• International Journal of Aeronautical and Space Sciences
• /
• v.13 no.1
• /
• pp.1-13
• /
• 2012

Over 3.8 billion years, through evolution nature came up with many effective continually improving solutions to its challenges. Humans have always been inspired by nature capabilities in problems solving and innovation. These efforts have been intensified in recent years where systematic studies are being made towards better understanding and applying more sophisticated capabilities in this field that is increasingly being titled biomimetics. The ultimate challenge to this field is the development of humanlike robots that talk, interpret speech, walk, as well as make eye-contact and facial expressions with some capabilities that are exceeding the original model from nature. This includes flight where there is no creature that is as large, can fly as high, carry so heavy weight, fly so fast, and able to operate in extreme conditions as the aircraft and other aerospace systems. However, there are many capabilities of biological systems that are not feasible to mimic using the available technology. In this paper, the state-of-the-art of some of the developed biomimetic capabilities, potentials and challenges will be reviewed.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.4
• /
• pp.105-108
• /
• 2018

Face Detection is an essential first step of the face recognition, and this is significant effects on face feature extraction and the effects of face recognition. Face detection has extensive research value and significance. In this paper, we present and analysis the principle, merits and demerits of the classic AdaBoost face detection and ASM algorithm based on point distribution model, which ASM solves the problems of face detection based on AdaBoost. First, the implemented scheme uses AdaBoost algorithm to detect original face from input images or video stream. Then, it uses ASM algorithm converges, which fit face region detected by AdaBoost to detect faces more accurately. Finally, it cuts out the specified size of the facial region on the basis of the positioning coordinates of eyes. The experimental result shows that the method can detect face rapidly and precisely, with a strong robustness.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.701-703
• /
• 2022

In this paper, we present a multi-class image scene classification method based on map learning. We were able to learn from the convolutional neural network model in the dataset, classify facial scene images of multiclass people, and classify the optimized CNN model into the Google image dataset in the experiment with significant results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.563-565
• /
• 2023

Acupuncture and acupressure apply needles or pressure to anatomical points for therapeutic benefit. The over 350 mapped acupuncture points in the human body can each treat various conditions, but anatomical variations make precisely locating these acupoints difficult. We propose a computer vision technique using the real-time hand and face tracking capabilities of the MediaPipe framework to identify acupoint locations. Our model detects anatomical facial and hand landmarks, and then maps these to corresponding acupoint regions. In summary, our proposed model facilitates precise acupoint localization for self-treatment and enhances practitioners' abilities to deliver targeted acupuncture and acupressure therapies.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2012

In this paper an extension to an original active shape model(ASM) for facial feature extraction is presented. The original ASM suffers from poor shape alignment by aligning the shape model to a new instant of the object in a given image using a simple similarity transformation. It exploits only informations such as scale, rotation and shift in horizontal and vertical directions, which does not cope effectively with the complex pose variation. To solve the problem, new shape alignment with 6 degrees of freedom is derived, which corresponds to an affine transformation. Another extension is to speed up the calculation of the Mahalanobis distance for 2-D profiles by trimming the profile covariance matrices. Extensive experiment is conducted with several images of varying poses to check the performance of the proposed method to segment the human faces.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.354-357
• /
• 2021

Infants communicate their feelings and needs to the outside world through non-verbal methods such as crying and displaying diverse facial expressions. However, inexperienced parents tend to decode these non-verbal messages incorrectly and take inappropriate actions, which might affect the bonding they build with their babies and the cognitive development of the newborns. In this paper, we propose an aural-visual two-stream based infant cry recognition system to help parents comprehend the feelings and needs of crying babies. The proposed system first extracts the features from the pre-processed audio and video data by using the VGGish model and 3D-CNN model respectively, fuses the extracted features using a fully connected layer, and finally applies a SoftMax function to classify the fused features and recognize the corresponding type of cry. The experimental results show that the proposed system classification exceeds 0.92 in F1-score, which is 0.08 and 0.10 higher than the single-stream aural model and single-stream visual model.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.936-941
• /
• 2006

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.

• The Journal of Korea Robotics Society
• /
• v.3 no.4
• /
• pp.270-277
• /
• 2008

The development of a face robot basically targets very natural human-robot interaction (HRI), especially emotional interaction. So does a face robot introduced in this paper, named Buddy. Since Buddy was developed for a mobile service robot, it doesn't have a living-being like face such as human's or animal's, but a typically robot-like face with hard skin, which maybe suitable for mass production. Besides, its structure and mechanism should be simple and its production cost also should be low enough. This paper introduces the mechanisms and functions of mobile face robot named Buddy which can take on natural and precise facial expressions and make dynamic gestures driven by one laptop PC. Buddy also can perform lip-sync, eye-contact, face-tracking for lifelike interaction. By adopting a customized emotional reaction decision model, Buddy can create own personality, emotion and motive using various sensor data input. Based on this model, Buddy can interact probably with users and perform real-time learning using personality factors. The interaction performance of Buddy is successfully demonstrated by experiments and simulations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9C
• /
• pp.887-898
• /
• 2005

In this paper, we introduce a probabilistic model based on Bayesian networks BNs) for recognizing human fatigue. First of all, we measured face feature information such as eyelid movement, gaze, head movement, and facial expression by IR illumination. But, an individual face feature information does not provide enough information to determine human fatigue. Therefore in this paper, a Bayesian network model was constructed to fuse as many as possible fatigue cause parameters and face feature information for probabilistic inferring human fatigue. The MSBNX simulation result ending a 0.95 BN fatigue index threshold. As a result of the experiment, when comparisons are inferred BN fatigue index and the TOVA response time, there is a mutual correlation and from this information we can conclude that this method is very effective at recognizing a human fatigue.