• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.60-68
• /
• 2007

In this paper, we propose an automatic facial expressions recognition system to analyze facial expressions (happiness, disgust, surprise and neutral) using tree structures based on heuristic rules. The facial region is first obtained using skin-color model and connected-component analysis (CCs). Thereafter the origins of user's eyes are localized using neural network (NN)-based texture classifier, then the facial features using some heuristics are localized. After detection of facial features, the facial expression recognition are performed using decision tree. To assess the validity of the proposed system, we tested the proposed system using 180 facial image in the MMI, JAFFE, VAK DB. The results show that our system have the accuracy of 93%.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.15-23
• /
• 2016

This paper proposes an effective algorithm of Korean license plate recognition. By applying Haar-like feature and Canny edge detection on a captured vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are classified using neural networks trained by backpropagation algorithm to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1556-1567
• /
• 2009

The death rate of pedestrian in car accidents in Korea is 2.5 times higher than the average of OECD countries'. If a system that can detect pedestrians and send alarm to drivers is built and reduces the rate, it is worth developing such a pedestrian detection system (PDS). Since the accident rate in which pedestrians are involved is higher at nighttime than in daytime, the adoption of nighttime PDS is being standardized by big auto companies. However, they are usually using night visions or multiple sensors, which are usually expensive. In this paper we suggest a method for nighttime PDS using single wide dynamic range (WDR) monochrome camera in visible spectrum band. In our experiments, pedestrians were accurately detected if only most edges of pedestrians could be obtained.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.125-131
• /
• 2019

A vanishing point is a point on an image to which parallel lines projected from a real space gather. A vanishing point in a road space provides important spatial information. It is possible to improve the position of an extracted lane or generate a depth map image using a vanishing point in the road space. In this paper, we propose a method of detecting vanishing points on images taken from a vehicle's point of view using Deep Neural Network (DNN) and Histogram of Oriented Gradient (HoG). The proposed algorithm is divided into a HoG feature extraction step, in which the edge direction is extracted by dividing an image into blocks, a DNN learning step, and a test step. In the learning stage, learning is performed using 2,300 road images taken from a vehicle's point of views. In the test phase, the efficiency of the proposed algorithm using the Normalized Euclidean Distance (NormDist) method is measured.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1280-1287
• /
• 2020

This paper proposes a vision-based food recognition method for automated production of custom cakes. A small camera module mounted on a food art printer recognizes objects' shape and estimates their center points through image processing. Through the perspective transformation, the top-view image is obtained from the original image taken at an oblique position. The line and circular hough transformations are applied to recognize square and circular shapes respectively. In addition, the center of gravity of each figure are accurately detected in units of pixels. The test results show that the shape recognition rate is more than 98.75% under 180 ~ 250 lux of light and the positioning error rate is less than 0.87% under 50 ~ 120 lux. These values sufficiently meet the needs of the corresponding market. In addition, the processing delay is also less than 0.5 seconds per frame, so the proposed algorithm is suitable for commercial purpose.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.70-77
• /
• 2008

This paper proposes a new text candidate region detection method that uses genetic algorithm based on information of the segmented regions. In image segmentation, a classification of the pixels at each color channel and a reclassification of the region-unit for reducing inhomogeneous clusters are performed. EWFCM(Entropy-based Weighted C-Means) algorithm to classify the pixels at each color channel is an improved FCM algorithm added with spatial information, and therefore it removes the meaningless regions like noise. A region-based reclassification based on a similarity between each segmented region of the most inhomogeneous cluster and the other clusters reduces the inhomogeneous clusters more efficiently than pixel- and cluster-based reclassifications. And detecting text candidate regions is performed by genetic algorithm based on energy and variance of the directional edge components, the number, and a size of the segmented regions. The region information-based detection method can singles out semantic text candidate regions more accurately than pixel-based detection method and the detection results will be more useful in recognizing the text regions hereafter. Experiments showed the results of the segmentation and the detection. And it confirmed that the proposed method was superior to the existing methods.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.389-401
• /
• 2001

This paper proposes an abstraction mechanism of the low-level digital video features for the automatic retrievals of the explosion scenes from the digital video library. In the proposed abstraction mechanism, the regional dominant colors of the key frame and the motion energy of the shot are defined as the primary abstractions of the shot for the explosion scene retrievals. It is because an explosion shot usually consists of the frames with a yellow-tone pixel and the objects in the shot are moved rapidly. The regional dominant colors of shot are selected by dividing its key frame image into several regions and extracting their regional dominant colors, and the motion energy of the shot is defined as the edge image differences between key frame and its neighboring frame. The edge image of the key frame makes the retrieval of the explosion scene more precisely, because the flames usually veils all other objects in the shot so that the edge image of the key frame comes to be simple enough in the explosion shot. The proposed automatic retrieval algorithm declares an explosion scene if it has a shot with a yellow regional dominant color and its motion energy is several times higher than the average motion energy of the shots in that scene. The edge image of the key frame is also used to filter out the false detection. Upon the extensive exporimental results, we could argue that the recall and precision of the proposed abstraction and detecting algorithm are about 0.8, and also found that they are not sensitive to the thresholds. This abstraction mechanism could be used to summarize the long action videos, and extract a high level semantic information from digital video archive.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.646-654
• /
• 2007

In recent years, the use of text inserted into TV contents has grown to provide viewers with better visual understanding. In this paper, video text is defined as superimposed text region located of the bottom of video. Video text extraction is the first step for video information retrieval and video indexing. Most of video text detection and extraction methods in the previous work are based on text color, contrast between text and background, edge, character filter, and so on. However, the video text extraction has big problems due to low resolution of video and complex background. To solve these problems, we propose a method to extract text from videos using the Harris corner detector. The proposed algorithm consists of four steps: corer map generation using the Harris corner detector, extraction of text candidates considering density of comers, text region determination using labeling, and post-processing. The proposed algorithm is language independent and can be applied to texts with various colors. Text region update between frames is also exploited to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.375-384
• /
• 2011

This paper suggests a method to recognize facial expressions of animation characters by means of dominant colors and feature points. The proposed method defines a simplified mesh model adequate for the animation character and detects its face and facial components by using dominant colors. It also extracts edge-based feature points for each facial component. It then classifies the feature points into corresponding AUs(action units) through neural network, and finally recognizes character facial expressions with the suggested AU specification. Experimental results show that the suggested method can recognize facial expressions of animation characters reliably.