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.
Vehicle Video detection is an important part of intelligent transportation system for its characteristics of effectiveness and accuracy, and it provides important data for the security of urban traffic operation. However, in order to improve the reliability of vehicle detection in the traffic video detection system, in this paper, a pulse-coupled neural network (PCNN) is used for the image segmentation...
Forest stands are important forest management units for many forestry applications. Airborne Laser Scanning (ALS), also known as Light Detection and Ranging (LiDAR), provides abundant information on vertical structures of forests, and it is more stable than the conventional aerial or satellite spectral imaging in various conditions. In order to obtain accurate Forest Stand Delineations (FSD), a method...
Contour extraction of stone slabs is the first-step for optimization of cutting the irregular stone slab in real time. A color image segmentation method to extract the stone slab contour in the complex background is proposed. Firstly, we define a sample window and detecting window in HSI color image space, and extract the image feature of sample window as the prior knowledge. Traverse the whole image...
The facial features segmentation based on image information, due to the influence of illumination, posture variation and expression, segmentation accuracy is literally not too inspiring. Using 3D face model is one of the effective approaches to tackle the problems above. In this paper, an effective method of 3D facial features segmentation based on the geometric features and statistical features of...
This paper presents a novel system for vision-based driving posture recognition. The driving posture dataset was prepared by a side-mounted camera looking at a driver's left profile. After pre-processing for illumination variations, eight action classes of constitutive components of the driving activities were segmented, including normal driving, operating a cell phone, eating and smoking. A global...
Rising admissions in the South African institutions of higher education have enlarged student-to-lecturer ratios and increased the lecturer's workload, already burdened by administrative tasks. After marking tests, lecturers usually fill in a document called the cover page where the student's number, name and marks according to the questions are placed. Once this is done, they will have to recopy...
Thresholding segmentation is a critical preprocessing step on many image processing applications. However, most of the existing thresholding methods can only deal with an image with some special histogram patterns. To automatically determine the robust and optimum thresholds for the images with various histogram patterns, this paper proposes a new thresholding segmentation method based on maximum...
As an efficient pre-processing technology, superpixel has been widely used in image segmentation, which improves the final results and reduces the complexity of the subsequent processing tasks. This paper presents an interactive image segmentation method based on the hierarchical superpixels initialization and region merging. It firstly proposes a novel hierarchical superpixels initialization framework...
Generating region outlines from grayscale images using contour generation algorithms is one of the basic methods for image segmentation. The results can be used in 3D reconstruction from contours. The algorithm proposed in this paper which uses templates can effectively deal with the cases when contours pass through grid points and reach image boundaries.
Oil spill detection becomes very important nowadays, due to the importance of oil and to prevent pollution caused by oil leakage. Synthetic Aperture Radar (SAR) images show oil spill boundaries clearly. An oil spill appears as an obscure spot in SAR images. Therefore, thresholding is considered the best method to extract this patch and define its boundaries clearly. This paper proposes a novel thresholding...
In this paper, we propose LinedCut: a novel method for interactive image segmentation which requires only a single line drawing to identify the object of interest in the image. The handy interaction mode can address the problem of object scale very well. Our approach consists of the following three steps: first, a given image is over-segmented into superpixels using superpixel algorithm; secondly,...
Writing-in-the-air (WIA) system provides a novel input experience using the fingertip as a virtual pen based on the color and depth information from only one Kinect camera. We present a new fingertip detection and tracking framework for the robust and realtime fingertip position estimation and further improve the air-writing character recognition accuracy. Firstly, we propose a new physical constraint...
Traffic video surveillance cameras are widely used in China today. However, the resolution of the output video is very low and it is difficult to recognize the license number of the vehicles that broke traffic regulations. The Super-resolution image reconstruction techniques thus can be used to solve this problem. In this paper, we examine several important superresolution algorithms and developed...
Color image segmentation is an important topic in the image processing field. In most segmentation methods based on MRF-MAP, the segmentation quality is far behind requirement due to the absence of appearance models, and it is often suffering from the low computational efficiency of iterated calculations. To address these problems, the paper proposes a new segmentation method for color images based...
Fuzzy clustering techniques, especially Fuzzy C-Means clustering method (FCM), is a popular algorithm widely used in the images segmentation. However, as the conventional FCM doesn't optimize data in feature space and doesn't involve any spatial information, it is sensitive to the noise. In the paper, we presented a novel FCM clustering algorithm based on kernel spatial information to segment the...
Image dehazing has always been a focus of wide attention in recent years with great breakthrough. However, the existed algorithms may produce noise and color distortion in the process of image restoration, especially in the sky region. In this paper, an improved dark channel prior algorithm is proposed, which detects the sky firstly and divides the image into sky region and nonsky region, and then...
In order to speed up the convergence of GrabCut algorithm and enhance the accuracy of segmentation, this paper puts forward an algorithm of GrabCut color image segmentation based on region of interest (ROI). The user selects a ROI by dragging a rectangle. The GrabCut algorithm is used in ROI only. The object is then extracted automatically. The experimental results demonstrate that the new algorithm...
Caption texts in news video highly summarize the related news story and can be used for effective retrieval. This paper presents an effective caption location method based on edge detection and an improved caption segmentation method combined with Otsu and K-means clustering algorithm. Experiment results show that the caption location method performs well in the news video and the caption segmentation...
In image processing to achieve de-noising is an important task. The main thing in image de-noising is to attain edges of image. Many algorithms and methods have been proposed recently but they have not yet achieved the desired level. Among these block matching 3D (BM3D) is the method which is considered best to remove noise as compared to previous techniques. Before BM3D technique, Non Local Means...
We propose a shape-adaptive wavelet-based finite ridgelet coding method, which can efficiently code an arbitrarily shaped video object. Mechanism of SA-FRIT on the shape adaptive ridgelet transform are discussed, based on the mask images on video object shape adaptive ridgelet three level decomposition. The existing SPIHT was improved, compression method proposed an extension of SPIHT. The method...
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.