exceptional pronunciation dictionary is created by extracting the words which have exceptional pronunciations from text corpus based on the characteristics of the words of exceptional pronunciation through phonological research and text analysis. Thus, the method contributes to improve performance of Korean automatic pronunciation generator as well as the performance of speech recognition system and TTS system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.231-234
• /
• 2011

Audiovisual-based human emotion recognition can be considered a good approach for multimodal humancomputer interaction. However, the optimal multimodal information fusion remains challenges. In order to overcome the limitations and bring robustness to the interface, we propose a framework of automatic human emotion recognition system from speech and face display. In this paper, we develop a new approach for fusing information in model-level based on the relationship between speech and face expression to detect automatic temporal segments and perform multimodal information fusion.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.416-424
• /
• 2016

In this study, automatic detection of stator winding inter-turn short circuit fault (SWISCFs) in surface-mounted permanent magnet synchronous motors (SPMSMs) and automatic classification of fault severity via a pattern recognition system (PRS) are presented. In the case of a stator short circuit fault, performance losses become an important issue for SPMSMs. To detect stator winding short circuit faults automatically and to estimate the severity of the fault, an artificial neural network (ANN)-based PRS was used. It was found that the amplitude of the third harmonic of the current was the most distinctive characteristic for detecting the short circuit fault ratio of the SPMSM. To validate the proposed method, both simulation results and experimental results are presented.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.85-88
• /
• 2011

This paper describes a single channel speech enhancement as the pre-processor of automatic speech recognition system. The improvements are based on using optimally modified log-spectra (OM-LSA) gain function with a non-causal a priori signal-to-noise ratio (SNR) estimation. Experimental results show that the proposed method gives better perceptual evaluation of speech quality score (PESQ) and lower log-spectral distance, and also better word accuracy. In the enhancement system, parameters was turned for automatic speech recognition.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.14 no.1
• /
• pp.57-66
• /
• 2010

In this paper, we develop the Automatic Number Plate Recognition (ANPR) System. ANPR is generally composed of the following four steps: i) The acquisition of the image; ii) The extraction of the region of the number plate; iii) The partition of the number and iv) The recognition. The second and third steps incorporate image processing technique. We propose to resolve this by using Partial Differential Equation(PDE) based segmentation method. This method is computationally efficient and robust. Results indicate that our methods are capable to recognize the plate number on difficult situations.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• Journal of Power System Engineering
• /
• v.15 no.5
• /
• pp.83-90
• /
• 2011

In general, 20-high Sendzimir mills(ZRM) use small diameter work rolls to provide massive rolling force. Because of small diameter of work rolls, steel strip has a complex shape mixed with quarter, edge and center waves. Especially when the shape of the strip is controlled automatically, the actuator saturation occurs. These problems affect the productivity and quality of products. In this paper, the problems in automatic shape control of ZRM were analyzed. In order to evaluate the problems for the automatic shape control in ZRM, recognition performance was analyzed by comparing the measured shape and the recognized shape. The actuator positions by the shape recognition and the manual operation were compared. From the analysis results, the necessity of the improvement of recognition performance in ZRM is suggested.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.1
• /
• pp.63-73
• /
• 2021

This paper presents a algorithm for automatic target recognition robust to the influence of the flame in order to track the target by EOTS(Electro-Optical Targeting System) equipped on UAV(Unmanned Aerial Vehicle) when there is aerial target or marine target with flame at the same time. The proposed method converts infrared images of targets and flames into a gradient vector field, and applies each gradient magnitude to a polynomial curve fitting technique to extract polynomial coefficients, and learns them in a shallow neural network model to automatically recognize targets and flames. The performance of the proposed technique was confirmed by utilizing the various infrared image database of the target and flame. Using this algorithm, it can be applied to areas where collision avoidance, forest fire detection, automatic detection and recognition of targets in the air and sea during automatic flight of unmanned aircraft.