The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recently, a lot of research on the use of big data is made, and this paper was aimed to perform classification experiments using CNN for the detected object collected from traffic detectors. In addition the experimental results were compared with the HOG descriptor that is commonly used in existing pedestrian and object classification and wavelet, texture and descriptor that are used in the road surface...
In few decades, text detection methods have been proposed with significant results. Yet, most of them are only implemented for certain language. Thus, this work proposes a text detection method for multi language text. To do such a task, a Fast Stroke Width Transform (FSWT) is introduced. FSWT is a robust local image operator for text detection with complex background. It is improved version of Stroke...
Obscene video detection is a core technology to prevent inappropriate access of children or teenagers to obscene video contents. There are many obscene video or image detection methods such as skin region analysis based methods, global histogram based methods. However, accuracy of these methods are not high enough to be deployed in the real-world environment. In this paper, we propose an obscene video...
This paper describes an efficient and accurate method using two 2-Dimensional bandpass filtered signals for edge detection of images, which are obtained by decomposing an image into two high frequency subband images in wavelet domain. Simulation results show that the proposed method has high accuracy in detecting the edge areas of image as is compared to existing methods. It provides new insights...
In this paper, a novel method to automatically detect mosaic masking regions in an input image is proposed. Mosaic masking region can be used as an important clue for recognizing commercial pornographic images. The proposed method is composed of three steps. The first step is to extract SRE features using a new cross-shaped feature characteristic, and the second step is to estimate the parameters...
In foggy video, the visibility and contrast of objects are decreased dramatically, which causes the performance degradation of traffic monitoring systems. In this paper, an architecture for real-time traffic monitoring system is presented for foggy video. For the real-time traffic monitoring, it is required to satisfy two major constraints. First, the quality of an image after fog removal is good...
We introduce our initial design of gesture interface for the TV control of visually impaired users, with its implementation and user study. Two bare-hand gesture sets were designed using simple linear and circular motions of arms. For the two gesture sets, a rule-based recognition system was developed using a Kinect sensor. In a user study, the linear and circular gesture sets on our recognition system...
In this paper, we proposed an improved optical scattering tomography for optically dense media. We model a material by many layers with voxels, and light scattering by a distribution from a voxel in one layer to other voxels in the next layer. Then we write attenuation of light along a light path by an inner product of vectors, and formulate the scattering tomography as an inequality constraint optimization...
This paper proposes the image matching method that can match rigid object image and non-rigid object image by utilizing the same feature. To this end, first determines the matching of a rigid object image through geometric verification and then discriminate the non-rigid deformable image from the verified result by using supervised learning. Lastly, this paper proposes the method to match a non-rigid...
Optical tomography provides visual images of the interior of objects. There are various methods depending on how the material behaves under scattering. If scattering is weak, one approach extracts the scattering amplitudes from the inputed projected images and estimates a cross-sectional image from images without scattering. Conversely, if the scattering is strong, an approach is to use the scattering...
A Color Image Scale is one of useful resources for allowing designer the expression of mood through the color combination. This study proposes a method for estimating the mood in Color Image Scale from three color combinations by using machine learning technique. After we find the correlation between the mood and the properties of color combination, we extract three dominant colors from an image....
In this paper, the authors describe on an omnidirectional 3D measurement using double fish-eye stereo vision. This vision system consists of two stereo visions which are back to back each other. In the method, the image from the fish-eye vision is transformed into panoramic image and a parallax is detected by simple template matching to the transformed image. Using the method, three dimensional measurement...
This paper presents a novel approach to detecting tumor in the brain magnetic resonance images using regional features. First, the proposed algorithm segments head area and skull area using average of brain magnetic resonance images and local adaptive threshold technique. Next, super-pixel segmentation algorithm is applied in order to generate categorized regions on the segmented brain image. Second,...
Fishers linear discriminant analysis (FLDA) is one of the well-known methods to extract the best features for multi-class discrimination. Recently Kernel discriminant analysis (KDA) has been successfully applied in many applications. KDA is one of the nonlinear extensions of FLDA and construct nonlinear discriminant mapping by using kernel functions. Otsu derived the optimum nonlinear discriminant...
This paper presents a new way of text region detection on the basis of Canny edge detection and connected component. A Canny edge image is detected from a gray image obtained from an original color image. The Canny image is partitioned into n × n blocks and each n × n block is divided into smaller m × m blocks. If there are sufficient edge pixels in the m × m block, then the block is set to text candidate...
The detection of moving objects is the first step in video surveillance systems. But due to the challenging backgrounds such as illumination conditions, color saturation, and shadows, etc., the state of the art methods do not provide accurate segmentation using only a single camera. Recently, subspace learning model such as Robust Principal Component analysis (RPCA) shows a very nice framework towards...
This study targets the process that forms three-dimensional plastic film from a two-dimensional printed arbitrary pattern. When three dimensional film is formed from two dimensional, expansions and contractions occurs. In this paper, we introduce an automatic printing system that form two-dimensional film includes partial expands and contractions to observe it naturally in three-dimensions. Our key...
An Image matching technique of target objects recognition and detection is widely used in industrial image processing. In this paper, the authors proposed eigen template method for two dimentional target objects recognition and detection. We have proposed eigen template method of applying the principal component analysis (PCA) to image matching. Also, the authors have proposed to edge based eigen...
In this paper, a novel method to automatically classify an pornographic video using fast motion features is proposed. In proposed method, predefined number of clips without a shot change are extracted from an input video and new, fast motion features are computed for each clip. Each clip is given a pornographic possibility based on motion distribution information. If the possibility is bigger than...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.