• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.677-680
• /
• 2016

In computer vision and image processing, feature detection and description are essential parts of many applications which require a representation for objects of interest. Applications like object recognition or motion tracking will not produce high accuracy results without good features. Due to its importance, research on image feature has attracted a significant attention and several techniques have been introduced. This paper provides a review on well-known image feature detection and description techniques. Moreover, two experiments are conducted for the purpose of evaluating the performance of mentioned techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.524-543
• /
• 2022

Correct facade image parsing is essential to the semantic understanding of outdoor scenes. Unfortunately, there are often various occlusions in front of buildings, which fails many existing methods. In this paper, we propose an end-to-end deep network for facade parsing with occlusions. The network learns to decompose an input image into visible and invisible parts by occlusion reasoning. Then, a context aggregation module is proposed to collect nonlocal cues for semantic segmentation of the visible part. In addition, considering the regularity of man-made buildings, a repetitive pattern completion branch is designed to infer the contents in the invisible regions by referring to the visible part. Finally, the parsing map of the input facade image is generated by fusing the results of the visible and invisible results. Experiments on both synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art methods in parsing facades with occlusions. Moreover, we applied our method in applications of image inpainting and 3D semantic modeling.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1220-1230
• /
• 2015

An autonomous valet parking (AVP) system is designed to locate a vacant parking space and park the vehicle in which it resides on behalf of the driver, once the driver has left the vehicle. In addition, the AVP is able to direct the vehicle to a location desired by the driver when requested. In this paper, for an AVP system, we introduce technology to recognize a parking space using image sensors. The proposed technology is mainly divided into three parts. First, spatial analysis is carried out using a height map that is based on dense motion stereo. Second, modelling of road markings is conducted using a probability map with a new salient-line feature extractor. Finally, parking space recognition is based on a Bayesian classifier. The experimental results show an execution time of up to 10 ms and a recognition rate of over 99%. Also, the performance and properties of the proposed technology were evaluated with a variety of data. Our algorithms, which are part of the proposed technology, are expected to apply to various research areas regarding autonomous vehicles, such as map generation, road marking recognition, localization, and environment recognition.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.417-424
• /
• 2022

In this paper, the developed trunk cargo unloading automation system is introduced, and the RGB-D sensor-based box loading situation recognition method and unloading plan applied to this system are suggested. First of all, it is necessary to recognize the position of the box in a truck. To do this, we first apply CNN-based YOLO, which can recognize objects in RGB images in real-time. Then, the normal vector of the center of the box is obtained using the depth image to reduce misrecognition in parts other than the box, and the inner wall of the truck in an image is removed. And a method of classifying the layers of the boxes according to the distance using the recognized depth information of the boxes is suggested. Given the coordinates of the boxes on the nearest layer, a method of generating the optimal path to take out the boxes the fastest using this information is introduced. In addition, kinematic analysis is performed to move the conveyor to the position of the box to be taken out of the truck, and kinematic analysis is also performed to control the robot arm that takes out the boxes. Finally, the effectiveness of the developed system and algorithm through a test bed is proved.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.649-654
• /
• 2005

In this paper, we describe an implementation of real-time face recognition system under ubiquitous computing environments. First, face image is captured by PDA with CMOS camera and then this image with user n and name is transmitted via WLAN(Wireless LAN) to the server and finally PDA receives verification result from the server The proposed system consists of server and client parts. Server uses PCA and LDA algorithm which calculates eigenvector and eigenvalue matrices using the face images from the PDA at enrollment process. And then, it sends recognition result using Euclidean distance at verification process. Here, captured image is first compressed by the wave- let transform and sent as JPG format for real-time processing. Implemented system makes an improvement of the speed and performance by comparing Euclidean distance with previously calculated eigenvector and eignevalue matrices in the learning process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.2
• /
• pp.376-381
• /
• 2009

The image data compression, recognition, restoration, etc. are parts of the digital image processing technology. In the process by various devices, noises would be made. Because the noise could damage the image, we use the image filter to preserve the original image from the noise. The image filter used in digital image process basically has a two-dimensional structure. There an two methods of creating the filter - One is reiterating one dimension and the other is using an indivisible two-dimension image filter. The image filter is being widely used along with one-dimension filter according to each noise, and various median filters are being used to remove the impulse noise. In this paper, I suggested a powerful modified median filter, and compared with conventional filters for objective verification.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.759-768
• /
• 2005

This paper describes an algorithm that can recognize gestures constructing subspace gesture symbols with hybrid feature information. The previous popular methods based on geometric feature and appearance have resulted in ambiguous output in case of recognizing between similar gesture because they use just the Position information of the hands, feet or bodily shape features. However, our proposed method can classify not only recognition of motion but also similar gestures by the partial feature information presenting which parts of body move and the global feature information including 2-dimensional bodily motion. And this method which is a simple and robust recognition algorithm can be applied in various application such surveillance system and intelligent interface systems.

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.239-244
• /
• 2016

Mugshot face images, routinely collected by police, usually contain both frontal and profile views. Existing automated face recognition methods exploited mugshot databases by enlarging the gallery with synthetic multi-view face images generated from the mugshot face images. This paper, instead, proposes to match the query arbitrary view face image directly to the enrolled frontal and profile face images. During matching, the 3D face shape model reconstructed from the mugshot face images is used to establish corresponding semantic parts between query and gallery face images, based on which comparison is done. The final recognition result is obtained by fusing the matching results with frontal and profile face images. Compared with previous methods, the proposed method better utilizes mugshot databases without using synthetic face images that may have artifacts. Its effectiveness has been demonstrated on the Color FERET and CMU PIE databases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.1
• /
• pp.73-80
• /
• 1994

Fourier Descriptors(FD) is a common way for representing the boundary of an object. In this paper, an algorithm has been implemented to do object recognition by using FD. This is applied to various tool object, and is tested. This implementation contains two parts: image acquisition and object recognition. Appropriate lighting, viewing angle, and strong contrast of background and object are taken into account in this aspect. Minimum distances are calculated by using FD's and boundary matching among objects on the process of object recognition. Rotation, translation and scaling of the object will not influence the performance of the algorithm. Experiments show that we can use only one fourth of 1024 FD coefficients to do raped object recognition.