Changyong Yoon

Continuous Human Action Recognition Using Depth-MHI-HOG and a Spotter Model

In this paper, we propose a new method for spotting and recognizing continuous human actions using a vision sensor. The method is comprised of depth-MHI-HOG (DMH), action modeling, action spotting, and recognition. First, to effectively separate the foreground from background, we propose a method called DMH. It includes a standard structure for segmenting images and extracting features by using depth information, MHI, and HOG. Second, action modeling is performed to model various actions using extracted features. The modeling of actions is performed by creating sequences of actions through k-means clustering; these sequences constitute HMM input. Third, a method of action spotting is proposed to filter meaningless actions from continuous actions and to identify precise start and end points of actions. By employing the spotter model, the proposed method improves action recognition performance. Finally, the proposed method recognizes actions based on start and end points. We evaluate recognition performance by employing the proposed method to obtain and compare probabilities by applying input sequences in action models and the spotter model. Through various experiments, we demonstrate that the proposed method is efficient for recognizing continuous human actions in real environments.

Face recognition using wavelets and fuzzy C-means clustering

In this paper we perform wavelet transform of the input 256/spl times/256 color image and decompose input image into low-pass and high-pass components. After finding the position of face using the histogram of the edges, a face region in low-pass band image is extracted. Since RGB color image is easily affected by illumination, the image of low pass component is normalized, and a face region is detected using face color information. In this paper, we use 3000 images of 10 persons, and KL transform is applied in order to classify face vectors effectively. FCM (Fuzzy C-means) algorithm classifies face vectors, which have similar features, into the same cluster. In this case, the number of cluster is equal to that of a person, and the mean vector of each cluster is used as codebook. We estimate the proposed systems performance through experiments. The recognition rate of learning images and that of testing image are computed using correlation coefficients and Euclidean distance.

Real-Time Road Sign Detection Using Fuzzy-Boosting

This paper describes a vision-based and real-time system for detecting road signs from within a moving vehicle. The system architecture which is proposed in this paper consists of two parts, the learning and the detection part of road sign images. The proposed system has the standard architecture with adaboost algorithm. Adaboost is a popular algorithm which used to detect an object in real time. To improve the detection rate of adaboost algorithm, this paper proposes a new combination method of classifiers in every stage. In the case of detecting road signs in real environment, it can be ambiguous to decide to which class input images belong. To overcome this problem, we propose a method that applies fuzzy measure and fuzzy integral which use the importance and the evaluated values of classifiers within one stage. It is called fuzzy-boosting in this paper. Also, to improve the speed of a road sign detection algorithm using adaboost at the detection step, we propose a method which chooses several candidates by using MC generator. In this paper, as the sub-windows of chosen candidates pass classifiers which are made from fuzzy-boosting, we decide whether a road sign is detected or not. Using experiment result, we analyze and compare the detection speed and the classification error rate of the proposed algorithm applied to various environment and condition.

Intelligent system for automatic adjustment of 3D facial shape model and face expression recognition

A facial expression recognition system using features from the automatically adjusted 3D facial shape model is proposed in this dissertation. The region of face is detected from input images with a face and the 3D facial shape model is deformed to fit the detected region and the facial feature points. In this paper, the face synthesis techniques are applied to face region detection and the extracted features are used for training of the intelligent facial expression recognition system. Then the face expression recognition system employs a neuro-fuzzy technology with supervised-learning function. Some experiments are accomplished using various image data, it was turned out that the region detection and 3D shape model adjustment method is efficient and the processing time was reduced.

Human Detection and Fuzzy Temperature Control System for Energy Reduction of Cooling Device in Elevator

Abstract In this paper, we propose human detection and fuzzy temperature control system for energy reduction of cooling device in elevator. In order to improve problems of existing co oling device using the refrigerant, energy reduc-tion and efficient management are continuously achieved because of operation of thermoelectric cooling device using the human detection and fuzzy temperature control system. The proposed system confirms the number o fpassengers in elevator and temperature is then controlled by th ose numbers and an average temperature for the season in fuzzy system. The human detection method scans the nu mber of passengers using a head part as a feature based on birds-eye view camera in elevator. The fuzzy system determines elevator internal temperature considering atmospheric temperature and the scanned passenger n umbers as a look-up table. The proposed sys-tem reduces energy of the cooling device through the human dete ction and temperature control. In experiment,energy reduction is confirmed and the performance of the propos ed system is verified.Key Words : Elevator, Cooling Device, Human Detection, Fuzzy System, Temperature ControlReceived: Feb. 2, 2015Revised : Apr. 6, 2015Accepted: Apr. 7, 2015

Depth Image-Based Human Action Recognition Using Convolution Neural Network and Spatio-Temporal Templates

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

Development of Fuzzy Support Vector Machine and Evaluation of Performance Using Ionosphere Radar Data

Support Vector machine is the classifier which is based on the statistical training theory. Twin Support Vector Machine(TWSVM) is a kind of binary classifier that determines two nonparallel planes by solving two related SVM-type problems. The training time of TWSVM is shorter than that of SVM, but TWSVM doesn`t shows worse performance than that of SVM. This paper proposes the TWSVM which is applied fuzzy membership, and compares the performance of this classifier with the other classifiers using Ionosphere radar data set.